ESA-YOLOv5m: a lightweight spatial and improved attention-driven detection for brain tumor MRI analysis
Overall, the results validate that integrating a lightweight spatial attention mechanism significantly enhances tumor localization and model generalization while preserving real-time inference. The proposed ESA-YOLOv5m framework provides a reliable and scalable solution for automated brain tumor detection, suitable for clinical decision-support systems and edge healthcare applications.
Authors
- Noshina Tariq (ORCID: https://orcid.org/0000-0002-9754-253X)
- Maram Fahaad Almufareh
- Mamoona Humayun (ORCID: https://orcid.org/0000-0001-6339-2257)
- Meshal Alharbi (ORCID: https://orcid.org/0000-0002-6025-7858)
- Haya Aldossary (ORCID: https://orcid.org/0009-0003-4076-1541)
Institutions
- Prince Sattam Bin Abdulaziz University (SA)
- Jouf University (SA)
- National University of Computer and Emerging Sciences (PK)
- Imam Abdulrahman Al Faisal Hospital (SA)
- Imam Abdulrahman Bin Faisal University (SA)
- University of Roehampton (GB)
Publication Details
- Journal
- Frontiers in Medicine
- Published
- 2025-12-19
- DOI
- https://doi.org/10.3389/fmed.2025.1733180
- Primary Topic
- Brain Tumor Detection and Classification
- Type
- article
- Field-Weighted Citation Impact
- 0.00