Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{177421,
        author = {Jay Shankar Wanjale and Rutuja Deshmukh and Aakanksha Upadhya and Aditya Pisal and Jayashree Surpur},
        title = {AI-Driven Brain MRI diagnosis using Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {2250-2254},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=177421},
        abstract = {Early detection of brain diseases such as tumors and Alzheimer’s is crucial for effective treatment. However, traditional MRI analysis is often time-consuming, heavily reliant on radiologists, and susceptible to human error. This project is an innovative solution that harnesses Artificial Intelligence and Deep Learning to automate brain MRI image enhancement and disease classification, addressing the limitations of traditional, manual MRI analysis which is often time-consuming and error-prone. A key challenge in neuroimaging is the accurate extraction of Brain MRI images, especially from low-quality scans with artifacts and grey-level inconsistencies that hinder precise diagnosis. Our software employs a Cycle-GAN architecture, where a generator enhances low-quality MRI images and a discriminator refines the output by distinguishing between real and generated images, ensuring improved feature learning. The enhanced image is then fed into a pre-trained Convolutional Neural Network (CNN) that identifies diseases based on image patterns and features. Following classification, the system's user interface generates a downloadable report in .txt format, detailing the diagnosed condition, its symptoms, causes, treatments, precautions, and expert guidance. This comprehensive approach empowers neurologists to accelerate diagnosis and initiate timely, more accurate treatment plans.},
        keywords = {:-  Magnetic resonance imaging, Brain image extraction, Artifacts, Grey inconsistencies, Generative adversarial networks, medical imaging, image synthesis, image enhancement, image augmentation, image segmentation, Convolutional Neural Network, CNN Classifier, Report generation.},
        month = {May},
        }