An Efficient Scientific Programming Technique for MRI Classification using Deep Residual Networks

• Published in: Journal of Electrical Systems Vol. 20; no. 2s; pp. 241 - 255
• Main Authors: Sawhney, Rahul, Sharma, Shilpi, Narayan, Vipul, Srivastava, Swapnita
• Format: Journal Article
• Language: English
• Published: Paris Engineering and Scientific Research Groups 04.04.2024
• Subjects: Brain; Brain cancer; Classification; Deep learning; Image contrast; Image quality; Image segmentation; Imaging techniques; Ionizing radiation; Machine learning; Magnetic resonance imaging; Medical imaging; Tumors
• ISSN: 1112-5209
• DOI: 10.52783/jes.1135

Classifying brain tumors is crucial for both diagnosing and treating patients with these diseases. Imaging techniques of many kinds are used to detect brain cancers. In contrast, MRI is frequently used because to its superior picture quality and the fact that it does not require ionizing radiation. Recently, the subfield of machine learning known as deep learning has shown especially promising results in the areas of classification and segmentation. To identify the various tumor types seen in the brain, we trained a deep residual network using imaging datasets. There will be a tremendous amount of information generated from the MRI images. It is the radiologist's job to look at these imagesMeningiomas, pituitary tumours, and gliomas are the three most prevalent forms of brain tumours. Because of the complexity of brain tumors, a physical inspection might lead to mistakes. Classification methods that use machine learning to automate the process have shown to be superior to human curation every time. Therefore, we developed a CNN-based deep residual network-based detection and classification system.