A Survey on Brain Tumor Diagnosis

Brain Tumors are extremely dangerous since they take many lives annually. Excrescence damages brain tissue or raises intracranial pressure, which has an impact on the brain. It is crucial to identify brain tumors accurately and promptly to treat this deadly illness. Prior discovery can save a life w...

Full description

Saved in:
Bibliographic Details
Published in2024 Second International Conference on Emerging Trends in Information Technology and Engineering (ICETITE) pp. 1 - 8
Main Authors Koli, Aakash, Mandrekar, Pushpam, Silveira, Fraser, Shetgaonkar, Pratiksha R., Kumar, K. M. Chaman
Format Conference Proceeding
LanguageEnglish
Published IEEE 22.02.2024
Subjects
Brain modeling
Brain Tumor
Classification
CNN
Deep learning
Federated learning
Medical Image Analysis
MRI
Shape
Support vector machines
Surgery
Surveys
Transfer Learning
Online AccessGet full text

Cover

More Information
Summary:Brain Tumors are extremely dangerous since they take many lives annually. Excrescence damages brain tissue or raises intracranial pressure, which has an impact on the brain. It is crucial to identify brain tumors accurately and promptly to treat this deadly illness. Prior discovery can save a life when done promptly and aid in the development of better specificity. In contrast to the laborious and fatally mistake-prone procedure of creating a homemade opinion of a tumor, machine literacy algorithms have recently been used to comprehend medical pictures and information. In spite of a number of significant threats as well as encouraging developments in this field, accurate segmentation and classification remain a challenging task. The fact that the tumors differ in size, shape, and location presents a significant obstacle to their detection. In this study, we reviewed numerous recent articles in the literature that discuss and implement various techniques for grain tumor diagnosis using automated computer-aided techniques. The objective of our project is to develop a self-supervised federated learning-based model for detecting brain tumors from MRI scans. In the proposed automated computer-aided framework, we aim to leverage a Federated Learning Environment using deep neural networks. This novel strategy aims to overcome the shortcomings of current techniques in order to improve the precision and efficacy of brain tumor diagnosis. Also, the existing challenges of the field are discussed.
DOI:10.1109/ic-ETITE58242.2024.10493537