Masked Image Modeling Meets Self-Distillation: A Transformer-Based Prostate Gland Segmentation Framework for Pathology Slides
Haoyue Zhang, Sushant Patkar, Rosina Lis, Maria J Merino, Peter A Pinto, Peter L Choyke, Baris Turkbey, Stephanie Harmon, José I López · 2024
Read Masked Image Modeling Meets Self-Distillation: A Transformer-Based Prostate Gland Segmentation Framework for Pathology Slides by Haoyue Zhang, Sushant Patkar, Rosina Lis, Maria J Merino, Peter A Pinto, Peter L Choyke, Baris Turkbey, Stephanie Harmon, José I López (2024) 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-11640496.txt.
Description
Haoyue Zhang and co-authors present a 2024 framework for finding prostate glands in pathology slides. Marking glands by hand is slow work, yet gland shape helps grade the cancer and plan later tests. The team wanted a tool that could mark the glands on its own, without a person tracing each one.
Their design pairs a Swin Transformer UNet with masked image modeling, so the model learns from slides before it is taught the task. A second step, guided by tumor labels, tunes the model further. Tests used biopsy and surgery samples from two public data sets. The scores were strong on one set and lower on the other, which the authors report in full.
Catalog record
| CREATOR | Haoyue Zhang, Sushant Patkar, Rosina Lis, Maria J Merino, Peter A Pinto, Peter L Choyke, Baris Turkbey, Stephanie Harmon, José I López |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 29 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |