Weakly supervised deep learning image analysis can differentiate melanoma from naevi on haematoxylin and eosin‐stained histopathology slides
Weakly supervised DL on pathological slides of common mucocutaneous melanocytic tumours provides highly accurate diagnostic value for discrimination of melanomas and naevi. External validation and further assessment on less frequently occurring histologic subtypes and borderline cases using this method is required.
Authors
- Sidong Liu (ORCID: https://orcid.org/0000-0002-2371-0713)
- Cong Cong (ORCID: https://orcid.org/0000-0001-9990-9529)
- Ismael A. Vergara (ORCID: https://orcid.org/0000-0002-2960-2967)
- Nurudeen A. Adegoke (ORCID: https://orcid.org/0000-0001-7592-5460)
- Nigel G. Maher (ORCID: https://orcid.org/0000-0002-8140-2719)
- Homay Danaei Mehr (ORCID: https://orcid.org/0000-0003-1027-4550)
- Richard A. Scolyer (ORCID: https://orcid.org/0000-0002-8991-0013)
Institutions
- The University of Sydney (AU)
- Royal Prince Alfred Hospital (AU)
- Melanoma Institute Australia (AU)
- Macquarie University (AU)
Publication Details
- Journal
- Journal of the European Academy of Dermatology and Venereology
- Published
- 2024-08-31
- DOI
- https://doi.org/10.1111/jdv.20307
- Citations
- 8
- Primary Topic
- Cutaneous Melanoma Detection and Management
- Type
- article
- Field-Weighted Citation Impact
- 2.26
Funders
- Royal College of Pathologists of Australasia
- University of Sydney
- Melanoma Institute Australia
- National Health and Medical Research Council