Scientific Data (Aug 2024)
The SLICE-3D dataset: 400,000 skin lesion image crops extracted from 3D TBP for skin cancer detection
- Nicholas R. Kurtansky,
- Brian M. D’Alessandro,
- Maura C. Gillis,
- Brigid Betz-Stablein,
- Sara E. Cerminara,
- Rafael Garcia,
- Marcela Alves Girundi,
- Elisabeth Victoria Goessinger,
- Philippe Gottfrois,
- Pascale Guitera,
- Allan C. Halpern,
- Valerie Jakrot,
- Harald Kittler,
- Kivanc Kose,
- Konstantinos Liopyris,
- Josep Malvehy,
- Victoria J. Mar,
- Linda K. Martin,
- Thomas Mathew,
- Lara Valeska Maul,
- Adam Mothershaw,
- Alina M. Mueller,
- Christoph Mueller,
- Alexander A. Navarini,
- Tarlia Rajeswaran,
- Vin Rajeswaran,
- Anup Saha,
- Maithili Sashindranath,
- Laura Serra-García,
- H. Peter Soyer,
- Georgios Theocharis,
- Ayesha Vos,
- Jochen Weber,
- Veronica Rotemberg
Affiliations
- Nicholas R. Kurtansky
- Dermatology Service, Department of Medicine, Memorial Sloan Kettering Cancer Center
- Brian M. D’Alessandro
- Canfield Scientific, Inc.
- Maura C. Gillis
- Dermatology Service, Department of Medicine, Memorial Sloan Kettering Cancer Center
- Brigid Betz-Stablein
- Frazer Institute, The University of Queensland, Dermatology Research Centre
- Sara E. Cerminara
- Department of Dermatology, University Hospital of Basel
- Rafael Garcia
- Computer Vision and Robotics Institute, University of Girona
- Marcela Alves Girundi
- Melanoma Institute Australia
- Elisabeth Victoria Goessinger
- Department of Dermatology, University Hospital of Basel
- Philippe Gottfrois
- Department of Dermatology, University Hospital of Basel
- Pascale Guitera
- Melanoma Institute Australia
- Allan C. Halpern
- Dermatology Service, Department of Medicine, Memorial Sloan Kettering Cancer Center
- Valerie Jakrot
- Melanoma Institute Australia
- Harald Kittler
- ViDIR Group, Department of Dermatology, Medical University of Vienna
- Kivanc Kose
- Dermatology Service, Department of Medicine, Memorial Sloan Kettering Cancer Center
- Konstantinos Liopyris
- University of Athens Medical School
- Josep Malvehy
- Dermatology Department, Hospital Clínic Barcelona, Universitat de Barcelona, IDIBAPS
- Victoria J. Mar
- School of Public Health and Preventive Medicine, Monash University
- Linda K. Martin
- Melanoma Institute Australia
- Thomas Mathew
- Melanoma Institute Australia
- Lara Valeska Maul
- Department of Dermatology, University Hospital of Zurich
- Adam Mothershaw
- Frazer Institute, The University of Queensland, Dermatology Research Centre
- Alina M. Mueller
- Department of Dermatology, University Hospital of Basel
- Christoph Mueller
- ViDIR Group, Department of Dermatology, Medical University of Vienna
- Alexander A. Navarini
- Department of Dermatology, University Hospital of Basel
- Tarlia Rajeswaran
- FNQH Cairns Skin Cancer Clinic
- Vin Rajeswaran
- FNQH Cairns Skin Cancer Clinic
- Anup Saha
- Computer Vision and Robotics Institute, University of Girona
- Maithili Sashindranath
- School of Public Health and Preventive Medicine, Monash University
- Laura Serra-García
- Dermatology Department, Hospital Clínic Barcelona
- H. Peter Soyer
- Frazer Institute, The University of Queensland, Dermatology Research Centre
- Georgios Theocharis
- University of Athens Medical School
- Ayesha Vos
- Victorian Melanoma Service, Alfred Hospital
- Jochen Weber
- Dermatology Service, Department of Medicine, Memorial Sloan Kettering Cancer Center
- Veronica Rotemberg
- Dermatology Service, Department of Medicine, Memorial Sloan Kettering Cancer Center
- DOI
- https://doi.org/10.1038/s41597-024-03743-w
- Journal volume & issue
-
Vol. 11,
no. 1
pp. 1 – 11
Abstract
Abstract AI image classification algorithms have shown promising results when applied to skin cancer detection. Most public skin cancer image datasets are comprised of dermoscopic photos and are limited by selection bias, lack of standardization, and lend themselves to development of algorithms that can only be used by skilled clinicians. The SLICE-3D (“Skin Lesion Image Crops Extracted from 3D TBP”) dataset described here addresses those concerns and contains images of over 400,000 distinct skin lesions from seven dermatologic centers from around the world. De-identified images were systematically extracted from sensitive 3D Total Body Photographs and are comparable in optical resolution to smartphone images. Algorithms trained on lower quality images could improve clinical workflows and detect skin cancers earlier if deployed in primary care or non-clinical settings, where photos are captured by non-expert physicians or patients. Such a tool could prompt individuals to visit a specialized dermatologist. This dataset circumvents many inherent limitations of prior datasets and may be used to build upon previous applications of skin imaging for cancer detection.
