Automated triage of cancer-suspicious skin lesions with 3D total-body photography
Careful selection of skin lesions that require expert evaluation is important for early skin cancer detection. Yet challenges include lack of cost-effective asymptomatic screening, geographical inequality in access to specialty dermatology, and long wait times due to exam inefficiencies and staff shortages. Machine learning models trained on high-quality dermoscopy photos have been shown to aid clinicians in diagnosing individual, hand-selected skin lesions. In contrast, models designed for triage have been less explored due to limited datasets that represent a broader net of skin lesions. 3D total body photography is an emerging technology used in dermatology to document all apparent skin lesions on a patient for skin cancer monitoring. A multi-institutional and global project collected over 900,000 lesion crops off 3D total body photos for an online grand challenge in machine learning. Here we summarize the results of the competition, 'ISIC 2024 - Skin Cancer Detection with 3D-TBP', demonstrate superiority of a model that utilized intra-patient context against a prior published approach, and explore clinical plausibility of automated atypical skin lesion triage through an ablation study.
Authors
- Harald Kittler (ORCID: https://orcid.org/0000-0002-0051-8016)
- Vin Rajeswaran
- Allan C. Halpern (ORCID: https://orcid.org/0000-0001-7320-1901)
- Zongyuan Ge (ORCID: https://orcid.org/0000-0002-5880-8673)
- Lara Valeska Maul (ORCID: https://orcid.org/0000-0001-9202-0073)
- Konstantinos Liopyris (ORCID: https://orcid.org/0000-0001-9566-8238)
- Victoria Mar (ORCID: https://orcid.org/0000-0002-7533-1678)
- Siyuan Yan (ORCID: https://orcid.org/0000-0002-6372-8336)
- B D'Alessandro (ORCID: https://orcid.org/0000-0002-0050-401X)
- Nicholas R. Kurtansky (ORCID: https://orcid.org/0000-0002-6745-0386)
- H. Peter Soyer (ORCID: https://orcid.org/0000-0002-4770-561X)
- Linda K. Martin (ORCID: https://orcid.org/0000-0001-9519-7077)
- Alexander A. Navarini (ORCID: https://orcid.org/0000-0001-7059-632X)
- Josep Malvehy (ORCID: https://orcid.org/0000-0002-6998-914X)
- Pascale Guitera (ORCID: https://orcid.org/0000-0001-9519-110X)
- Noel Codella (ORCID: https://orcid.org/0000-0001-6735-9067)
- Kıvanç Köse (ORCID: https://orcid.org/0000-0003-3185-2639)
- Veronica Rotemberg (ORCID: https://orcid.org/0000-0003-0639-2677)
- Jochen Weber (ORCID: https://orcid.org/0000-0002-2397-4954)
- Tarlia Rajeswaran
- Maura C. Gillis
- Nadia Reichman
Institutions
- Microsoft (United States) (US)
- The University of Sydney (AU)
- New South Wales Department of Health (AU)
- Memorial Sloan Kettering Cancer Center (US)
- The University of Queensland (AU)
- National and Kapodistrian University of Athens (GR)
- University of Zurich (CH)
- Royal Prince Alfred Hospital (AU)
- Cairns Hospital (AU)
- University Hospital of Basel (CH)
- UNSW Sydney (AU)
- University Hospital of Zurich (CH)
- Hospital Clínic de Barcelona (ES)
- Melanoma Institute Australia (AU)
- Monash Health (AU)
- Canfield Scientific (United States) (US)
- Instituto de Investigación de Enfermedades Raras (ES)
- Alfred Health (AU)
- Monash University (AU)
- Medical University of Vienna (AT)
Publication Details
- Journal
- npj Digital Medicine
- Published
- 2025-11-21
- DOI
- https://doi.org/10.1038/s41746-025-02070-7
- Primary Topic
- Cutaneous Melanoma Detection and Management
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- U.S. Department of Defense
- National Institutes of Health
- National Cancer Institute