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{194868,
        author = {Shaik Sameer and K Rama Krishna and P Ram Charan Reddy and S Swarnalatha},
        title = {AI-Driven Brain Tumor Diagnostics: YOLOv12 Optimization and Real-Time Detection from Annotated MRI Scans},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {6088-6094},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194868},
        abstract = {Early and accurate detection of brain tumors from MRI scans remains critical for timely intervention and improved patient survival. This paper presents Brain Tumor Detection Dashboard, a modern, real-time web application built with Streamlit that integrates a fine-tuned Ultralytics YOLOv12 model for automated tumor detection and classification. YOLOv12’s attention-centric architecture (featuring Area Attention, R-ELAN, and Flash Attention) enables superior accuracy and efficiency compared to previous YOLO versions. The system supports four classes glioma, meningioma, pituitary tumor, and no tumor with instant bounding-box visualization, confidence scoring, and rule-based clinical recommendations. The React-like Streamlit frontend combined with a lightweight Python backend delivers sub-100 ms inference on consumer hardware. Extensive evaluation on standard brain MRI datasets (Figshare, BR35H, and Roboflow) yields a mean Average Precision mAP@0.5 of 0.952, precision of 0.963, recall of 0.948, and average inference time of 78 ms on CPU. The dashboard demonstrates how the latest YOLOv12 model, when deployed in an intuitive web interface, can effectively bridge advanced AI research and practical clinical workflows.},
        keywords = {YOLOv12, Brain Tumor Detection, MRI Analysis, Streamlit, Attention-Centric Object Detection, Medical Imaging Dashboard, Ultralytics, Computer Vision, Deep Learning, AI in Healthcare.},
        month = {March},
        }