Accurate Detection of Brain Tumor Using Optimized Feature Selection Based On Deep Learning Techniques

Multimedia Tools and Applications (2023) 82:44623–44653
https://doi.org/10.1007/s11042-023-15239-7
Accurate detection of brain tumor using optimized feature

selection based on deep learning techniques
Praveen Kumar Ramtekkar1 · Anjana Pandey1 · Mahesh Kumar Pawar1
Received: 6 September 2021 / Revised: 12 March 2023 / Accepted: 30 March 2023 /

Published online: 25 April 2023
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023
Abstract
An unusual increase of nerves inside the brain, which disturbs the actual working of
the brain, is called a brain tumor. It has led to the death of lots of lives. To save people
from this disease timely detection and the right cure is the need of time. Finding of
tumor-affected cells in the human brain is a cumbersome and time- consuming task.
However, the accuracy and time required to detect brain tumors is a big challenge in
the arena of image processing. This research paper proposes a novel, accurate and opti-
mized system to detect brain tumors. The system follows the activities like, preproc-
essing, segmentation, feature extraction, optimization and detection. For preprocessing
system uses a compound filter, which is a composition of Gaussian, mean and median
filters. Threshold and histogram techniques are applied for image segmentation. Grey
level co-occurrence matrix (GLCM) is used for feature extraction. The optimized con-
volution neural network (CNN) technique is applied here that uses whale optimiza-
tion and grey wolf optimization for best feature selection. Detection of brain tumors is
achieved through CNN classifier. This system compares its performance with another
modern technique of optimization by using accuracy, precision and recall parameters
and claims the supremacy of this work. This system is implemented in the Python pro-
gramming language. The brain tumor detection accuracy of this optimized system has
been measured at 98.9%.
Keywords Brain tumor · CNN · GLCM · Histogram segmentation · Particle swarm

optimization (PSO) · Whale optimization algorithm (WOA) · Gray wolf optimization
(GWO)
* Praveen Kumar Ramtekkar

[email protected]
Anjana Pandey
[email protected]
Mahesh Kumar Pawar
[email protected]
1
University Institute of Technology, Rajiv Gandhi Proudyogiki Vishwavidyalaya, Bhopal,
Madhya Pradesh, India
13
Vol.:(0123456789)
44624 Multimedia Tools and Applications (2023) 82:44623–44653
1 Introduction
The brain is a complex organ which controls every process that regulates our body.
Together, the brain and spinal cord that extends from it make up the central nervous sys-
tem. The cells of brain grow unusually and the mechanism which controls normal cells
is not able to stabilize progress of brain’s cells, which causes brain tumor. Tumor lodges
space in skull, which disturbs usual working of brain and makes stress on brain. Because of
higher stress on brain, several brain tissues are moved, pushed against skull and becomes
liable for harm of nerves of other healthy brain’s tissues [16]. Brain tumors are mainly
classified as benign and malignant tumors. As per the investigation of the World Health
Organization (WHO), 120 types of brain tumors are reported based on cell origin and cell
behavior from less aggressive to more aggressive. Brain tumors are mainly classified as
benign and malignant tumors. Benign tumors grow inside the brain and are non-cancerous
and malignant or cancerous.
Today, the involvement of Information Technology (IT) and e-health care techniques
in the medical arena support physicians to deliver superior quality health services to the
diseased. Tumor in brain disturbs the human brain critically, due to unusual increasing of
cells in the brain. It disturbs the regular working of the brain and might be fatal for life. A
brain tumor is typical cancer in human beings, which is directly related to death. Therefore,
timely detection of this disease is the need of time and plays a significant part in dropping
the death rate.
The exact method to understand the brain tumor and its stages is a main job to prevent
and to carry out the steps in curing the disease. For this magnetic resonance imaging (MRI)
is widely used by physicians to analyze brain tumors. The result of the analysis carried out
in this paper reveals whether the brain is normal one or tumor infected by applying the
deep learning techniques. Several techniques of medical imaging such as Ultra Sound, Sin-
gle-Photon Emission Computerized Tomography (SPECT), Computed Tomography (CT)
Scan, X-Rays, Positron Emission Tomography (PET) and Magnetic Resonance Imaging
(MRI) have been applied for the identification of brain tumors [5]. In relation to another
imaging process, MRI is commonly used since it provides better contrast of brain MRI
images and malignant tissues. Hence, identification of brain tumors is frequently done via
MRI images [3]. Analyzing the MRI scan image is the modern technique to detect the pres-
ence of a brain tumor at its early stage. Preprocessing also performs an important role in
identifying the tumor in brain cancer detection. Conversion of segmented MRI image into
a group of features are known as feature extraction. Pre-processing is applied to this system
to reduce the noise and artifact from the image. Next, histogram and threshold techniques
are used to segment the tumor area which is located on a non-uniform basis. GLCM is used
for feature extraction after the segmentation. Optimization is the process of obtaining the
best results in minimum effort. A WOA and GWO algorithms are proposed for the selec-
tion of the best image features from the features obtained by GLCM.
In this research paper, the detection of brain tumor is done by using deep learning tech-
niques. When these techniques are applied on the MRI images, the detection of brain tumor
is done very fast and a higher accuracy helps in providing the treatment to the patients.
These prediction also assists the physicians in making quick decisions. In this proposed
system CNN is applied with whale optimization in detecting the presence of brain tumor.
In CNN the dimension of the image is reduced at every CNN layer without the loss of
information needed for training. Different processing task like zero padding, convolution,
batch normalization, ReLU, max pooling, flatten and dense are applied for creating the
CNN model. Finally the performance of this system is compared with other systems that
13
Multimedia Tools and Applications (2023) 82:44623–44653 44625
uses deep learning and optimization techniques for brain tumor identification. This work
justifies that system based on deep neural network give promising results in detection accu-
racy of brain tumor via image processing techniques. Optimization techniques have been
applied with deep neural network models to set optimized values for model parameters like
accuracy, precision, recall and F-Score. This combination of the use of optimization tech-
niques with deep neural network enhances the performance of the system by converging it
faster. These optimization algorithms proves their efficacy in tumor detection. Therefore,
to take the advantage of optimization algorithm, this system uses the whale optimization
technique with CNN to improve the brain tumor detection accuracy and processing speed.
This research work is divided into seven sections. Section 1, Introduction, briefs this
proposed research work. Section 2, Literature Review, describes the existing work related
to this proposed work. Section 3, Methods and Materials, includes details of MR images,
datasets, and proposed architecture of brain tumor detection, WOA, GWO algorithm and
CNN. Section 4, Results and discussion, describes the results obtained by using PSO,
genetic algorithm (GA), GWO and WOA algorithms along with CNN classifier based on
accuracy, precision, recall and F-score parameters. Section 4, Performance Comparison,
compares the results based on the accuracy of proposed and exiting work. At last, conclu-
sion has been drawn.
2 Literature survey
Tumor detection in an MRI brain image in the field of medical science is a challenging and
hard task. Researchers are involved in this field to acquire the best results and techniques
to identify tumors. Today deep learning-based optimization techniques contribute excellent
results and the practice of using CNN is increasing day by day.
Geetha A, et al. (2019) [7] proposes a new accurate brain tumor detection model. The
model includes certain processes such as preprocessing, segmentation, feature extraction
and classification. Initially, two main processes contrast enhancement and skull stripping
have been processed. The fuzzy C-means clustering (FCM) algorithm has been used for the
segmentation. GLCM and grey-level run-length matrix (GRLM) features were extracted
in the feature extraction phase. Moreover, this system uses a deep belief network (DBN)
for classification. The optimized DBN concept is used here, for which GWO is used.
The proposed model is termed as GW-DBN model. This proposed model compares its
performance over other conventional methods in terms of accuracy, specificity, sensitiv-
ity, precision, negative predictive value (NPV), F1-Score and Matthews correlation coef-
ficient (MCC), false negative rate (FNR), false positive rate (FPR) and false discovery
rate (FDR). The results obtained by this model show that the accuracy of GW-DBN was
0.39%, 67.32%, 15.83% and 7.56% better than conventional DBN, naïve Bayesian (NB),
support vector machine (SVM) and neural network (NN), respectively. The sensitivity of
the proposed model was 18.51%, 42.22% and 1.58% superior to NB, SVM and NN, respec-
tively. FNR of GW-DBN was 55.55% and 70.37% better than NB and SVM models. The
F1-Score of the proposed model was 49.01%, 22.35% and 7.56% better than NB, SVM and
NN, respectively. Thus, the performance of proposed model for detecting brain tumor was
proven over other methods.
Sindhu A, et al. (2020) [26] presents a system which applies five steps, i.e., preproc-
essing, segmentation, feature extraction, feature selection (optimization) and classifi-
cation. This system performs preprocessing as an initial step to remove the noises. The
13
segmentation has been used to identify the tumor location. The features extracted from seg-
mented images consist of irrelevant features, which reduces the classification accuracy in
disease identification. Therefore, efficient feature selection method was introduced in this
system to improve the classification performance. For the improvement of results obtained
by feature selection, initially, image segmentation is carried out by using saliency-based
k-means clustering segmentation and then feature extraction is done by using First Order
and Second Order Statistical features by GLCM and GLRM. Further PSO and whale opti-
mization techniques are applied for best feature selection. The results obtained by these
methods indicate the potential advantages of using feature selection techniques to improve
the classification accuracy with a smaller number of feature subset. From the result, it is
concluded that the performance of whale optimization is superior to PSO method for clas-
sification. The machine learning classifiers such as DT, KNN, SVM and AdaBoost with
ensemble KNN-SVM classifier are utilized to classify the tumor as normal or abnormal.
The proposed framework achieves a classification accuracy of 98.3%.
Rammurthy D, et al. (2020) [20] describes an optimization based technique, viz. Whale
Harris Hawks optimization (WHHO) for brain tumor detection using MRI. In this system
segmentation is performed using cellular automata and rough set theory and the image fea-
tures are extracted from the segments, which include tumor size, Local Optical Oriented Pat-
tern (LOOP), Mean, Variance and Kurtosis. Further, the brain tumor detection is carried out
using deep convolution neural network (DCNN), wherein the training is performed using pro-
posed WHHO which has been designed by integrating Whale optimization algorithm (WOA)
and Harris hawks optimization (HHO) algorithm. The WHHO-based DCNN performed well
with accuracy of 0.816, specificity of 0.791 and sensitivity of 0.974, respectively.
Ramtekkar PK, et al. (2020) [21] designs a model for the development of an automatic
system that works on brain MRI images to detect and classify tumors using CNN classi-
fier and deep learning techniques. This proposed model includes series of stages namely
preprocessing, segmentation, feature extraction, tumor detection, tumor classification and
tumor location for detecting and classifying brain tumor. Here, CNN classifier has been
combined with GLCM for the extraction of tumor region. The model also proposes the use
of Partial Differential Equation (PDE) for image clustering, K-means and Otsu threshold-
ing for image segmentation and multi histogram equalization for image enhancement. This
paper reviews various techniques of image classification and concludes their advantages
and disadvantages. The performance of this proposed model has been expected well than
other manual and semi-automatic systems that uses SVM and Artificial Neural Network
(ANN) classifiers. Finally, the model also illustrates that DNN is preferred for brain tumor
detection and classification since it provides higher accuracy than modern techniques.
Hossain T, et al. (2020) [11] proposes a system to distinguish normal and abnormal
pixels, based on texture based and statistical features of an MRI. This system also suggests
a method to extract brain tumor from 2D MRI by FCM algorithm which was followed by
traditional classifiers and CNN. The experimental work of this system has been carried
out on a real-time dataset with diverse tumor sizes, locations, shapes and different image
intensities. Initially, the system uses traditional classifiers namely SVM, K-Nearest Neigh-
bor (KNN), Multilayer Perceptron (MLP), Logistic Regression, NB and Random Forest to
classify the tumor and this work was implemented in scikit-learn. Further, the CNN has
been used to classify the tumor, which was implemented in Keras and Tensorflow. This
system with CNN yields better performance than the traditional classifier. The use of CNN
gained an accuracy of 97.87%, which is quite compelling.
Mishra PK, et al. (2021) [18] recommends a model which observes that earlier DCNN
models do not consider the weights as of learning instances which may decrease accuracy
13
levels of the segmentation procedure. This paper suggested the framework for optimiz-
ing the network parameters such as weight and bias vector of DCNN models using swarm
intelligent based algorithms like Genetic Algorithm (GA), PSO, GWO and WOA. The
simulation results of this model reveals that the WOA optimized DCNN segmentation
model is outperformed than other three optimization based DCNN models i.e., GA-DCNN,
PSO-DCNN, GWO-DCNN. DCNN classifier with whale optimization for the detection of
brain tumors with an accuracy of 98%. This paper compares the accuracy obtained by PSO,
GWO, WAO and GA.
Irmak E (2021) [12] creates a system to make multi classification of brain tumors for the
initial diagnosis purposes using CNN. For this three different CNN models are proposed
for three different classification of tumor. The first CNN model achieves 99.33% accuracy.
Second model classifies the brain tumor into five types as normal, glioma, meningioma,
pituitary and metastatic with an accuracy of 92.66%. The third model classifies the tumors
into three grades as Grade II, Grade III and Grade IV with an accuracy of 98.14%. The
important hyper parameters of CNN models are automatically designated using the grid
search optimization algorithm. This CNN models are compared with other popular state-
of-the-art CNN models such as AlexNet, Inceptionv3, ResNet-50, VGG-16 and GoogleNet.
Satisfactory classification results are obtained using large and publicly available clinical
datasets. The proposed CNN models can be employed to assist physicians and radiologists
in validating their initial screening for brain tumor multi-classification purposes.
Sharma AK et al. (2022) [25] develops the DL architectures such as recurrent networks
and CNN (ConvNets), which are proven appropriate for non-handcrafted extraction of
complex features in skin image. To additional expand the efficiency of the ConvNet mod-
els, a cascaded ensemble network that uses an integration of ConvNet and handcrafted fea-
tures based multi-layer perceptron has proposed in this paper. This model utilizes the CNN
model to mine non-handcrafted image features, color moments and texture features as
handcrafted features. It is demonstrated that accuracy of ensemble DL model is improved
to 98.3% from 85.3% of CNN model.
Verma SS et al. (2021) [27] The Coronavirus Disease 2019 (COVID-19) outbreak has a
devastating impact on health and the economy globally, that’s why it is critical to diagnose
positive cases rapidly. Currently, the most effective test to detect COVID-19 is Reverse
Transcription-polymerase chain reaction (RT-PCR) which is time-consuming, expensive
and sometimes not accurate. It is found in many studies that, radiology seems promising
by extracting features from X-rays. COVID-19 motivates the researchers to undergo the
deep learning process to detect the COVID- 19 patient rapidly. This paper has classified
the X-rays images into COVID- 19 and normal by using multi-model classification process.
This multi-model classification incorporates Support Vector Machine (SVM) in the last
layer of VGG16 Convolution network. For synchronization among VGG16 and SVM we
have added one more layer of convolution, pool, and dense between VGG16 and SVM.
Further, for transformations and discovering the best result, we have used the Radial Basis
function. CovXmlc is compared with five existing models using different parameters and
metrics. The result shows that our proposed CovXmlc with minimal dataset reached accu-
racy up to 95% which is significantly higher than the existing ones. Similarly, it also per-
forms better on other metrics such as recall, precision and F-score.
Khan AH, et al. (2022) [14] Observed that brain tumors may be one of the serious of
psychiatric complications like, depression and panic attacks. Early detection of a brain
tumor is more effective in tumor healing. The medical image processing plays an important
role in assisting humans in identifying different diseases. Classification of brain tumors
is a significant part that depends on the expertise and knowledge of the physician. An
13
intelligent system for detecting and classifying brain tumors is essential to help physicians.
The novel feature of the study is the division of brain tumors into glioma, meningioma, and
pituitary using a hierarchical deep learning method. The diagnosis and tumor classifica-
tion are significant for the quick and productive cure and medical image processing using
a CNN is giving excellent outcomes in this capacity. CNN uses the image fragments to
train the data and classify them into tumor types. Hierarchical Deep Learning-Based Brain
Tumor (HDLBT) classification is proposed with the help of CNN for the detection and
classification of brain tumors. The proposed system categorizes the tumor into four types:
glioma, meningioma, pituitary and no-tumor and achieves 92.13% precision and miss rate
of 7.87%.
Gunasekara SR et al. (2021) [9] States that the main requirements of tumor extraction
are the annotation and segmentation of tumor boundaries correctly. To fulfill this purpose,
the paper presents a threefold DL architecture. First, the classifiers are implemented with
a DCNN and second a region-based CNN (R-CNN) is performed on the classified images
to localize the tumor regions of interest. At third stage, the concentrated tumor boundary
is contoured for the segmentation by using the Chan-Vese segmentation algorithm. As the
typical edge detection algorithms based on gradients of pixel intensity tend to fail in the
medical image segmentation process, an active contour algorithm defined with the level
set function is proposed. Specifically, the Chan-Vese algorithm was applied to detect the
tumor boundaries for the segmentation process. To evaluate the performance of the overall
system, Dice Score, Rand Index (RI), Variation of Information (VOI), Global Consistency
Error (GCE), Boundary Displacement Error (BDE), Mean Absolute Error (MAE), and
Peak Signal to Noise Ratio (PSNR) were calculated by comparing the segmented bound-
ary area which is the final output of the proposed, against the demarcations of the subject
specialists which is the gold standard. Overall performance of the proposed architecture
for both glioma and meningioma segmentation is with an average Dice Score of 0.92 (also,
with RI of 0.9936, VOI of 0.0301, GCE of 0.004, BDE of 2.099, PSNR of 77.076, and
MAE of 52.946), pointing to the high reliability of the proposed architecture.
Avsar E (2019) [2] observed that the MRI is a useful method for the diagnosis of tumors
in human brain. Under this system, MRI images have been analyzed to detect the regions
containing tumor and classify these regions into three different tumor categories like, men-
ingioma, glioma and pituitary. DL is a relatively recent and powerful method for image
classification. Therefore, this system has used faster Region-based CNN, which is based on
DL techniques. The proposed system was implemented using TensorFlow library. A pub-
licly available dataset containing 3064 MRI brain images (708 meningioma, 1426 glioma,
930 pituitary) of 233 patients has been used to train and test classifier. This system yields
an accuracy of 91.66% which is higher than other system using the same dataset.
Ramtekkar PK, et al. (2023) [22] proposes novel, precise and optimized system to detect
brain tumors. This system includes preprocessing, segmentation, feature extraction, optimi-
zation and detection steps. The compound filter has been designed by applying Gaussian,
mean and median filters for preprocessing. Threshold and histogram techniques have been
applied for image segmentation. GLCM has used for feature extraction. The optimized
CNN was applied along with ant colony optimization (ACO), bee colony optimization
(BCO), PSO, GA, GWO and WOA for best feature selection. Detection of brain tumors is
achieved through CNN classifiers. Performance of this system has been compared using
accuracy, precision and recall parameters. The accuracy of this optimized system was
measured at 98.9%.
Based on the literature survey presented above, the following drawbacks are observed
by the previous methodologies used:
13
• The basic difficulties of the previous methods were binary categorization of tumors
which creates further ambiguity for the physicians. Due to a lack of data, physicians fail
to get reliable results.
• It is observed that tumor detection using brain MRI is a difficult task due to two rea-
sons. The first, brain tumors exhibit a great degree of variability in size, severity and
form. The second, tumors come in various pathological varieties, showing the same
symptoms. These difficulties are not covered by the previous methods.
• The former methods which applied deep learning had improved tumor detection accu-
racy but they needed a large amount of training data for analysis. However, the compu-
tational cost and training time associated with brain tumor detection were substantial.
• In the earlier methods segmentation and detection of tumor areas from brain MRIs was
complicated and time consuming for analysis. However, the accuracy is significantly
improved for the identification of brain tumors.
• The prior methods which used genetic algorithms needed less data to detect brain
tumors, but it may be challenging to eliminate the objective function. Genetic algo-
rithms are time consuming and non-deterministic. Therefore, each time you run the
algorithm on the same samples of data, the solutions they provide can differ.
Following are the main contributions of this novel optimized system:
• Making familiar scientific community and new researchers with brain tumor detection
techniques based on optimization and deep learning concept.
• Spreading awareness with the specific use of optimization techniques in brain tumor
detection.
• Developing the idea for a new technique which can be a combination of deep learning
and optimization algorithm for brain tumor detection.
• Providing information regarding optimization techniques to detect brain tumor in
human.
• Presenting a combination of CNN and WOA for the detection of brain tumor.
• Providing sufficient information to young researchers, scientists, technocrats about dif-
ferent optimization techniques such as WOA, GWO, PSO, GA, etc. and working of
CNN for brain tumor detection.
• The proposed system will be helpful to develop the Binary and multi-objective variants
of this system for brain tumor detection in future.
• Finally, the proposed CNN models can be employed to assist physicians in validating
their initial screening for brain tumor multi-classification purposes.
3 Methods and materials
3.1 Magnetic resonance imaging (MRI) scanning
Lots of scanning methods such as CT scan, PET, MRI, etc. are used to study brain tumors.
At present, MRI is mostly the preferred imaging method, as it produces images of high
resolution, which helps to extract features clearly. It is also useful for the visualization of
pathological and physiological changes of live tissues. Aims behind the use of MRIs for
brain tumors imaging are [17].
13
• It does not use Ionizing radiation.

• Its resolution is high.
• It generates 3D images, which helps to generate complex tumor localization.
• Power of achievement of structural and functional data of tumor throughout the same scan.
These days, MRI is the utmost demanded radiological imaging technique, because it
helps the internal structure of the brain to be viewed with few details. It helps in detecting,
descent contrast among dissimilar soft tissues of the brain, which makes it suitable to offer
brain images of moderate quality as compared to alternate techniques of imaging (https://
case.edu/med/neurology/NR/MRI%20Basics.htm).
3.2 Dataset
For the practical work of this proposed work, we collected 253 brain MRI images online
from Kaggle (https://www.kaggle.com) dataset for brain tumor detection. Our dataset con-
tains two classes – Yes and No. Class Yes and No represents tumor and non-tumor images.
There are 155 images in class Yes and 98 in Class No. All these images are MRI images
from various modalities, such as T1, T2, Fluid-attenuated inversion recovery (FLAIR) [10].
The size of each image is (128, 128) exactly in axial view. All the images of the dataset
are available at: https://www.kaggle.com/navoneel/brain-mri-images-for-brain-tumor-detec
tion. Further, the dataset size is augmented to 2318 images. Out of these images, 1622 have
been used for training, 348 for testing and 348 have been utilized for validation.
3.3 Proposed architecture of brain tumor detection
Brain tumor detection in the early phase is an important task for the reduction of casualties of
patients. In this system architecture based on deep learning techniques has been introduced,
which is a combination of image classification and deep learning techniques. Convolution
neural network with whale and wolf optimization is used for brain tumor detection. The
detection of brain tumors is done in four steps: preprocessing, segmentation, feature extrac-
tion, CNN-based optimization and detection. The proposed architecture is depicted in Fig. 1.
3.3.1 Preprocessing
Processing the MRI is cumbersome task. Before processing MRI, it is necessary to remove
unnecessary artifacts in MRI. After the elimination of unnecessary noise, MRI becomes
ready for further processing [10]. Preprocessing includes grayscale conversion and filter-
ing. After conversion to grayscale, extra noise is eliminated by applying filtering tech-
niques. This proposed system defines a compound filter, which is a composition of Gauss-
ian, mean and median filter and is used for elimination of Gaussian, salt and pepper and
speckle noises in a greyscale images. The advantage of compound filter is that it preserves
the edges and boundaries in MRI.
• Greyscale conversion Greyscale conversion of MRI is the common preprocessing prac-

tice [13]. RGB MRI contains unnecessary information that is not required for processing of
the image. Such information can be discarded by converting RGB MRI into grayscale MRI
[4]. RGB scale presents MRI into 3 channels, B, G, R and each channel consists of 8 bits.
13
Fig. 1 Proposed architecture of brain tumor detection
For each B, G, R component, the image holds different intensity levels. That is why for a
color image we have intensities for each scale. Therefore, RGB needs large amount of data
to store and manipulate. Figure 1 shows a sample of conversion of RGB MRI image into
greyscale Image.
• Filtering After conversion to greyscale, extra noise is eliminated by applying filtering

techniques. This proposed system defines a compound filter, which is a composition of
Gaussian, mean and median filter and is used for elimination of Gaussian, salt and pepper
and speckle noises in greyscale images. The advantage of a compound filter is that it pre-
serves the edges and boundaries in MRI.
3.3.2 Segmentation
MRI Image Segmentation [4] is very important since numbers of images are produced at the
time of scanning and it is very difficult for physicians to divide these images manually in a
reasonable time. Image segmentation means, the partition of MRI images in several non-over-
lapping sections. Segmentation partitions the image into groups of pixels that are more impor-
tant and easier for analysis. Segmentation is performed to identify boundaries or objects in an
image and the resulting sections together cover the whole image. Segmentation methods work
on two features of image intensity, similarity and discontinuity. Many segmentation techniques
are available, like threshold based segmentation and histogram-based methods, region-based,
edge-based and clustering methods. Threshold and histogram-based segmentation is a most
13
likely technique for processing the MRI images. This work uses threshold and histogram-
based segmentation methods for the analysis of brain tumors and calculation of area of tumor
in MRI images. The sample result of threshold and histogram segmentation is shown in Fig. 1.
3.3.3 Feature Extraction
Feature extraction means shortening a number of resources needed to define a big group
of data correctly. During the analysis of the large set of data, the problems stem if a huge
number of variables are used. Analysis of the huge number of variables needs more mem-
ory and computation time. Feature extraction is the process of creating groupings of varia-
bles to solve these complications and then describing the data with enough accuracy. In this
proposed work, GLCM [15] is used to obtain both statistical and texture-based features.
The number of columns and number of rows in GLCM remains the same as the number
of gray levels of the image. Assume (Pi: ∆x, ∆y) is an element of GLCM. Here, (Pi: ∆x,
∆y) represents the relative frequency with which two pixels, which are separated by a pixel
distance (∆x, ∆y) occurs within a given neighborhood, where the intensity of the first pixel
is i and the other’s is j. The matrix element (Pi: d, ∅) contains the second- order statistical
probability values for the changes between gray level i and j at a displacement distance d
and angle ∅.
The proposed system extracts the following features using GLCM are shown in Table 3.
i. Contrast: Contrast splits the darkest and brightest area of an image. It is calculated
using the following formula:
∑n−1
Contrast = P (i − j)2
i,j=0 i,j
(1)
ii. Correlation: Correlation is calculated as the correlation coefficient between -1 and + 1.

∑n−1 (i − μ)(j − μ)
Correlation = Pi,j (2)
i,j=0 𝜎2
iii. Homogeneity: Homogeneity means the quality or state of being homogeneous.
∑n−1 Pi,j
Homogeneity = (3)
i,j=0
1 + (i − j)2
iv. Entropy: the degree of uncertainty in a random variable is termed entropy.

∑n−1
Entropy = Pi,j log(Pi,j )
i,j=0
(4)
v. Energy: Energy is used in GLCM to calculate the total of squared elements. Energy
measures homogeneity. A high level of energy indicates that the image has excellent
homogeneity or pixels of an image are very similar.
∑n−1
Energy = P 2
i,j=0 i,j
(5)
vi. Smoothness: Smoothness is a measure of grey level contrast that is used to establish
descriptors of relative smoothness.
13
1
Smoothness = 1 − (6)
1 + s2
Here, s is the standard deviation of an image.

vii. Kurtosis: Kurtosis is used to compute the flatness of the distribution which is relative
to a normal distribution.
{[ ] }
1 ∑m ∑n Pi,j − 𝜎 4
Kurtosis = −3 (7)
mn i=1 j=1 𝜎
Here, Pi, is the pixel value at point(i, j), m and s are the mean and standard deviation
respectively.
viii. Root Mean Square (RMS): RMS calculates the value of each row or column of the
input matrix of the given dimension of the input or whole input.
−
√ � �2
�Pi,j � (8)
RMS = � �
m
Eight GLCM textural features, Contrast, Correlation, Homogeneity, Entropy, Energy,

Smoothness, Kurtosis and RMS of each image out of 253 images are calculated, as
shown in Table 1.
3.3.4 Optimization
The optimization phase deals with the optimizers for the selection of image features.
For the implementation of the proposed optimizer, the whale and wolf optimization
algorithms are presented here. Feature selection is to be converted in to a more reliable
and suitable form for the classifier implementation to detect brain tumors. This paper
introduced the whale and wolf optimized features for deep learning-based CNN algo-
rithms to detect the healthy and tumor-infected brain in MRI images. Meanwhile, the
proposed algorithm has been compared in terms of accuracy, precision and recall with
another modern optimization algorithm is shown below:
• Particle swam optimization (PSO) algorithm PSO [24] is a swarm intelligence-based

optimization algorithm. It follows the behavior of particles of the swarm and their interac-
tions. The birds move from one place to another for food. The bird which is nearby to food
can smell it. PSO algorithm uses n swarm particles and the position of each particle stands
for the possible solution. The particle changes its position as per given below three rules:
• particle keeps its inertia

• particle updates the condition w.r.t. its optimal position
• particle updates the condition w.r.t. the most optimal position of swarm.
13
Table 1 Extracted features of MRI images

Image Contrast Correlation Homogeneity Entropy Energy Smoothness Kurtosis RMS
I001 1.7326 0.1075 1.0987 2.4589 0.8927 0.9450 15.255 0.0845

I002 0.2414 0.1237 0.8876 3.8976 0.3686 0.9335 12.544 0.0933
I003 0.2725 0.1465 0.8745 3.1765 0.3644 0.9194 15.280 0.0919
I004 1.1327 0.1253 0.9178 2.8345 0.4168 0.9607 15.438 0.0860
I005 1.2434 0.1344 1.1984 2.6623 0.7424 0.9316 13.231 0.0931
I006 1.2723 0.1147 1.5873 3.4078 0.3683 0.9445 17.285 0.0944
I007 1.0326 0.1195 1.4742 3.4412 0.3246 0.9493 18.164 0.0849
I008 0.1417 0.0964 1.3177 2.4534 0.4268 0.9522 16.173 0.0852
I009 0.2736 0.1126 0.0985 3.2223 0.7923 0.9509 17.148 0.0950
I010 1.7325 0.1183 1.8875 2.5565 0.7680 0.9348 18.145 0.0934
I011 0.4414 0.0942 1.8744 3.7643 0.4649 0.6915 19.154 0.0891
I012 1.5720 0.1166 1.9172 3.1178 0.6165 0.9524 14.175 0.0952
I013 1.4411 0.1347 2.3329 2.9065 0.3423 0.3233 16.254 0.0823
I014 1.2526 0.1565 1.4378 2.6634 0.5685 0.9387 15.264 0.0938
I015 1.0625 0.1344 1.3246 2.8834 0.4243 0.9464 12.858 0.0946
I016 0.1414 0.1183 1.1274 2.4376 0.8262 0.9362 19.243 0.0936
I017 0.4723 0.1222 1.1180 3.6712 0.5527 0.9229 17.233 0.0922
I018 1.3326 0.1337 1.1871 2.4534 0.4485 0.9261 12.208 0.0926
I019 1.5415 0.1446 0.8743 2.8967 0.3684 0.9396 15.676 0.0939
I020 0.5924 0.1115 1.2174 3.2754 0.4163 0.9145 15.917 0.0914
I021 1.8413 0.1623 1.3985 2.5834 0.7422 0.9554 12.133 0.0955
I022 1.6727 0.1067 1.4576 2.9623 0.3680 0.9183 13.615 0.0918
I023 1.5328 0.1332 1.5747 3.1076 0.3241 0.9205 12.859 0.0920
I024 0.4459 0.1571 1.6173 3.1454 0.4263 0.9530 17.447 0.0953
I025 0.2445 0.1730 0.7984 2.7834 0.7924 0.9368 19.355 0.0936
I026 1.3424 0.1358 1.7875 3.1287 0.7685 0.9555 18.412 0.0855
I027 1.4667 0.1036 2.5749 2.5167 0.4646 0.9634 13.287 0.0863
I028 0.7726 0.1145 1.4170 3.7156 0.6167 0.9493 17.433 0.0949
I029 1.4313 0.1974 0.8328 3.1756 0.3424 0.9506 21.363 0.0950
I030 0.4722 0.1583 1.4377 2.5023 0.5683 0.9315 17.298 0.0931
I031 1.3367 0.1060 0.7246 2.6056 0.4248 0.9644 15.136 0.0964
I032 0.3548 0.1128 1.1275 2.4834 0.8266 0.9593 12.124 0.0959
I033 0.5726 0.1781 1.7174 3.2378 0.5464 0.9322 19.411 0.0932
I034 1.3233 0.0993 1.6680 3.4732 0.7653 0.9707 12.909 0.0870
I035 1.2212 0.0924 1.4576 3.1758 0.3752 0.9545 13.142 0.0854
I036 1.2224 0.1040 1.4545 2.284 0.3240 0.6311 18.152 0.0631
I037 0.2545 0.1168 1.4174 3.3614 0.3369 0.9724 21.225 0.0972
I038 0.5436 0.1747 0.9793 3.3036 0.6741 0.3835 14.204 0.0383
I039 0.5518 0.1486 1.5876 3.3486 0.7236 0.9783 20.798 0.0978
I040 1.4436 0.1225 0.8745 2.9845 0.7845 0.9667 18.243 0.0966
I041 1.5933 0.1934 0.9174 3.2224 0.4564 0.9566 14.214 0.0956
I042 1.6585 0.1143 1.8323 2.6195 0.3883 0.9623 22.212 0.0862
I043 1.6383 0.1167 0.8872 3.9137 0.5382 0.9462 18.613 0.0846
I044 0.1642 0.0738 0.7249 3.0754 0.8949 0.9899 18.972 0.0889
13
Table 1 (continued)
Image Contrast Correlation Homogeneity Entropy Energy Smoothness Kurtosis RMS
I045 1.3753 0.1054 0.9278 2.9034 0.4560 0.9340 13.195 0.0934

I046 1.4337 0.1383 1.5177 2.6720 0.8651 0.9651 18.142 0.0965
I047 1.4336 0.1592 1.2326 2.8474 0.6685 0.9583 12.859 0.0958
I048 0.7869 0.1711 1.4371 3.1322 0.7646 0.9304 19.647 0.0830
I049 0.8418 0.1307 1.3240 3.1740 0.6564 0.9736 22.154 0.0873
I050 2.0026 0.1048 0.9276 3.4265 0.7643 0.9667 20.527 0.0966
The algorithm follows these steps:
• Initialize the best neighborhood particle pbest and the best global particle gbest with
random values to calculate a fitness value for each particle, which is then compared
with pbest and gbest values.
• If the particle has a better value than pbest and gbest, then we update the values of
pbest and gbest as the values of that particle.
• Otherwise, update the particles’ position and velocity according to Eqs. (9) and (10)
respectively, so as to follow the best particle.
( ) ( )
vidk = wvidk + c1 r1 pbestidk − xidk + c2 r2 pbestidk − xidk (9)
(10)
k+1 k k+1
xid = xid + vid
Where c1 and c 2 are the learning factors and w is the initial weight. After visiting all
the particles, the particle with the best fitness factor is selected as an initial particle of
the CNN algorithm.
• Genetic algorithm (GA) Genetic algorithm [1] uses the following data for its working:
• genotype: the segmented result of an image is considered as an individual described by

the class of each pixel.
• initial population: is a group of individuals categorized by their genotypes.
• fitness function: allows computing the fitness of an individual to the environment by
seeing its genotype.
• operators: defines alterations on genotypes in order to make the population develop dur-
ing generations. There are three operators:
Individual mutation: allows the individual’s genes to modify for better adaption
to the environment. Here the non-uniform mutation process is used, which randomly
selects one chromosome and sets it equal to the non-uniform random number:
� ( )
xi = xi +( bi − xi) (G), ifr1 < 0.5
� (11)
xi = xi − xi + ai f (G), ifr1 < 0.5
where
13
( ( ))b
G
f (G) = r2 1 − (12)
Gmax
r1, r2 numbers in range [0, 1]

ai, bi lower and upper bound of chromosome ri
G current generation
Gmax maximum number of generations
b shape parameter
• Selection of individual: for individual selection normalized geometric ranking selec-

tion method is applied in the next generation of individuals. The probability Pi for
each individual i to be selected as given below:
q(1 − q)r−1
Pi = (13)
1 − (1 − q)n
Where:
q the probability of selecting the best individual

r rank of the individual, where 1 is the best
n population size
• Crossover: by the combination of genes of two individuals third individual can repro-
duce. Here, the arithmetic crossover produces two complementary linear combinations
of the parents as given below:
(14)
�
X = aX + (1 − a)
(15)
�
Y = (1 − a) + aY
Where:
X, Y genotype of parents
a number in the range [0, 1]
X’, Y’ genotype of the linear combinations of the parents
• Stopping criterion: it ends the evolution of the population.
• Humpback whale optimization algorithm (HWOA) The proposed HWOA based on

deep learning [23] helps to enhance the speed of the training procedure using optimally
13
selecting the parameters pixel resolution. In the whale optimization technique, the hump-
back whales hunt the prey by applying three processes namely search, encircle and forming
a bubble net for hunting the prey.
Mathematical modeling of HWOA For the mathematical presentation of HWOA pro-

cesses, encircling the prey, spiral bubble-net feeding activities and searching for prey are
explained below.
Phase 1: Initialization The initialization phase of HWOA is used to develop the initial
solution randomly. After preprocessing of MRI image of brain tumor, its pixel size gen-
erated by the parameters of CNN is optimally selected by HWOA algorithm. The CNN
parameters such as number of kernels, padding, pooling type, number of feature maps and
whale population are randomly initialized. The random value in the search space is given
in Eq. (16):
( )
(u) = e1 , e2 , e3 , … , eh (16)
Here, E is the original population of the whale and h is the number of interconnection
layers for optimization.
Phase 2: Fitness calculation For brain tumor detection, the fitness function is used for the
best classification measure by maximizing its accuracy and evaluated using Eq. (17):
(u) = maxi(Accuracy) (17)
Phase 3. Encircling prey stage Humpback whale (agent) knows the position of prey and
encircle them. Whale considers that the current best candidate solution is the best-obtained
solution and close to the optimal solution. After assigning the best candidate solution, other
agents try to update their positions towards the best search agent by using the Eq. (18) and
(19):
D = |C.X ∗ (t) − X(t)| (18)
D = (t + 1) = X ∗ (t) − AD (19)
where t is current iteration, A and C are coefficient vectors, X* and X are position vectors
of the best solution and solution respectively, | | represents absolute value.
The value of vectors A and C are calculated by using Eq. (20) and (21):
A = 2a.r.a (20)
C = 2.r (21)
where, components of a are linearly decreased from 2 to 0 over the course of iterations and
r is a random vector in [0 1].
Phase 4. Exploitation or attack stage The humpback whales use a bubble-net mechanism
for attacking the prey. There is two mechanisms of attack as given below:
13
• Shrinking encircling mechanism: In this mechanism, the value of A is a random value

in the interval [-a, a] and it is decreased from 2 to 0 over the course of iterations as
shown in Eq. (3).
• Spiral updating position mechanism: In this mechanism, the distance between the loca-
tion of the whale and prey is computed. Thereafter, the helix-shaped movement of the
humpback is created by using Eqs. (22) and (23).
(22)
�
(t + 1) = D .cbl .cos(2𝜋l) + X ∗ (t)
Where,
(23)
�
D = |X ∗ (t) − X(t)|
is the distance between the prey or best solution and ith whale, b is a constant, l is a random
number in the range [-1 1].
The humpback whales apply the above two mechanisms when they come nearby the
prey. There is a probability of 50% to select these two mechanisms to update the position of
whales as shown in Eqs. (24) and (25):
(t + 1) = X ∗ (t) − AD, ifp < 0.5 (24)
or
(25)
�
(t + 1) = D .cbl .cos(2𝜋l) + X ∗ (t), ifp ≥ 0.5
where, p is a random number in the range [0 1].
Phase 5. Exploration or search stage The humpback whales or search agents hunt for
prey or the best solution randomly and alter their locations as per the location of another
whale. To force the search agent to move away from the referenced whale, the value of
A > 1 or A < 1 is used. The arithmetic representation of the exploration phase is given in
Eqs. (26) and (27):
D = ||C.Xrand − X || (26)
(t + 1) = ||Xrand − AD|| (27)
where Xrand is a random position vector selected from the current population?
At the time of updating each solution, the fitness calculation is measured to find the best
solution among them. Among the best solution, a set of new solutions is selected and then
the fitness function is computed for continuing the above solution updating process.
Phase 6: Termination criteria At the last, it satisfies the finest parameters of CNN by
the hunting behavior of the whale. As a result of finding the optimal solution, the predic-
tion model is trained. Since the objective function is to improve the accuracy of training
data, the prediction model obtained for the best fitness structure is well trained to predict
unknown data.
13
• Gray wolf optimization (GWO) algorithm GWO [28] is applied to optimize the features
along the hidden neurons of CNN. It has four levels: the first level alpha (∝) represents the
leader of the troop. Alpha may be male or female and have the power of taking decisions.
The second level beta (𝛽 ) helps alpha in taking decisions. The third level delta (𝛿) is sub-
ordinates and the fourth level omega (𝜔) is known as the scapegoat. All the three levels ∝,
𝛽 and 𝛿 guide in the hunting procedure. The encircling behavior is shown in Eq. (28) and
(29).
A = (tr) − (tr) (28)
(tr + 1) = (tr) − CA) (29)

where tr indicates present iteration, C and B represent coefficient vectors, XP refers the
position vector of the prey, X specifies the position vector of the grey wolf. The assessment
of C and B are defined in Eqs. (30) and (31), where, mi is linearly minimized from 2 to 0, v1
and v2 are the random vectors in the range [0, 1].
C = 2mi .v1 − mi (30)
B = 2v2 (31)
Generally, ∝ guides the hunting process. The leading three best solutions are saved from
the search space and the respective update strategy is assessed as per Eq. (32–34).
A∝ = ||B1 .X∝ − X||

|
Aβ = |B2 .Xβ − X|
| (32)
| |
A𝛿 = ||B1 .X𝛿 − X ||
(33)
X1 = X∝ − C1 (A∝ )
X2 = X𝛽 − C2 (A𝛽 )
X3 = X𝛿 − C3 (A𝛿 ) (34)
X +X +X
X(tr + 1) = 1 32 3
The final ∝, 𝛽 and 𝛿 maybe a random position in search space. The final position will be
the optimal feature and hidden neuron that works for the detection of a brain tumor.
3.3.5 Convolution neural network (CNN)
The proposed system uses deep learning-based CNN for the detection of brain tumors by
using the features extracted from pre-processed brain tumor images in step 3. This deep
learning CNN includes many hidden layers known as zero paddings, convolution, batch
normalization, ReLU, max pooling, flatten and fully connected layer as explained below.
CNN [19] is generally used in image processing to detect and classify brain tumors. In
this proposed work Nine Layers CNN is used and practically implemented using Python
programming language for the identification of brain tumors from brain MRI images. Fig-
ure 2 describes the working of CNN.
13
Fig. 2 Working flow of CNN
Steps of CNN algorithm There are four types of layers for a CNN. These are convolu-
tional layer, pooling layer, ReLU correction layer and fully-connected layer. Details of the-
ses layers are given below.
i. Convolutional layer
The convolutional layer is the key component of CNN and is always the first layer. Its
purpose is to detect the presence of a set of features in the images received as input. This is
done by convolution filtering: the principle is to “drag” a window representing the feature
on the image and to calculate the convolution product between the feature and each portion
of the scanned image. A feature is then seen as a filter, these two terms are equivalent in
this context.
The convolutional layer thus receives several images as input and calculates the con-
volution of each of them with each filter. The filters correspond exactly to the features we
want to find in the images.
We get for each pair (image, filter) a feature map, which tells us where the features are
in the image: the higher the value, the more the corresponding place in the image resem-
bles the feature.
Unlike traditional methods, features are not pre-defined according to a particular for-
malism, but learned by the network during the training phase. Filter kernels refer to the
convolution layer weights. They are initialized and then updated by back-propagation using
gradient descent.
ii. The pooling layer
This layer is often placed between two layers of convolution. It receives several feature
maps and applies the pooling operation to each of them. The pooling operation consists
in reducing the size of the images while preserving their important features.
To do this, we cut the image into regular cells, then we keep the maximum value within
each cell. In practice, small square cells are often used to avoid losing too much informa-
tion. The most common choices are 2 × 2 adjacent cells that don’t overlap, or 3 × 3 cells,
separated from each other by a step of 2 pixels (thus overlapping).
We get in output the same number of feature maps as input, but these are much smaller.
The pooling layer reduces the number of parameters and calculations in the network. This
improves the efficiency of the network and avoids over-learning. The maximum values are
13
spotted less accurately in the feature maps obtained after pooling than in those received in
input.
iii. The Rectified Linear Units (ReLU) correction layer
ReLU refers to the real non-linear function defined by
ReLU(x) = max(0, x).
The ReLU correction layer replaces all negative values received as inputs by zeros. It
acts as an activation function.
iv. The fully-connected layer
The fully-connected layer is always the last layer of a neural network. This layer receives
an input vector and produces a new output vector. To do this, it applies a linear combina-
tion and then possibly an activation function to the input values received. The last fully-
connected layer classifies the image as an input to the network: it returns a vector of size N,
where N is the number of classes in our image classification problem. Each element of the
vector indicates the probability for the input image to belong to a class.
To calculate the probabilities, the fully-connected layer, multiplies each input element
by weight, makes the sum, and then applies an activation function (logistic if N = 2, soft-
max if N > 2). This is equivalent to multiplying the input vector by the matrix containing
the weights. The fact that each input value is connected with all output values explains the
term fully-connected.
The convolutional neural network learns weight values in the same way as it learns the
convolution layer filters: during the training phase, by back-propagation of the gradient.
The fully connected layer determines the relationship between the position of features in
the image and a class. Indeed, the input table being the result of the previous layer, it cor-
responds to a feature map for a given feature: the high values indicate the location (more or
less precise depending on the pooling) of this feature in the image. If the location of a fea-
ture at a certain point in the image is characteristic of a certain class, then the correspond-
ing value in the table is given significant weight.
The parameterization of the layers A CNN differs from another networks by the way
the layers are stacked, but also parameterized. The convolution and pooling layers have
hyper parameters, that is to say parameters whose you must first define the value. The size
of the output feature maps of the convolution and pooling layers depends on the hyper
parameters.
Each image (or feature map) is W × H × D, where W is its width in pixels, H is its height
in pixels and D the number of channels (1 for a black and white image, 3 for a color image).
The convolutional layer has four hyper parameters:
1. The number of filters K .

2. The size F filters: each filter is of dimensions F × F × D pixels.
3. The S step with which you drag the window corresponding to the filter on the image.
For example, a step of 1 means moving the window one pixel at a time.
4. The Zero padding: adds a black contour of P pixels thickness to the input image of the
layer. Without this contour, the exit dimensions are smaller. Thus, the more convolu-
13
tional layers are stacked with P = 0, the smaller the input image of the network is. We
lose a lot of information quickly, which makes the task of extracting features difficult.
For each input image of size W × H × D, the pooling layer returns a matrix of dimen-
sions WC × HC ×DC , where:
W−F+2P
WC = S
+1
HC = H−F+2P
S
+1
DC = K
Choosing, F = F−1 2
, S = 1 gives feature maps of the same width and height as those
received in the input.
The pooling layer has two hyper parameters:
1. The size F of the cells: the image is divided into square cells of size F × F pixels.
2. The S step: cells are separated from each other by S pixels.
For each input image of size W × H × D, the pooling layer returns a matrix of dimen-
sions WP × HP ×DP where:
WP = W−F
S
+1
H−F
HP = S + 1
DP = D
The choice of hyper parameters is made according to a classic scheme:

For the convolution layer, the filters are small and dragged on the image one pixel at a
time. The zero-padding value is chosen so that the width and height of the input volume are
not changed at the output. We choose F = 3, P = 1, S = 1 or F = 5, P = 2, S = 1
For pooling layer, F = 2, S = 2 is a choice. This eliminates 75% of the input pixels. We
can also choose F = 3, S = 2. In this case, the cells overlap. Choosing larger cells causes
too much loss of information and results in less good.
In Fig. 2 each input image I of the shape of (128, 128, 3) is served to CNN, which fol-
lows the sequence of layers.
Here the size of the image I is (128, 128, 3). We need to add an additional dimension
to process multiple batches in one epoch. Since size of batches can change, therefore, this
additional dimension is represented here as None. Hence the changed shape of input image
is (None, 128, 128, 3).
Zero Padding layer packs the border of the image I with 0 s. A zero padding layer of
pool size, 2*2 is used here to perfectly fit the input image by padding the image I with
zeros. After padding zero the size of image becomes (132, 132, 3) which is fed to convolu-
tion layer.
Convolution of the size of an image (132,132, 3) with the filter size of (7, 7), stride 1,
dilation rate 1 and valid padding, gives the output of size of image:
(132 − 7 + 1, 132 − 7 + 1) = (126, 126)
Here convolution layer uses 32 filters, therefore the output shape becomes (126, 126,
32). The filter is applied here for the detection of the presence of particular features in the
13
input image I. the output of the convolution layer (126, 126, 32) becomes the input of the
batch normalization layer.
The output of the batch normalization layer is (126, 126, 32). This is fed to the activa-
tion layer. The output of the activation layer is (126, 126, 32) which is fed to max-pooling
layer 0, It selects the biggest element from the rectified feature map. This layer uses 4 fil-
ters, 4 strides and a pool size of (4, 4) for its processing. Max pooling layer 0 gives output
image size using the formula as given below:
N−F
+1
S
Here:
N is the dimension of input to pooling layer, F is the dimension of filter and S is stride.
Then the size of the output image is
( )
126 − 4 126 − 4
+ 1, + = (31, 31)
4 4
This CNN includes another max-pooling layer to reduce the computation cost. Here
stride indicates the shifting of the number of pixels in the input matrix. If the value of
stride is 1, it allows to move filter 1 pixel at a time, if the stride is 2, means moving the fil-
ters 2 pixels at a time and so on.
The image size of (31, 31, 32) is fed to max-pooling layer 1. The max-pooling layer 1
uses 4 filters, 4 strides and a pool size of (4, 4). Therefore, max-pooling layer 1 produces an
output image of size
( )
31 − 4 31 − 4
+ 1, + = (7, 7)
4 4
The image size of (7, 7, 32) is fed to the next layer, which is flattened.
An activation function represents the non-linear transformation that is applied on an
input signal to convert into output. Here, the ReLU layer works as an activation function.
Therefore, it does not corroborate with the output. Non-linear ReLU layer is used to apply
nonlinear operation in CNN since non-negative linear values are needed to learn CNN.
Here, the output of ReLU is:
f (x) = max(0, x).Where,
if x < 0thenf(x) = 0, andif x > thenf(x) = x.
After pooling, we use flatten layer to transform the 3-dimensional matrix, which rep-
resents the input images into a 1-dimensional vector for processing. Thereafter, it is fed
to the neural network to process further. Flatten layer takes all the pixels and channels of
an image which creates a 1-dimensional vector without batch size. An input of size of an
image (7, 7, 32) is flattened to:
7 ∗ 7 ∗ 32 = 1568values.
At last, a fully connected layer along with one neuron and sigmoid activation function is
known as the dense layer is used for binary classification. The final output of our model is
1, it outputs 1 value per sample in the batch.
Each layer contains parameters. Trainable parameters can be updated with CNN and
non-trainable parameters remain static. The number of parameters of the convolution layer
is represented by Eq. (35):
13
44644
13
Table 2 Layer-Wise Output of CNN
Layer no Name of layer Inputs of layers Outputs of layers No. of parameters
1 Input (128, 128, 1) (None, 128, 128, 1) 0

2 Zero Padding (128, 128, 1) with pool size (2, 2) (None, 132, 132, 1) 0
3 Convolution (132, 132, 1) with filter size (7, 7), stride 1, dilation rate 1 and valid padding (None, 126, 126, 32) 4736
4 Batch Normalization (126, 126, 32) (None, 126, 126, 32) 128
5 Activation (126, 126, 32) (None, 126, 126, 32) 0
6 Max Pooling 0 (126, 126, 32) with filters 4, stride 4, pool size (4, 4) (None, 31, 31, 32) 0
7 Convolution (31, 31, 32) with filter size (7, 7), stride 1, dilation rate 1 and valid padding (None, 25, 25, 32) 4736
8 Batch Normalization (25, 25, 32) (None, 25, 25, 32) 128
9 Activation (25, 25, 32) (None, 25, 25, 32) 0
10 Max Pooling 1 (25, 25, 32) with filters 4, stride 4, pool size (4, 4) (None, 6, 6, 32) 0
11 Flatten (6, 6, 32) (None, 1152) 0
12 Dense 1152 (None, 1) 1569
Total parameters: 6433
Trainable parameters: 6369
Non-trainable parameters: 64
H ∗ W ∗ NIC ∗ NOC + NOC (if bias is issued) (35)

Here,
H Height of kernel,
W Width of kernel,
NIC Number of input channels,
NOC Number of output channels
For our convolution layer total parameters calculated, are 6433. Out of 6433 parameters,
the trainable parameters are 6369 and 64 are non-trainable.
The complete output of each layer of CNN is depicted in Table 2.
Calculation of parameters of CNN has been described as below.
1. The first layer input is used to read the image. So, no parameters are required by the
input layer.
2. In CNN, zero-padding refers to surrounding a matrix with zeros. This can help preserve
features that exist at the edges of the original matrix and control the size of the output
feature map. Therefore, the zero padding layer requires no parameters.
3. The convolution layer Conv, where CNN learns and certainly has weight matrices.
To calculate the numbers of learnable parameters in a Conv we use following for-
mula: ((shape of width of the filter * shape of height of the filter * number of filters
in the previous layer + 1) * number of filters in the current layer). Here 1 is added,
because of the bias term for each filter.The number of parameters in the first convolu-
tion layer Conv with filter shape = 7*7, stride = 1, dilation rate = 1 and valid padding
is = (7*7*3 + 1)*32) = 4736.
4. Batch normalization is a layer that allows every layer of the network to learn indepen-
dently. It is used to normalize the output of the previous layers. The Batch Normaliza-
tion layer has 128 parameters.
5. An activation function in a CNN defines how the weighted sum of the input is trans-
formed into an output from a node in a layer of the network. Activation layer uses
the ReLU function which requires no parameters. ReLU performs an element-wise
operation and sets all the negative pixels to 0.
6. There are no parameters to learn in max pooling layer 0. This layer has used to reduce
the image dimension size. This has got no learnable parameters because all it does is
calculate a specific number and no backprop learning involved.
7. The total number of parameters in the second convolution layer Conv with filter
shape = 7*7, stride = 1, dilation rate = 1 and valid padding is = (7*7*3) + 1)*32) = 4736.
8. Again the second batch normalization layer has 128 parameters.
9. A second activation layer uses ReLU function which requires no parameters.
10. There are also no parameters to learn in max pooling layer 1. This layer reduces the
image dimension size and has no learning parameters because all it does is calculate
a specific number and no backprop learning involved.
11. Flattening is used to convert all the two dimensional arrays from pooled feature maps
into a single dimensional array, which requires no parameters. Therefore, flatten layer
has no parameters.
13
Table 3 Parameters and values Algorithm Parameter Values

used in CNN
CNN Layer 8
Activation function ReLu
Optimizer ADAM
Loss binary_crossentropy
Epochs 20
validation_split 2
Batch Size 8
12. In Dense or fully-connected layer all inputs units have a separable weight to each out-
put unit. For n inputs and m outputs, the number of weights is n*m. This layer has the
bias for each output node, so There are (n + 1)*m parameters. Here n = 6, The formula
to calculate number of parameters are: (7*7*32)+1= 1569., Here 1 is added, because
of the bias term for each filter. Dense layer has 1569 parameters (Table 3).
In this system we have used 8 layers of CNN such as input, zero padding, convolution,
batch normalization, activation, max pooling, flatten and dense to detect brain tumor. Activa-
tion layer uses the ReLU function to accelerate the training speed of deep neural networks.
Adaptive Moment Estimation (ADAM) algorithm applied here for optimization because this
system uses a lot of data and parameters and requires minimum memory. ADAM is a combi-
nation of gradient descent with momentum algorithm and the Root Mean Square Propagation.
The single epoch represents one single pass of all the data through the CNN, here 20 epochs
have been used. In this system CNN uses the batch size of 8. This means that 8 MRI images of
the brain will be passed as a group to CNN at a time. The binary_ crossentropy loss function
is applied here to calculate the loss to train a CNN model for the classification of brain tumor
which reduces the classification of a binary choice i.e. yes or no, A or B, 0 or 1.
4 Results and discussion
To test and assess the proposed system, 696 images are taken as an input for testing the
whole system. The whale and wolf features, which are extracted from the datasets, are uti-
lized for testing system. For valuation, the presented approach can be estimated by some
statistical measurements, such as true negative (TN), true positive (TP), False Negative
(FN), and False positive (FP). These values are represented as a confusion matrix in as
shown in below table. Confusion matrix provides accuracy of detection of tumor of any
classifier. Confusion matrix (Table 4) is created by using actual and predicted values.
Accuracy: Accuracy refers to the ratio of the true patterns to the summation of entire
patterns. It can be expressed as
TN+TP
Accuracy = TP+FN+TN+FP
× 100
(36)
277+412
Accuracy = 696
= 98.9
13
Table 4 Confusion Matrix
No. of images 696 Output

Healthy Tumor infected
Healthy TP = 412 FP = 5 417

Tumor infected FN = 2 TN = 277 279
414 282 696
Therefore, the accuracy for the proposed system 98.9.

Precision: Precision can be described as the ratio of true positive to the summation of
entire positive patterns. It can be expressed as
TP
Precision = TP+FP
× 100
(37)
412
Precision = 412+5
= 98
Thus, precision for the proposed system is 98.

Recall: The recall parameter is used for calculating the false positive and true posi-
tive values, and also it can be called sensitivity. It can be expressed as
TP
Recall = TP+FN
× 100
(38)
412
Recall = 412+3
= 100

F-Score: To measure the value of F-Score, it requires both precision and recall val-
ues. It can be expressed as
Precision × Recall
F − Score = 2 × Precision + Recall
(39)
98×100
F − Score = 2 × 98+100
= 99

Where:
TP means both actual as well as predicted value is true.

FP means predicted value is true but actual value is false.
TN means both actual as well as predicted value is false.
FN means actual value is true and predicted value is false.
In this part, the performance analysis of proposed system is assessed by using accuracy,
precision, recall and F-Score parameters. For performance analysis the existing CNN and
deep learning based approaches which uses CNN and optimization based approaches such
as PSO + CNN, GA + CNN, Wolf + CNN, Whale + CNN are considered Observations val-
ues of the proposed and current methods are given in Table 5.
Table 5 describes the results of the current and proposed approach. The accuracy
obtained for the brain tumor detection from our proposed approach which has used
13
Table 5 Comparison of various optimization techniques with proposed system

Techniques Algorithm Accuracy Precision Recall F-Score
Deep Learning CNN 93.9% 95 94 87

PSO + CNN 95.6% 96 97 89
GA + CNN 95.9% 97 98 94
Optimization Wolf + CNN 96.4 97 100 97
Whale + CNN 98.9% 98 100 99
the Whale + CNN combination is 98.9%. The accuracy of the competitive algo-
rithms, such as CNN, PSO + CNN, GA + CNN and Wolf + CNN are 93.9%, 95.6%,
95.9%, and 96.4% respectively. The precision level for the proposed approach is 95
which uses Whale + CNN combination, whereas for the existing techniques like CNN,
PSO + CNN, GA + CNN, Wolf + CNN the values of precision are 95, 95, 96 and 97,
respectively. This shows that the precision level for the proposed approach is high. The
recall value for the suggested method is 100, whereas for the existing algorithms like
CNN, PSO + CNN, GA + CNN and Wolf + CNN are 94, 97, 98, and 100, respectively.
At last, the F-Score value for the proposed method is 99, whereas for the existing meth-
ods, CNN, PSO + CNN, GA + CNN and Wolf + CNN are 87, 89, 94 and 97 respec-
tively. Therefore, the presented approach based on Deep learning and Whale + CNN
based optimization techniques is more efficient in accuracy, precision, recall and
F-Score. Table 5 also clearly shows that the Whale + CNN classifier gives better results
of accuracy, precision, recall and F-Score than other algorithms. The feature optimiza-
tion and detection of brain tumors using CNN are implemented in Python which also
calculates the number of healthy and tumor infected images. 696 images were taken for
analysis. Out of that, 696 has been used for testing and the 70% for training. With this
the accuracy of Whale + CNN algorithm has achieved 98.9%. Whale + CNN algorithm
reached the maximum accuracy when compared with other algorithms. The confusion
matrix indicates that 414 images have been identified as normal and 282 are under
tumor infection. Comparative analysis of table accuracy, precision, recall and F-Score
is shown in Figs. 3, 4, 5 and 6.
The x-axis represents brain tumor detection performance methods like CNN,
PSO + CNN, GA + CNN, Wolf + CNN and Whale + CNN in the Fig. 3, The y-axis
represents the parameter values of Accuracy in Fig. 1, Precision in Fig. 2, Recall in
Fig. 3 Comparison with Accu-

racy
13
Fig. 4 Comparison with Preci-

sion
Fig. 5 Comparison with Recall
Fig. 6 Comparison with F-Score
Fig. 3 and F-Score in Fig. 4, respectively. The Figs. 1, 2, 3 and 4 respectively clearly
shows that the presented approach with Whale + CNN has highest value for its accu-
racy, precision, recall and F-Score. This indicates that that the proposed approach is
performed efficiently in accuracy, precision, recall and F-Score with other existing
algorithms. Therefore, the proposed method may be the most preferred method for
detecting brain tumors.
13
5 Performance comparison
Performance comparison of various existing optimization techniques of brain tumor detec-

tion with proposed system is presented in Table 6
Geetha et al. [7] utilized a DBN classifier with GWO to detect the tumor in MRI
images and calculated 94.11% accuracy in the year 2019. They proposed a model which
includes certain processes such as preprocessing, segmentation, feature extraction and
classification. Preprocessing applies two main processes, contrast enhancement and skull
stripping. The segmentation process, FCM algorithm has been used. GLCM and GRLM
are used for feature extraction. Moreover, this system uses a DBN for classification. The
optimized DBN concept is used here, for which GWO is used. Then, Sindhu A et al. [26]
designed an Adaboost ensemble KNN-SVM model which uses WOA to identify brain
tumors and achieved 98.3% accuracy in the year 2020. This model presents a system
which applies five steps, preprocessing, segmentation, feature extraction, feature selec-
tion (optimization) and classification. This system performs preprocessing as an initial
step to remove the noises by using HE/ACWM. The segmentation uses K Means cluster-
ing to identify the tumor location. Feature extraction is done by using First Order and
Second Order Statistical features by GLCM and GLRM. Further PSO and WOA are
applied for best feature selection. The machine learning classifiers such as DT, KNN,
SVM and AdaBoost with ensemble KNN-SVM classifiers are utilized to classify the
tumor as normal or abnormal. The Mishra PK et al. [18] applied a DCNN classifier with
WOA for the detection of brain tumors with the accuracy of 98% in the year 2021. This
system applies histogram alignment and median filter for preprocessing, Otsu threshold-
ing and morphological operations for image segmentation, WOA for feature selection
and DCNN for classification. Yin B et al. [28] used a multilayer perceptron neural net-
work classifier with WOA for the detection of brain tumors with the accuracy of 96.5%
in the year 2020. This system applies MICO for preprocessing, CNN for segmentation
and WAO for feature selection and multilayer perceptron neural network for classifica-
tion. Fouad A et al. [6] applied Ensemble Learning Classifier with WAO for the detec-
tion of brain tumors with the accuracy of 96.4% in the year 2020. This system applied
Haar Discrete Wavelet transforms hybrid with the Histogram of Oriented Gradients for
preprocessing. Important feature selection is done by using WAO and tumor classifica-
tion is done by using Ensemble Learning Classifier. Gong S et al. [8] applied radial basis
function (RBF) network with WAO for the detection of brain tumors with the accuracy
of 88% in the year 2020. This system applied a median filter for preprocessing, for seg-
mentation thresholding and Otsu methods, feature selection is done by WAO and tumor
detection uses RBF network. Compared to the above systems, this proposed system
obtained 98.9% accuracy with the CNN classifier and WAO for the brain tumor detection
in MRI images. Our proposed system uses a combination of Gaussian, mean and median
filter for preprocessing of image, threshold and histogram techniques for segmentation
and WOA for the best feature selection and finally CNN is applied for tumor detection.
6 Conclusion
This research paper proposed a novel accurate optimized system based on deep learning
techniques to detect brain tumors. The system uses preprocessing, segmentation, feature
extraction, optimization and detection activities to detect the tumor in MRI images by
13
Table 6 Performance comparison of existing optimization techniques with proposed system
Author Year Preprocessing Segmentation Feature extraction and selection Classification Accuracy
Geetha A et al. [7] 2019 Contrast enhancement, skull FCM Gray wolf optimization DBN 94.11
stripping
Sindhu A et al. [26] 2020 HE/ACWM K. Means clustering Whale optimization algorithm Adaboost ensemble 98.3
KNN-SVM
Mishra PK et al. [18] 2021 MICO CNN Whale optimization algorithm DCNN 98
Yin B et al. [28] 2020 histogram alignment, median Otsu thresholding and mor- Whale optimization algorithm multilayer perceptron neural 96.5
filter phological operations network
Fouad A et al. [6] 2019 Haar Discrete Wavelet transforms –- Whale optimization algorithm Ensemble Learning Classifier 96.4
hybrid with the Histogram of
Oriented Gradients
Gong S et al. [8] 2019 median filter Thresholding, Otsu method Whale optimization algorithm radial basis function (RBF) 88
network
Proposed Work 2021 Gaussian, mean and median filter Threshold & Histogram Whale optimization algorithm CNN 98.9
44651
13
using CNN. For preprocessing compound filter is used which is a composition of Gauss-
ian, mean and median filter. For segmentation of MRI images threshold and histogram,
methods are used. Image features are extracted by GLCM. Deep learning-based optimized
technique that uses whale and grey wolf optimization for the selection of best features of
an image. Detection of brain tumors is achieved by using CNN classifier. The performance
of this system is compared with other modern methods of optimization in terms of accu-
racy, precision and recall parameters and proves the superiority of this work. This system
is implemented on Python programming language. For the Identification of brain tumors
253 MRI images selected from the Kaggle dataset. Further, the dataset size is augmented
to 2318 images. Out of these images, 1622 have been used for training, 348 for testing and
348 have been utilized for validation. The results of implementation and evaluations with
the other related system show that this system can reach better detection performance than
another modern system. The brain tumor detection accuracy of this optimized system has
been measured at 98.9%
It might be hoped that this work will help physicians to take final decisions for further
treatment.
Funding There is no funding.
Data availability All the data for brain tumor detection created or used during the study are openly available
from the kaggle dataset at: https://www.kaggle.com/navoneel/brain-mri-images-for-brain-tumor-detection.
Declarations
Ethics approval This article contains no studies related to animals.
Conflicts of interest Author declares there is no conflict of interest.
References
1. Abdel-Gawad AH, Lobna A, Ahmed S, Radwan G (2020) Optimized Edge Detection Technique for
Brain Tumor Detection in MR Images. IEEE Access 8:136243–136259
2. Avsar E, Salcin K (2019) Detection and classification of brain tumors from MRI images using faster
R-CNN. Tehnički Glasnik 13(4):337–342
3. Bahadure NB et al (2017) Image analysis for MRI based brain tumor detection and feature extraction
using biologically inspired BWT and SVM. Int Biomed Imaging 2017:1–12
4. Bhima K, Jagan A (2016) Analysis of MRI based brain tumoridentification using segmentation tech-
nique. 2016 International Conference on Communication and Signal Processing (ICCSP), 2109-2113
5. Borole VY et al (2015) Image Processing Techniques for Brain Tumor Detection: A Review. Int J
Emerging Trends Technol Comput Sci 4:28–32
6. Fouad A, Moftah HM, Hefny HA (2020) Brain Diagnoses Detection Using Whale Optimization Algo-
rithm Based on Ensemble Learning Classifier. Int J Intell Eng Syst 13:2
7. Geetha GA, Gomathi, N (2019) A robust grey wolf-based deep learning for brain tumour detection in
MR images. Biomed Eng Biomed Tech 1:9–23
8. Gong S, Gao W, Abza F (2019) Brain tumor diagnosis based on artificial neural network and a chaos
whale optimization algorithm. Comput Intell 1–17
9. Gunasekara SR, Kaldera HNTK, Dissanayake MB (2021) A Systematic Approach for MRI Brain
Tumor Localization and Segmentation Using Deep Learning and Active Contouring. Hindawi J
Healthcare Eng 2021:13
10. Hebli AP, Gupta S (2016) Brain Tumor Detection Using Image processing: A Survey. In: Proceedings
of 65th IRF International Conference
13
11. Hossain T, Shadmani Shishir F, Ashraf M, Abdullah Al Nasim MD, Muhammad Shah F (2019) Brain
Tumor Detection Using Convolutional Neural Network, 1st International Conference on Advances in
Science, Engineering and Robotics Technology (ICASERT-2019)
12. Irmak E (2021) Multi-Classification of Brain Tumor MRI Images Using Deep Convolutional Neural
Network with Fully Optimized Framework. Iranian J Sci Technol Trans Electr Eng 45:1015–1036
13. Kapoor L, Thakur S (2017) A survey on brain tumor detection using image processing techniques.
2017 7th International Conference on Cloud Computing, Data Science & Engineering Confluence.
582–585
14. Khan AH, Abbas S, Khan MA, Farooq M, Khan WA, Siddiqui SY, Ahmad A (2022) Intelligent Model
for Brain Tumor Identification Using Deep Learning. Hindawi Appl Comput Intell Soft Comput
2022:10
15. Kumar P, Vijayakumar B (2016) An Efficient Brain Tumor MRI Segmentation and Classification
Using GLCM Texture Features and Feed Forward Neural Networks. World J Medical Sci 13:8592
16. Louis DN, Ohgaki H, Wiestler OD, Cavenee WK (2007) WHO Classification of Tumors of the Central
Nervous System. International Agency for Research on Cancer, Lyon, France
17. Medical Imaging in Cancer Care: Charting the Progress, US Oncology and National Electrical Manu-
facturers Association (2012)
18. Mishra PK, Satapathy SC, Rout M (2021) Segmentation of MRI Brain Tumor Image using Optimiza-
tion based Deep Convolutional Neural networks (DCNN). Open Comput Sci 11:380–390
19. Parihar AS (2017) A Study on Brain Tumor Segmentation Using Convolution Neural Network. 2017
International Conference on Inventive Computing and Informatics (ICICI)
20. Rammurthy D, Mahesh PK (2020) Whale Harris Hawks optimization based deep learning classifier for
brain tumor detection using MRI images. J King Saud Univ Comput Inf Sci 1–14.
21. Ramtekkar PK, Pandey A, Pawar MK (2020) A proposed model for automation of detection and clas-
sification of brain tumor by deep learning. 2020 2 nd International Conference on Data, Engineering and
Applications (IDEA).
22. Ramtekkar PK, Pandey A, Pawar MK (2023) Innovative brain tumor detection using optimized deep
learning techniques. Int J Syst Assur Eng Manag 14:459–473
23. Shankar K, Lakshmanaprabu SK, Khanna A, Tanwar S, Joel J, Rodrigues PC, Roy NR (2019) Alz-
heimer detection using Group Grey Wolf Optimization based features with convolutional classifier.
Comput Electr Eng 77:230–243
24. Sharifa M, Amina J, Razaa M, Yasmina M, Satapathy SC (2020) An Integrated Design of Particle
Swarm Optimization (PSO) with Fusion of Features for Detection of Brain Tumor. Pattern Recogn Lett
129:150–157
25. Sharma AK, Tiwari S, Aggarwal G,Goenka N, Kumar A, Chakrabarti P, Chakrabarti T, Gono R,
Leonowicz Z, Jasiński M (2022) Dermatologist-Level Classification of Skin Cancer Using Cascaded
Ensembling of Convolutional Neural Network and Handcrafted Features Based Deep Neural Network.
IEEE Access. https://doi.org/10.1109/ACCESS.2022.3149824
26. Sindhu A, Radha V (2020) An Optimal Feature Selection with Whale Algorithm and Adaboost
Ensemble Model for Pancreatic Cancer Classification in PET/CT Images. Biosc Biotech Res Comm
13(4):18861894
27. Verma SS, Prasad A, Kumar A (2021) CovXmlc: High performance COVID-19 detection on X-ray
images using Multi-Model classification. Biomed Signal Process Control
28. Yin B, Wang C, Abza F (2020) New brain tumor classification method based on an improved version
of whale optimization algorithm. Biomed Signal Process Control 56:1–10
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and
institutional affiliations.
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under
a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted
manuscript version of this article is solely governed by the terms of such publishing agreement and applicable
law.
13

Accurate Detection of Brain Tumor Using Optimized Feature Selection Based On Deep Learning Techniques

Uploaded by

Copyright:

Available Formats

Accurate Detection of Brain Tumor Using Optimized Feature Selection Based On Deep Learning Techniques

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Accurate Detection of Brain Tumor Using Optimized Feature Selection Based On Deep Learning Techniques

Uploaded by

Copyright:

Available Formats

Multimedia Tools and Applications (2023) 82:44623–44653

Accurate detection of brain tumor using optimized feature

Praveen Kumar Ramtekkar1 · Anjana Pandey1 · Mahesh Kumar Pawar1

Received: 6 September 2021 / Revised: 12 March 2023 / Accepted: 30 March 2023 /

Keywords Brain tumor · CNN · GLCM · Histogram segmentation · Particle swarm

* Praveen Kumar Ramtekkar

Following are the main contributions of this novel optimized system:

3 Methods and materials

3.1 Magnetic resonance imaging (MRI) scanning

• It does not use Ionizing radiation.

3.3 Proposed architecture of brain tumor detection

• Greyscale conversion Greyscale conversion of MRI is the common preprocessing prac-

Fig. 1 Proposed architecture of brain tumor detection

• Filtering After conversion to greyscale, extra noise is eliminated by applying filtering

ii. Correlation: Correlation is calculated as the correlation coefficient between -1 and + 1.

iv. Entropy: the degree of uncertainty in a random variable is termed entropy.

Here, s is the standard deviation of an image.

Eight GLCM textural features, Contrast, Correlation, Homogeneity, Entropy, Energy,

• Particle swam optimization (PSO) algorithm PSO [24] is a swarm intelligence-based

• particle keeps its inertia

Table 1 Extracted features of MRI images

I001 1.7326 0.1075 1.0987 2.4589 0.8927 0.9450 15.255 0.0845

I045 1.3753 0.1054 0.9278 2.9034 0.4560 0.9340 13.195 0.0934

The algorithm follows these steps:

• genotype: the segmented result of an image is considered as an individual described by

r1, r2 numbers in range [0, 1]

• Selection of individual: for individual selection normalized geometric ranking selec-

q the probability of selecting the best individual

• Stopping criterion: it ends the evolution of the population.

• Humpback whale optimization algorithm (HWOA) The proposed HWOA based on

Mathematical modeling of HWOA For the mathematical presentation of HWOA pro-

• Shrinking encircling mechanism: In this mechanism, the value of A is a random value

where, p is a random number in the range [0 1].

(t + 1) = ||Xrand − AD|| (27)

(tr + 1) = (tr) − CA) (29)

A∝ = ||B1 .X∝ − X||

3.3.5 Convolution neural network (CNN)

Fig. 2 Working flow of CNN

1. The number of filters K .

The choice of hyper parameters is made according to a classic scheme:

1 Input (128, 128, 1) (None, 128, 128, 1) 0

H ∗ W ∗ NIC ∗ NOC + NOC (if bias is issued) (35)

Table 3 Parameters and values Algorithm Parameter Values

4 Results and discussion

Table 4 Confusion Matrix

No. of images 696 Output

Healthy TP = 412 FP = 5 417

Therefore, the accuracy for the proposed system 98.9.

Thus, precision for the proposed system is 98.

Thus, precision for the proposed system is 100.

Thus, precision for the proposed system is 99.

TP means both actual as well as predicted value is true.

Table 5 Comparison of various optimization techniques with proposed system

Deep Learning CNN 93.9% 95 94 87

Fig. 3 Comparison with Accu-

Fig. 4 Comparison with Preci-

Fig. 5 Comparison with Recall

Fig. 6 Comparison with F-Score

Performance comparison of various existing optimization techniques of brain tumor detec-

3 Methods and materials

3.1 Magnetic resonance imaging (MRI) scanning

3.3 Proposed architecture of brain tumor detection

r1, r2 numbers in range [0, 1]

q the probability of selecting the best individual

3.3.5 Convolution neural network (CNN)

4 Results and discussion

TP means both actual as well as predicted value is true.