Multiscale Fourier transform multiple instance learning for the Gleason grading of prostate cancer from whole-slide images
The proposed MFMIL model demonstrates high diagnostic accuracy and strong clinical applicability for Gleason grading in both radical prostatectomy and prostate biopsy WSIs, offering a promising tool for enhancing prostate cancer diagnosis in routine pathology workflows.
Authors
- Zhiwei Xie (ORCID: https://orcid.org/0000-0003-0505-5724)
- Xudong Jia (ORCID: https://orcid.org/0000-0001-7911-8869)
- Huiming Tian (ORCID: https://orcid.org/0000-0002-6637-6540)
- Yu Xiao (ORCID: https://orcid.org/0000-0002-0911-6857)
- Junying Zeng (ORCID: https://orcid.org/0000-0002-7559-0637)
- Weigang Yan (ORCID: https://orcid.org/0000-0002-8995-1456)
- Chen Qin (ORCID: https://orcid.org/0009-0000-6558-6477)
- Zhien Zhou
- Yi Zhou (ORCID: https://orcid.org/0000-0003-2610-1523)
- Zhipeng Mai
Institutions
- Chinese Academy of Medical Sciences & Peking Union Medical College (CN)
- Peking Union Medical College Hospital (CN)
- Peking University Shenzhen Hospital (CN)
Publication Details
- Journal
- Quantitative Imaging in Medicine and Surgery
- Published
- 2025-09-24
- DOI
- https://doi.org/10.21037/qims-2025-439
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00