Mesopotamian Journal of Artificial Intelligence in Healthcare

Vol.2023, pp. 57–60

DOI: https://doi.org/10.58496/MJAIH/2023/011; ISSN: 3005-365X
https://mesopotamian.press/journals/index.php/MJAIH

Review Article
The Benefit of Artificial Intelligence in the Analysis of Malignant Brain Diseases: A
Mini Review
Humam Imad Wajeeh Al-Shahwani1,2*, , Alaa K. Faieq3,

1 Fakulti Teknologi Maklumat dan Komunikasi, Universiti Teknikal Malaysia Melaka, Malacca, Malaysia
2 Computer Science Department, College of Science, University of Baghdad, Baghdad, Iraq
3 College of Engineering, University of Information Technology and Communications, Baghdad, Iraq

A R TICLE INFO A BS TR ACT

Article History Brain diseases are considered life-threatening malignant diseases. Malignant brain diseases, such as
Received 10 July 2023
glioblastoma multiforme (GBM) and metastatic brain tumours, present significant challenges as doctors
Accepted 25 Oct. 2023 and healthcare workers must constantly monitor the patient's condition due to their aggressive nature and
Published 4 Nov. 2023 limited treatment options. In recent decades, artificial intelligence techniques and practices have
developed significantly in medical imaging disease diagnosis and contributing to the development of
Keywords
vaccines and vaccines. In this article, we will highlight the ability of artificial intelligence techniques to
Brain diseases
analyse and diagnose malignant brain diseases, enhance early detection of the disease, and help doctors
Machine learning treat patients. This article concluded that artificial intelligence is an essential part of assisting physicians
Artificial intelligence to make suitable decisions in real-time, and it also has a significant role in clinical practices, improving
Medical domain patient outcomes and providing excellent healthcare to patients.
Clinical practices

1. INTRODUCTION
In the medical domain, diagnostic imaging is one of the essential matters that is used to classify brain tumours and determine
the type of tumour that the patient suffers from with high accuracy and in a short period [1][2]. This procedure contributes
to determining appropriate and effective treatment to reduce the effects of the disease and improve patient outcomes. The
integration of artificial intelligence technologies into medical systems has led to a significant improvement in the
performance of health institutions in providing outstanding electronic healthcare while enhancing the accuracy of results
and reducing human errors [3-5]. In recent years, especially after the COVID-19 pandemic, artificial intelligence has begun
to make its way into various fields, and the medical domain is no exception [6][7]. The application of computer vision in
medical systems has a significant impact in the field of image diagnosis and analysis, as it has proven its ability to keep up
with specialists trained for this objective with high accuracy. Moreover, these systems can achieve these tasks in a
significant, instantaneous manner, which is unimaginable for humans, who are limited by factors such as fatigue,
exhaustion, and the speed of absorbing and extrapolating person-specific data. Computer vision is a branch of machine
learning that grows and enhances based on convolutional neural networks [8][9]. These networks have a remarkable ability
to find the most complex patterns hidden in a medical image based on pre-training, as they are provided with a large set of
images of what they want to discover or classify with high accuracy [10][11]. This makes it an essential tool in classification
tasks where there is incredible complexity when determining the type of tumour a patient has from medical images [12][13].
In other words, this complexity results from the significant anomalies present in these images in terms of location and shape
and even the possibility of the presence of different diseases with a similar appearance in the patient, which is challenging
to identify, even for specialists in the neurology domain. But there are other clinical tasks in which it can be used computer
vision. In fact, there are a large number of medical tools that use digital systems to obtain images of the inside of the
patient’s body in different dimensions. Whether viewed in real-time, such as through ultrasounds and CT scans, or from
impressions, such as MRIs and X-rays, it can be said that computer vision has a comprehensive and great scope in the

*Corresponding author. Email: [email protected]

58 Al-Shahwani et al, Mesopotamian Journal of Artificial Intelligence in Healthcare Vol.2023, 57–60

medical field. In the case of brain tumours, MRI is utilised because it is a medical examination that is not harmful to health
and provides clear images of internal tissues with details (See Figure 1).

Fig. 1. The difference between normal and tumour brain images [14].

Malignant brain diseases (glioblastoma multiforme (GBM) and metastatic brain tumours) are diseases that grow rapidly
and increase the number of deaths in the world. It requires the patient to pay significant attention to seeing a physician,
making accurate early diagnoses, and following customised treatment strategies regularly. Artificial intelligence
techniques, such as machine learning, have a significant role in improving the outcomes of brain tumours [15][16]. Machine
learning algorithms have the remarkable ability to analyse huge amounts of neuroimaging data, allowing physicians to see
the location of the disease and diagnose it more accurately and promptly [17][18]. These algorithms have the potential to
compete with oncology experts. Brain tumours are malignant tumours that grow in the brain or near it. They can occur in
brain tissue, including nearby nerves, the pituitary gland, and the membranes that cover the surface of the brain. These
tumours have an aggressive nature and have a profound impact on patients' lives. The growth of these tumours makes their
early detection and effective management a complex mystery for healthcare professionals. Traditional methods of
diagnosing these tumours relied heavily on the experience of radiologists and pathologists who analyse medical images,
tissue samples, and patient data by following straightforward strategies, as they have sufficient experience in diagnosing
these complex images. In addition, their ability to quickly process a huge amount of information is limited and may
sometimes need to be more accurate. Therefore, integrating artificial intelligence technologies and practices into the
healthcare environment is considered a major transformative force in developing the capabilities of radiology and brain
science specialists. These techniques have the ability to analyse a huge amount of information and have tremendous
capabilities in managing data and diagnosing the disease with high accuracy in identifying subtle abnormalities and
predicting the development of the disease with remarkable accuracy and speed within the patient’s body. The integration
of machine learning algorithms into healthcare and neuroimaging is a significant paradigm shift in dealing with malignant
brain diseases. These algorithms have a high potential to study disease behaviours, identify new patterns, and provide a
combined and comprehensive vision for monitoring disease development. This mini review contributes to providing a
comprehensive overview of the role of artificial intelligence in analysing malignant brain diseases and classifying and
diagnosing the disease. Artificial intelligence contributes to enhancing the accuracy of diagnosis, customising treatment
strategies, improving patient outcomes, and predicting disease development.

2. AI IN THE FACE OF MALIGNANT BRAIN DISEASES

The application of artificial intelligence techniques and machine learning algorithms in the field of treating neurological
tumours has created a significant breakthrough in the way of dealing with malignant diseases that affect the human brain .
The capabilities of artificial intelligence are being utilised across various phases of disease management, developing
healthcare systems, and assisting physicians in the early detection of diseases and predicting treatment and effects. This
section will discuss how artificial intelligence can be used to fight malignant brain diseases and assist physicians in making
sound medical decisions.
Early disease detection is one of the primary aspects that all physicians call for adherence to. Identifying tumours, their
types and locations in a timely manner can significantly affect treatment strategies, improve patient outcomes, and provide
them with advice and treatment. Medical imaging analysis supported by artificial intelligence is a practical tool that aims
to analyse tumour behaviour and identify abnormalities and disease areas. Machine learning algorithms analyse CT scans,
59 Al-Shahwani et al, Mesopotamian Journal of Artificial Intelligence in Healthcare Vol.2023, 57–60

X-rays, and MRI scans with high and remarkable accuracy, providing complete details about deformities and tumours and
distinguishing between benign and malignant diseases. Moreover, these algorithms contribute to reducing human errors
and accelerating the process of diagnosis and classification of data and images. Artificial intelligence techniques are used
in the surgical field, where surgeons use systems supported by artificial intelligence to enhance the accuracy of their work
and the safety of removing brain tumours. These systems combine preoperative imaging data with the patient's reaction
during the surgical procedure in real-time. This procedure assists surgeons to visualise the tumour's location accurately and
its relationship to vital brain structures. It also seeks to reduce damage to healthy tissue and enhance surgical results. At
significant, malignant brain diseases are heterogeneous, so it is preferable to design methods that contribute to treating
patients by providing them with appropriate treatment. Machine learning plays a significant role in analysing genetic and
molecular data, identifying the unique characteristics of the tumour, and finding the most practical treatment, as these
procedures contribute to saving patients’ lives and reducing side effects resulting from taking unnecessary medications.
Artificial intelligence techniques contribute to creating models to predict the development of disease stages, analysing
patient data and tumour characteristics while providing insights into how the tumour develops within the body and how the
patient may respond to the treatment proposed by specialists. All the details displayed by artificial intelligence are essential
to physicians because they assist them in making decisions and planning to perform surgery or treatment. Also, artificial
intelligence helps discover and develop appropriate treatments for all stages of the disease, as machine learning algorithms
can analyse large amounts of data for chemical compounds and predict their effectiveness against malignant brain tumours.
Drug discovery and growth are among the priorities of artificial intelligence through the implementation of structures
programmed to perform behaviours similar to specialists in drug and vaccine management [19][20]. There is another aspect
of artificial intelligence, as it contributes to the development of radiology by creating an advanced approach that extracts
quantitative information from medical images. This approach provides details that the human eye cannot see while
providing information on the tumour's heterogeneity, shape, and relationship with the brain. The advantages offered by this
approach are considered biomarkers for tumour characterization and disease diagnosis. The major goal of this approach is
to assist healthcare workers and specialists in monitoring patients and seeing the precise details of the tumour. Continuous
monitoring of patients is one of the most important priorities of healthcare workers because it contributes to saving lives,
knowing the stages of progress of the treatment suggested for them, and collecting complete details about the patient.
Systems that operate with artificial intelligence can assist in data analysis and report any signs indicating recurrence or
progression of the disease and allow healthcare workers to intervene immediately, modify treatment plans, improve
outcomes, and prevent dangerous stages that may lead to death. Machine learning algorithms are integrated into clinical
trials and research studies, analysing patient data based on their medical records and identifying individuals who may
benefit from experimental treatments, as they provide an environment in which patients can access advanced and practical
therapies. The primary goal of creating predictive models based on artificial intelligence is to study the behaviour of
clinical, radiological, and genetic data, as well as to assist in making decisions regarding treatment when dealing with
aggressive brain tumours. Artificial intelligence helps reduce disparities in healthcare services and provides electronic
services with significant resources. Moreover, the establishment of telemedicine allows people who live in distant areas to
get to hospitals and establish continuous communication with physicians and healthcare workers.

3. CONCLUSIONS
Artificial intelligence techniques are valuable in healthcare institutions, especially in managing malignant brain diseases
and early disease detection. These techniques have a role in directing surgery, individualising treatment, prognosticating,
and determining the appropriate treatment for this disease. Therefore, the presence of these techniques contributes to
developing the treatment of malignant brain tumours, enhancing patient outcomes, providing them hope, and saving their
lives. Moreover, artificial intelligence techniques are characterised by providing practices for protecting patient data
through a set of regulatory frameworks and not allowing anyone to manipulate it or make any modifications. Therefore,
the presence of these techniques in the systems of health institutions is considered necessary in the face of malignant brain
diseases. Artificial intelligence techniques are constantly growing and have high potential in developing healthcare workers
and helping them in continuous monitoring of patients and saving their lives.

Funding
The authors had no institutional or sponsor backing.
Conflicts Of Interest
The author's disclosure statement confirms the absence of any conflicts of interest.
60 Al-Shahwani et al, Mesopotamian Journal of Artificial Intelligence in Healthcare Vol.2023, 57–60

Acknowledgment
The authors extend appreciation to the institution for their unwavering support and encouragement during the course of
this research.

References
[1] I. Qureshi, J. Yan, Q. Abbas, K. Shaheed, A. B. Riaz, A. Wahid, et al., “Medical image segmentation using deep
semantic-based methods: A review of techniques, applications and emerging trends,” Information Fusion, vol.90,
pp.316-352, February 2023. https://doi.org/10.1016/j.inffus.2022.09.031
[2] P. Kora, C. P. Ooi, O. Faust, U. Raghavendra, A. Gudigar, et al., “Transfer learning techniques for medical image
analysis: A review,” Biocybernetics and Biomedical Engineering, vol.42, no.1, pp.79-107, March 2022.
https://doi.org/10.1016/j.bbe.2021.11.004
[3] S. Vyas, M. Shabaz, P. Pandit, L. R. Parvathy, and I. Ofori, “Integration of Artificial Intelligence and Blockchain
Technology in Healthcare and Agriculture,” Journal of Food Quality, vol.2022, no.4228448, pp.1-11, May 2022.
https://doi.org/10.1155/2022/4228448
[4] A. V. L. N. Sujith, G. S. Sajja, V. Mahalakshmi, S. Nuhmani, and B. Prasanalakshmi, “Systematic review of smart
health monitoring using deep learning and Artificial intelligence,” Neuroscience Informatics, vol.2, no.3, pp.100028,
September 2022. https://doi.org/10.1016/j.neuri.2021.100028
[5] C. Comito and C. Pizzuti, “Artificial intelligence for forecasting and diagnosing COVID-19 pandemic: A focused
review,” Artificial Intelligence in Medicine, vol.128, pp.102286, June 2022.
https://doi.org/10.1016/j.artmed.2022.102286
[6] M. M. Mijwil, “Deep Convolutional Neural Network Architecture to Detection COVID-19 from Chest X-ray Images,”
Iraqi Journal of Science, vol.64, no.5, pp.2561-2574, May 2023. https://doi.org/10.24996/ijs.2023.64.5.38
[7] D. M. El-Sherif, M. Abouzid, M. T. Elzarif, A. A. Ahmed, A. Albakri, and M. M. Alshehri, “Telehealth and Artificial
Intelligence Insights into Healthcare during the COVID-19 Pandemic,” Healthcare, vol.10, no.2, pp.1-15, February
2022. https://doi.org/10.3390/healthcare10020385
[8] M. M. Mijwil, AH. Al-Mistarehi, M. Abotaleb, E. M. El-kenawy, A. Ibrahim, A. A. Abdelhamid, M. E. Eid, “From
Pixels to Diagnoses: Deep Learning's Impact on Medical Image Processing-A Survey,” Wasit Journal of Computer
and Mathematics Science, vol.2, no.2, pp.8-14, September 2023. https://doi.org/10.31185/wjcms.178
[9] U. K. Lilhore, A. L. Imoize, C. Lee, S. Simaiya, S. K. Pani, et al., “Enhanced Convolutional Neural Network Model
for Cassava Leaf Disease Identification and Classification,” Mathematics, vol.10, no.4, pp.1-19, February 2022.
https://doi.org/10.3390/math10040580
[10] M. M. Mijwil and E. A. Al-Zubaidi, “Medical Image Classification for Coronavirus Disease (COVID-19) Using
Convolutional Neural Networks,” Iraqi Journal of Science, vol.62, no.8, pp.2740-2747, August 2021.
https://doi.org/10.24996/ijs.2021.62.8.27.
[11] L. Gaur, U. Bhatia, N. Z. Jhanjhi, G. Muhammad, and M. Masud, “Medical image-based detection of COVID-19 using
Deep Convolution Neural Networks,” Multimedia Systems, vol.29, pp.1729–1738, April 2021.
https://doi.org/10.1007/s00530-021-00794-6
[12] M. M. Mijwil, R. Doshi, K. K. Hiran, O. J. Unogwu, and I. Bala, “MobileNetV1-Based Deep Learning Model for
Accurate Brain Tumor Classification,” Mesopotamian Journal of Computer Science, vol.2023, pp:32-41, March 2023.
https://doi.org/10.58496/MJCSC/2023/005
[13] M. Aamir, Z. Rahman, Z. A. Dayo, W. A. Abro, M. I. Uddin, et al., “A deep learning approach for brain tumor
classification using MRI images,” Computers and Electrical Engineering, vol.101, pp.108105, July 2022.
https://doi.org/10.1016/j.compeleceng.2022.108105
[14] G. Maheswari and K. V. Shaheena, “MRI Brain Tumor Segmentation Algorithms and Approaches-A Survey,”
International Journal of Latest Engineering and Management Research, vol.2, no.1, pp.33-37, October 2017.
[15] A. Raza, H. Ayub, J. A. Khan, I. Ahmad, A. S. Salama, et al., “A Hybrid Deep Learning-Based Approach for Brain
Tumor Classification,” Electronics, vol.11, no.7, pp.1-17, April 2022. https://doi.org/10.3390/electronics11071146
[16] M. Rasool, N. A. Ismail, W. Boulila, A. Ammar, H. Samma, et al., “A Hybrid Deep Learning Model for Brain Tumour
Classification,” Entropy, vol.24, no.6, pp.1-16, June 2022. https://doi.org/10.3390/e24060799
[17] Y. Kumar, A. Koul, R. Singla, and M. F. Ijaz, “Artificial intelligence in disease diagnosis: a systematic literature
review, synthesizing framework and future research agenda,” Journal of Ambient Intelligence and Humanized
Computing, vol.14, pp.8459–8486, January 2022. https://doi.org/10.1007/s12652-021-03612-z
[18] S. M. Khazaal and H. Maarouf, “Utilization of machine learning techniques to predict coronary artery Disease: A
Comparative Study,” Journal of Baghdad College of Economic Sciences, vol.74, pp.289-301, October 2023.
[19] O. J. Unogwu, M. Ike, and O. O. Joktan, “Employing Artificial Intelligence Methods in Drug Development: A New
Era in Medicine,” Mesopotamian Journal of Artificial Intelligence in Healthcare, vol.2023, pp.52–56, October 2023.
https://doi.org/10.58496/MJAIH/2023/010
[20] M. J. Lamberti, M. Wilkinson, B. A. Donzanti, G. E. Wohlhieter, S. Parikh, et al., “A Study on the Application and
Use of Artificial Intelligence to Support Drug Development,” Clinical Therapeutics, vol.41, no.8, pp.1414-1426,
August 2019. https://doi.org/10.1016/j.clinthera.2019.05.018