An AI Driven Framework for Automated Detection and Classification of Brain Hemorrhage

Sruthi S. Nair, Gayathri C M, Dr. Neethu M

Abstract: Brain hemorrhage is a critical neurological emergency that demands rapid and accurate diagnosis to reduce mortality and long-term disability. Recent advancements in artificial intelligence (AI), particularly deep learning, have significantly enhanced automated medical image analysis. This paper synthesizes insights from multiple studies on AI-based brain hemorrhage detection using computed tomography (CT) imaging and proposes a comprehensive framework integrating advanced architectures- CNN, ResNet, MobileNet, and YOLO- for detection, localization, and classification. The framework combines segmentation and classification workflows while addressing interpretability, data scarcity, and clinical deployment through transfer learning, explainable AI, and federated learning. Reported benchmarks indicate accuracy up to 99%, Dice coefficient of 0.99, and Jaccard Index of 0.88. Future directions include 3D CNNs, hybrid CNN-RNN models, multimodal fusion, and real-time deployment for emergency care.

Keywords: Automated diagnosis, Neuroimaging AI, Convolutional networks, Predictive modeling, Clinical decision support

How to Cite?: Sruthi S. Nair, Gayathri C M, Dr. Neethu M, "An AI Driven Framework for Automated Detection and Classification of Brain Hemorrhage", Volume 15 Issue 2, February 2026, International Journal of Science and Research (IJSR), Pages: 1083-1086, https://www.ijsr.net/getabstract.php?paperid=SR26117182025, DOI: https://dx.dx.doi.org/10.21275/SR26117182025

Download Citation: APA | MLA | BibTeX | EndNote | RefMan