Work

Democratizing Neuro-Oncology: Real-Time Multi-Class Brain Tumor Localization in MRI Using YOLOv11 for Early Intervention

Year: 2026

Type: preprint

Abstract: 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 ([email protected]) 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.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.22230739

Author: Sorna, İzzet Can

Language: English

Topic: Brain Tumor Detection and Classification

Subfield: Neurology

Field: Neuroscience

Domain: Life Sciences

SDG: Good health and well-being

Open Access status: green

OpenAlex ID: W7204904361

Cites:

Cited by:

Related to: