Validation study demonstrates rapid multi-class brain tumor localization in MRI scans, highlighting the potential of lightweight deep learning models for clinical diagnostic support.
Early and precise detection of brain tumors from Magnetic Resonance Imaging (MRI) is vital for improving patient survival rates and guiding clinical interventions. This study proposes an ultra-fast, highly accurate multi-class brain tumor localization framework based on the state-of-the-art YOLOv11 architecture. Evaluated on a comprehensive dataset of 5,805 MRI scans across four distinct categories (glioma, meningioma, pituitary tumor, and no tumor), the proposed model achieves a mean Average Precision (mAP@0.5) of 97.04% and a real-time inference speed of 110 Frames Per Second (FPS). The findings demonstrate the viability of deploying lightweight deep learning models in neuro-oncology for rapid, accessible diagnostic support in clinical workflows.
No takes yet. Share an insight, caveat, or question.
İzzet Can Sorna (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: