0% found this document useful (0 votes)
23 views6 pages

Skin Cancer Detection Using Transfer Learning, Sasikala Et. Al

Skin Cancer Detection Using Transfer Learning

Uploaded by

Sasi Kala
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
23 views6 pages

Skin Cancer Detection Using Transfer Learning, Sasikala Et. Al

Skin Cancer Detection Using Transfer Learning

Uploaded by

Sasi Kala
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 6

Biosc.Biotech.Res.Comm.

Special Issue Vol 13 No 11 (2020) Pp-55-60

Towards Improving Skin Cancer Detection Using


Transfer Learning
S. Sasikala1*, S. Arun Kumar2, S.N. Shivappriya3 and Priyadharshini T4
Assosciate Professor, 2Assistant Professor, 4UG Scholar
1,3

Department of Electronics and Communication Engineering,


Kumaraguru College of Technology, Coimbatore-49, India

ABSTRACT
In present time, skin cancer is the deadliest disease among humans. In US, two persons die every hour owing to skin
cancer. Skin cancer is developed on the body when exposed to sunlight and is the abnormal growth of the skin cell.
The patient’s life can be saved through earlier and faster detection of skin cancer. The formal method of skin cancer
detection is Biopsy, it is done by removing the skin cells and testing the samples in a clinical lab. Biopsy method is
invasive and time-consuming. With the newer technologies, early detection of skin cancer at the initial stage is possible.
Image processing techniques are instrumental in the health care industry to detect abnormalities in the human body. In
this work, Convolutional Neural Network (CNN) algorithm with four different transfer learning techniques are used to
classify the images of the skin with dermoscopic analysis which enables fast detection. A CNN model is trained using
a dataset of 3700 clinical images and its performance is tested over 660 images which represent the identification of
deadliest skin cancer. A considerable improvement in accuracy of skin cancer detection using deep learning architecture
ResNet34 provides a reliable approach for early detection and treatment.

KEY WORDS: Convolutional Neural Network, Deep learning, detection, transfer learning, Skin
cancer.

INTRODUCTION Skin cancer is classified into Melanoma, Basal Cell


Carcinoma (BCC) and Squamous Cell Carcinoma (SCC).
Skin cancer is the uncontrollable growth of damaged Melanoma is the most dangerous type of cancer which
cells in the outer most layer of the skin. This is because leads to death that usually appears on the moles and the
of damage in DNA sequence due to the environmental areas on the skin which is exposed to sunlight as well
factors like cigarette smoke and exposure to Ultra Violet as not exposed to sunlight. The affected part of the skin
(UV) light. DNA damage triggers mutation which leads contains melanocytes that spread to other parts of the
to rapid multiplication of skin cells that forms malignant body. BCC is the most laggard growing and never be large
tumors [Miller .et. al. (1994)]. in size. It appears on the skin exposed areas such as hand,
face, leg, ears and scalp. It usually matures as an ulcer
and does not improve. The early detection of this can be
curable. Some are hostile and cannot be treated because
ARTICLE INFORMATION it spreads to the deeper cells of the tissue. SQC appears on
*Corresponding Author: [email protected]
the sun exposed part and on the incurable inflammation
Received 05th Oct 2020 Accepted after revision 10th Dec 2020 part of the body and occurs in the person who has low
Print ISSN: 0974-6455 Online ISSN: 2321-4007 CODEN: BBRCBA immune power. It is large, appears in incurable scars and
in lips. The early detection is possible.
Thomson Reuters ISI Web of Science Clarivate Analytics USA and
Crossref Indexed Journal

55
NAAS Journal Score 2020 (4.31) SJIF: 2020 (7.728)
A Society of Science and Nature Publication,
Bhopal India 2020. All rights reserved.
Online Contents Available at: http//www.bbrc.in/
Doi: http://dx.doi.org/10.21786/bbrc/13.11/13
S. Sasikala et al.,

Benign is a non-cancerous which does not spread to accuracy. The Pre-processing increases the performance
any other parts of the body. It is caused due to exposure by noise removal. Post-processing enhanced the image
of sunlight, inflammation of skin, infections, and quality and the boundary of the cancer cell was enhanced.
genetics. The problem is that the dataset was too small. There was
no uniqueness in the image processing technique and
Melanoma mostly occurs in the skin rarely in the mouth the variations between the dermoscopy and the digital
and intestines with the abnormal cells that contain image were large. By increasing the number of images
melanocytes which control the pigment in our skin. For in the data set, high accuracy over training and testing
women, melanoma mostly occurs on the legs and for data set could be obtained [Lau, H.T. and Al-Jumaily,
men on the back. They usually develop from the mole A., (2009)].
with abnormal changes as an increase in size, changes
in the color, causes itches or skin breakdown. It can Skin cancer is the most common disease in human
occur in the areas between fingernails, palms, toenails and its incidence is increasing dramatically. The newer
and eyes [Miller .et. al. (1994)]. Benign usually appears technology-based detecting skin cancer is recommended
on the skin which is highly exposed to sunlight such as for accurate identification but the percentage of detection
face, shoulders, neck, hand and leg. This appears as lump by computer is comparatively high with manual
and looks like patches which continues after a week and detection. Here Digital Dermoscopy is widely considered
develops over a month or a year. as one of the most effective means to classify the skin
cancers. Segmentation of images is done using K-means
Skin cancer is the common type of cancer in worldwide algorithm. It includes various stages like skin image,
and especially in US. By the age of 70, skin cancer will be enhancement, lesion segmentation, feature extraction
developed by 1 in 5 Americans. In every hour, more than and finally classifying it to normal and abnormal.
2 people die because of skin cancer. Risk for melanoma Convolution Neural Network (CNN) for detection of
will be doubled while exposure of sunburns is more images, which is much cost-efficient in comparison
than 5 in number. Early detection helps to survive for 5 with digital dermoscopy gives accurate output with
years and the survival rate is 99 percent. At least 40% appropriate detection of the cancer. The model proposed
of cases have skin cancer when globally accounting for the automatic method of detecting skin cancer from
common cancer. Non-melanoma skin cancer occurs 2 the photographed image which was captured from the
to 3 million people per year. Globally in 2012, 232,000 affected area of the skin. In this, Support Vector Machine
people were in skin cancer, and 55,000 people died. (SVM) algorithm is used to classify the image which was
According to the survey of last 20 to 40 years, Australia either melanoma or benign. A total of 100 image for
(white people), New Zealand and South Africa People melanoma and 100 for benign was used in the study. The
have the highest rate of Skin cancer in the world [Apalla, eminent drawback of this method is that the data set did
Z.et. al. (2017)]. not contain the dark-skinned images. To overcome these
difficulties, more images are used to train the data and
The early detection involves Biopsy method, in that the to test the trained data with all types of images of the
damaged skin is removed and tested in laboratories which skin [Esteva, A et. al (2017)].
take longer duration for the detection of skin cancer and
it is more painful method. Computer Aided Diagnosis Three methods were used for the segmentation of
(CAD) is used to avoid the longer duration consumption Otsu's method, gradient vector flow and color-based
and it is a non-invasive method. Many works in literature segmentation using K-mean clustering. Otsu's method
[Sasikala, S. et al. (2018) & (2020)] have focused on did not require any variation in the parameter for the
machine learning, feature transformation, optimisation, different skin lesions. The gradient vector flow had the
and deep learning for improving the cancer diagnosis. active contour to boundary concavities although with
Henceforth, the proposed work aims to develop a CAD the presence of the noises. The drawback of it was the
system for early identification of skin cancer using deep execution speed to converge to the object. This method
learning. required the changing parameter for the different skin
lesions. In color-based classification, it had the possibility
The significant contributions of the proposed work of reducing the computational cost calculation for every
are: pixel in the image. To overcome these drawbacks, the
• To design a cost-effective CAD system for the early Convolutional Neural Network (CNN) algorithm with the
identification of skin cancer. back-propagation model is used for the fast execution
• To construct a deep learning model that can detect to converge the object image for training [Rubegni P et
and categorize given image into either a benign type al. (2012)].
or malignant type.
• To reduce training time by using pre-trained model An artificial neural network algorithm was used for the
with high accuracy rate. classification of the image and feature extraction for the
thresholding. This method involved a binary classifier for
Related Works: Automatic detection of skin cancer classifying benign and malignant tumor. By the result
involved pre-processing and the post-processing of the artificial neural network, the accuracy was low.
techniques for the classification of the image with high The different types of classification methods and image

56
S. Sasikala et al.,

processing techniques could be used for high accuracy algorithm was used in this method to classify the images
and the accurate detection of the cancer [Hosny, K.M., as melanoma or benign. The performance accuracy of
Kassem, M.A. and Foaud, M.M. (2018)]. the proposed model was high. The back-propagation
method was used to fine-tune the weights to classify the
Melanoma and benign lesions have high similarity, due images accurately. From the literature, it is observed that
to this it takes a long time to identify and classify. The using CNN with the ResNet 34 architecture gives high
automatic classification of skin lesions helps to reduce accuracy with the low error rate with the probability
time, efforts and one of the best ways to give an accurate of the classifier. Therefore, the proposed method for
identification of lesions. The use of transfer learning and classifying benign and malignant tumors using CNN
pre-trained neural network has been experimented. In this with ResNet architecture.
method, binary classifier model was used. This proposed
method provides accuracy around 96 percentage. The Material and Methods
weights are fine-tuned and the dataset undergoes various
rotation angles to overcome problems. From this paper, In the present time, machine learning and deep learning
we included a feature for greater accuracy for the better approaches are used in healthcare for improved
identification of lesions [Mahmoud, M.K.A., Al-Jumaily, diagnosis. In this work, Convolutional Neural Network
A. and Takruri, M (2011)]. (CNN) algorithm with four different transfer learning
approaches viz, AlexNet, VGG16, ResNet50, ResNet34 are
Rule based approach, back propagation and neural used to classify the images of the skin with dermoscopic
network was used to select the features and to classify analysis which enables fast detection. The workflow with
the lesions. The lesions were either melanoma or benign. RESNET 34 transfer learning is proposed in figure 1.
As in this, the number of correct classifications increased.
The neural network handled the complex relations
among the identification of lesions. This model had a Figure 1: Architecture for Skin Cancer detection
drawback of slow convergence rate and the trapping
of the local minima. To overcome this, CNN could be
used to increase the convergence rate and reduce the
complexity of classifying the images to increase the
trapping of the local minima [Mendes, D.B. and da Silva,
N.C. (2018)]. ResNet-134 architecture was used that was
trained over 3797 images and later 956 images were
tested with the network and achieved an accuracy of
about 78%. This technique took a long time to train the
data set of approximately 35 hours. The images were Table I represents the number of layers and the
not trained properly and led to the wrong prediction parameters used in the four transfer learning approaches
of the cancer lesions and made a problem for humans. used in this work.
By using ResNet 34, the time consumption to train the
data set and the accuracy could be reduced [Jain, S. and
Pise, N. (2015)]. Table 1. Different types of CNN Architectures Used

SVM algorithm and snake active contour were used for Name of the Number Number of
image segmentation. To reduce the complexity in SVM, Architecture of Layers Parameters
the snake parameters were used to predict the initial curve.
The segmentation and the classification of the images are
Alexnet 8 61M
not accurate. To overcome these difficulties, CNN with
ResNet 34 architecture could be used to detect the image VGG 16 16 138 M
accurately without any discrepancy [Aswin, R.B., Jaleel, ResNet 34 34 21.282M
J.A. and Salim, S. (2014)]. Computer-aided approach ResNet 50 50 23.521M
was used to detect skin cancer. The steps involved
in the detection of cancer are image pre-processing,
segmentation, feature extraction, and classification. Figure 2: Benign tumour Malignant tumour
Image resizing affected the quality of classification. By
using this method, segmentation process involved the
drawback was that the large stacks of data set could not
be used for the classification of the image. To overcome
these drawbacks, the CNN algorithm is used to classify
large data set for accurate results [Hosny, K.M., Kassem,
M.A. and Foaud, M.M.(2019)].

Transfer learning was applied with AlexNet by replacing


last layer to classify the different types of lesions as
melanoma and benign by softmax classification. CNN
57
S. Sasikala et al.,

Data Base: The data sets are clinical images which which is a small matrix is used. The size of the typical
are collected from Kaggle [kaggle.com]. The dataset filter on the first layer of CNN is [5x5x3]. After
has images of benign and malignant skin lesions in a computing the dot product and by sliding the filter over
balanced number. It consists of malignant and benign the image, a convolved feature, activation map or feature
classes with 1800 images each. 70% of data is used for map is formed (output volume). The number of filters is
training and 30% for testing. A sample image in database known as depth. The size of the filter and the receptive
is shown in figure 2. field, which is the local region of the input volume are
the same. The set of neurons that are all pointing to the
Transfer learning is one of the machine learning receptive field is known as depth column or fiber. Stride
techniques, used to develop a model for any recognition/ is used for spatially producing smaller output volumes.
classification task. Also, it is the recommended method in
deep learning where pre-trained models are used as the Pool Layer: The function of this layer reduces the
starting point of analysis. In transfer learning, a model computational complexity of the model and spatial
trained on a single task is repurposed on another related dimensions of the given input data. Over fitting is also
task. It is an optimization that allows quick progress controlled by this layer. It does not depend on the depth
when modelling the new task. slice of the input. Different functions are Max pool,
Average pool or L2 norm-pool. Max pooling is the most
Convolutional Neural Network (CNN): A Convolutional important part of the input layer.
Neural Network (CNN or ConvNet) is a specialized type
of artificial neural network (ANN) which is used in image
processing, recognition and this is designed to process Table 2. Results obtained with four CNN models
pixel data. CNN has some layers as the input layer, an
output layer and hidden layers (multiple convolutional MODEL/ ResNet34 ResNet50 VGG16 AlexNet
layers, pooling layers, fully connected layers and Metrics
normalization layers) [Krizhevsky, A., Sutskever, I. and
Hinton, G.E(2017)]. The figure 3 represents the highly Accuracy 88.4 % 76.9 % 69.2 % 65.3 %
performing architecture of CNN. Input Layer. The input Error Rate 17.6 % 30.7 % 26.9 % 26.9 %
layer or volume is an image and the dimensions of the Sensitivity 0.875 0.875 0.875 1
image are [width x height x depth]. This dimension Specificity 0.778 0.875 0.556 0.5
denotes the matrix of pixel values. For example, input
F1 score 0.736 0.736 0.608 0.64
is [32x32x3]. So width=32, height=32 and depth=3. Here
the depth represents R, G, B channels. And the input
volume should be divisible number of times by 2.
Table 3. Epoch Vs accuracy and error rate table

Figure 3: Convolutional Neural Network with its layers


EPOCH TRAINING VALID ACCURACY ERROR
LOSS LOSS (%) RATE

0 0.8663 0.5069 79.78 0.202


10 0.4237 0.3699 84.49 0.1550
20 0.2985 0.3901 81.76 0.1823
30 0.2321 0.3265 86.77 0.1322
40 0.1562 0.3912 86.02 0.1398
50 0.1219 0.3808 87.84 0.1215
60 0.1120 0.3591 88.14 0.1185
70 0.084 0.3691 88.45 0.1155
80 0.0655 0.3957 88.90 0.1109
Convolutional Layer: The main objective of this layer 90 0.0486 0.3945 88.75 0.1124
is feature extraction from the input layer. A small part 99 0.0661 0.3858 88.6 0.1139
of the image is joined to the convolutional layer to
reduce the expense. For this purpose, dot products are
Fully Connected Layer: The main function of this layer
applied between a filter and a receptive field on all the
is to connect each neuron of one layer to each neuron
dimensions. After this dot product, the output volume
in another layer. This layer uses the softmax activation
with a single integer is obtained. This is known as a
function. This function is used for classifying the
feature map. This process is done for the entire input
generated features of the input images into various
image. The input for the next layer will be the output
classes. This classification is based on the training
of the present layer. For feature detection, filter, kernel
dataset.
or feature detector

58
S. Sasikala et al.,

Resnet: ResNet is the short form for a residual network


which is an ANN kind. ResNet could train extraordinary Table 4. Epoch Vs accuracy and error rate table for optimal
deep neural networks with more than 500 layers and still learning rate
achieves powerful performance. According to the number
of layers in the network, the number of parameters is EPOCH TRAINING VALID ACCURACY ERROR
selected. At its core, it uses batch normalization. The LOSS LOSS (%) RATE
input layer is adjusted by batch normalization for
increasing the performance of the network. The problem
0 0.8663 0.3291 89.51 0.1048
of covariate shift is reduced. The identity connection
helps to preserve the network from vanishing gradient 1 0.4237 0.3354 89.96 0.1003
problem. This connection is used in ResNet. Bottle design 2 0.2985 0.3285 89.81 0.1018
residual network is used by Deep Residual Network to 3 0.2321 0.3951 89.66 0.1033
increase the network performance [He, K., Zhang, X., 4 0.1562 0.3852 89.81 0.1018
Ren, S. and Sun, J. (2016)]. Res-Net converges faster than 5 0.1219 0.4383 89.05 0.1094
plain counterpart. It also reduces degradation problem.
ResNet-34 architecture offers bigger batch size which 6 0.1120 0.3675 89.05 0.1094
reduces training time. Further, ResNet-34 has a better 7 0.084 0.4057 88.75 0.1124
validation error of 5.6% when compared to VGG. This is 8 0.0655 0.4074 88.75 0.1124
due to different depths of models. Hence Resnet is used 9 0.0486 0.4150 88.44 0.1155
in the proposed work. 10 0.0661 0.3712 90.12 0.0987

RESLTS AND DISCUSSION


CONCLUSION
The data sets are processed with pre-trained CNN ResNet
34 networks to classify the type of skin cancer that is Detection of skin cancer lesions as malignant (melanoma)
either benign or malignant. The final testing stage is or benign is performed using the CNN RESNET34. The
done by choosing random skin lesion image. It is then performance of this system is studied using the accuracy
tested for accuracy and error rate. Skin cancer detection and error rate with respect to the variations in number
is done with python for Transfer learning. The initial of epochs and learning rate. The accuracy increases
results obtained with all four approaches are tabulated with decrease in learning rate. The Maximum accuracy
in the Table 2 below. Among the four models RESNET 34 of 90.12% is achieved when LR is decreased to 1x10-6
shows better performance than the other three models. after 10 epochs. In this work, only the detection of skin
cancer is considered. In future, it could be extended for
ResNet 34 alters only the first and last layer that is the diagnosis of various types of skin cancer such as
classification layers for more efficiency when compared melanocytic nevi, BCC, SCC through multi class classifier
with already proposed methods. By using a pre-trained and collecting appropriate data sets. The number of
RESNET model and GPU, the training time had been layers in the CNN could also be increased for further
reduced to 1 hour. The detection of Skin cancer involves improvement in the performance. Strengthening the
binary classifier as malignant and benign. Skin cancer dataset by increasing the images in each class will also
detection is done with a different number of Epochs and lead better diagnostic results.
learning rates. The lower number of epoch and a higher
learning rate results in more error probability and less References
accuracy. The number of epochs given and corresponding Apalla, Z., Nashan, D., Weller, R.B. and Castellsagué,
output are listed in the Table 3 for training ResNet using X., (2017). Skin cancer: epidemiology, disease burden,
higher Learning Rate (LR). The loss vs accuracy obtained
pathophysiology, diagnosis, and therapeutic approaches.
by initially testing with 100 images of data sets with
70 for train and validation respectively is studied. This Dermatology and therapy, 7(1), pp.5-19..
resulted in high validation loss and less accuracy (62%). Aswin, R.B., Jaleel, J.A. and Salim, S., (2014). Hybrid
To improve the system accuracy the training process genetic algorithm—Artificial neural network classifier for
used several data sets. Further training with 4360 images skin cancer detection. In 2014 International Conference
(Train - 3700, Valid - 660) of data set gives improved
on Control, Instrumentation, Communication and
accuracy of about 88.6% in 100 epochs.
Computational Technologies (ICCICCT) (pp. 1304-1309).
For the accurate detection of skin cancer, the learning IEEE..
rate is given as lower and higher as 1e-06 and 1e-03 with Miller, D.L. and Weinstock, M.A., (1994). Nonmelanoma
a loss of 0.06 and 0.145 respectively. With the maximum skin cancer in the United States: incidence. Journal of
learning rate of 1e-03, the following accuracy and error the American Academy of Dermatology, 30(5), pp.774-
rate for 10 epochs are identified. This gives the maximum
778.
accuracy of 90.12% and the minimum error rate of 9.8%
after 10 epochs. The table below shows the change in Esteva, A., Kuprel, B., Novoa, R.A., Ko, J., Swetter, S.M.,
accuracy and error rate for every epoch. The results are Blau, H.M. and Thrun, S., (2017). Dermatologist-level
tabulated in Table IV. classification of skin cancer with deep neural networks.

59
S. Sasikala et al.,

nature, 542(7639), pp.115-118. based diagnosis of melanoma using only useful image
He, K., Zhang, X., Ren, S. and Sun, J., (2016). Deep features. In 2018 International Workshop on Advanced
residual learning for image recognition. In Proceedings Image Technology (IWAIT) (pp. 1-4). IEEE.
of the IEEE conference on computer vision and pattern Mahmoud, M.K.A., Al-Jumaily, A. and Takruri, M.,
recognition (pp. 770-778). (2011). The automatic identification of melanoma by
Hosny, K.M., Kassem, M.A. and Foaud, M.M., (2018). wavelet and curvelet analysis: study based on neural
Skin cancer classification using deep learning and network classification. In 2011 11th International
transfer learning. In 2018 9th Cairo International Conference on Hybrid Intelligent Systems (HIS) (pp.
Biomedical Engineering Conference (CIBEC) (pp. 90-93). 680-685). IEEE..
IEEE. Mendes, D.B. and da Silva, N.C., (2018). Skin lesions
Hosny, K.M., Kassem, M.A. and Foaud, M.M., (2019). classification using convolutional neural networks in
Classification of skin lesions using transfer learning clinical images. arXiv preprint arXiv:1812.02316..
and augmentation with Alex-net. PloS one, 14(5), Rubegni P, Cevenini G, Burroni M, Perotti R, Dell'Eva
p.e0217293. G, Sbano P, Miracco C, Luzi P, Tosi P, Barbini P,
https://www.kaggle.com/fanconic/skin-cancer- Andreassi L. (2002) Automated diagnosis of pigmented
malignant-vs-benign skin lesions. International Journal of Cancer. 2002 Oct
Jain, S. and Pise, N., (2015). Computer aided melanoma 20;101(6): 576-80.
skin cancer detection using image processing. Procedia Sasikala, S., Bharathi, M. and Sowmiya, B.R., (2018).
Computer Science, 48, pp.735-740.. Lung Cancer Detection and Classification Using Deep
Krizhevsky, A., Sutskever, I. and Hinton, G.E., (2017). CNN. International Journal of Innovative Technology
Imagenet classification with deep convolutional neural and Exploring Engineering (IJITEE) ISSN, pp.2278-
networks. Communications of the ACM, 60(6), pp.84- 3075.
90. Sasikala, S., Ezhilarasi, M. and Kumar, S.A., (2020).
Lau, H.T. and Al-Jumaily, A., (2009), December. Detection of breast cancer using fusion of MLO and
Automatically early detection of skin cancer: Study CC view features through a hybrid technique based
based on neural netwok classification. In 2009 on binary firefly algorithm and optimum-path forest
International Conference of Soft Computing and Pattern classifier. In Applied Nature-Inspired Computing:
Recognition (pp. 375-380). IEEE. Algorithms and Case Studies (pp. 23-40). Springer,
Mustafa, S., & Kimura, A. (2018, January). An SVM- Singapore.

60

You might also like