A generalised vision transformer-based self-supervised model for diagnosing and grading prostate cancer using histological images
The self-supervised ViT-based model effectively diagnoses and grades prostate cancer using histological images, distinguishing benign and malignant tissues and classifying malignancies by aggressiveness. External validation highlights its robustness and clinical applicability in digital pathology.
Authors
- Alex William Hewitt (ORCID: https://orcid.org/0000-0002-5123-5999)
- Abadh K. Chaurasia (ORCID: https://orcid.org/0000-0003-4691-2921)
- H Harris (ORCID: https://orcid.org/0000-0002-0575-9513)
- Patrick W Toohey
Institutions
- University of Tasmania (AU)
- Royal Hobart Hospital (AU)
- Ta Solutions (China) (CN)
Publication Details
- Journal
- Prostate Cancer and Prostatic Diseases
- Published
- 2025-03-14
- DOI
- https://doi.org/10.1038/s41391-025-00957-w
- Citations
- 8
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 19.85
Funders
- Medical Research Council
- National Health and Medical Research Council