Copyright © 2026 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{188110,
        author = {Tanuja Ramesh Bandichode},
        title = {Exploring Deep Learning and Machine Learning Approaches for Brain Hemorrhage},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {1091-1098},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188110},
        abstract = {Spotting brain bleeding fast helps save lives in emergencies. Reading CT scans by hand takes too long, plus results can differ between doctors. Here’s a side-by-side look at three smart systems - MobileNet, ResNet50, and VGG16 - that aim to do it automatically brain bleed spotting. We gathered a set of CT scans with and without bleeding, then cleaned them up using scale adjustment, extra sample creation, also slice focusing tricks. These systems got updated through prior learning tweaks, plus checked by how often they guessed right, nailed the positives, caught actual cases, specificity, F1- score, yet ROC–AUC. ResNet50 hit top accuracy - 100% - while MobileNet came close at 99.3%, then VGG16 trailed at 97%. Despite lower peak performance, MobileNet offered the sharpest trade-off: solid precision without heavy computing needs, so it fits better in clinics with tight tech limits. Results suggest leaner models or those with skip connections can speed up dependable diagnosis tools. This study adds to that direction building smart helpers for brain emergencies using artificial thinking tech.},
        keywords = {Brain hemrrohage detection, CNN model, deep laerning, Machine learning, MobileNet, ResNet, CT scan, medical image, improve medical care.},
        month = {December},
        }