Enhanced ResU-Net for brain tumor segmentation using EfficientNetB0, channel attention, and ASPP
Majid Behzadpour, Ebrahim Azizi, Bengie L Ortiz, Kai Wu · 2026
Read Enhanced ResU-Net for brain tumor segmentation using EfficientNetB0, channel attention, and ASPP by Majid Behzadpour, Ebrahim Azizi, Bengie L Ortiz, Kai Wu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13139756.txt.
Description
Majid Behzadpour and co-authors improve brain tumor segmentation in this 2026 paper. Exact tumor outlines guide diagnosis and treatment planning for brain cancer. Hand tracing is slow, so automated methods matter for clinic use.
Their model builds on ResU-Net with three additions. An EfficientNetB0 encoder draws on pretrained features for sharp extraction. A channel attention step focuses the model on tumor-linked traits. A pyramid pooling module reads context at many scales, which helps with varied tumor shapes. On two benchmark sets the model beat the plain ResU-Net and its variants. Scores for whole tumor regions were strong on the BraTS 2020 data.
Catalog record
| CREATOR | Majid Behzadpour, Ebrahim Azizi, Bengie L Ortiz, Kai Wu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 37 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |