Optimal Res-UNET architecture with deep supervision for tumor segmentation
Optimized Res-UNET with deep supervision significantly enhances segmentation accuracy for brain tumors in MRI images, surpassing traditional U-Net models. This model addresses critical issues such as dataset imbalance, lack of annotated data, and computational inefficiencies. Future studies should consider the broader application of optimized U-Net variants across other medical imaging segmentation tasks.
Authors
- Shtwai Alsubai (ORCID: https://orcid.org/0000-0002-6584-7400)
- Fazeel Abid (ORCID: https://orcid.org/0000-0002-3925-6180)
- Onur Osman (ORCID: https://orcid.org/0000-0001-7675-7999)
- Jawad Rasheed (ORCID: https://orcid.org/0000-0003-3761-1641)
- Rahman Maqsood
Institutions
- İstanbul Sabahattin Zaim Üniversitesi (TR)
- Information Technology University (PK)
- University of Lahore (PK)
- Prince Sattam Bin Abdulaziz University (SA)
- Applied Science Private University (JO)
- İstanbul Nişantaşı Üniversitesi (TR)
- Istanbul University (TR)
- University of Management and Technology (PK)
Publication Details
- Journal
- Frontiers in Medicine
- Published
- 2025-05-30
- DOI
- https://doi.org/10.3389/fmed.2025.1593016
- Citations
- 4
- Primary Topic
- Brain Tumor Detection and Classification
- Type
- article
- Field-Weighted Citation Impact
- 3.37