Automatized self-supervised learning for skin lesion screening.
Melanoma
Screening
Self-supervised learning
Ugly duckling
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
03 Jun 2024
03 Jun 2024
Historique:
received:
01
08
2023
accepted:
08
05
2024
medline:
4
6
2024
pubmed:
4
6
2024
entrez:
3
6
2024
Statut:
epublish
Résumé
Melanoma, the deadliest form of skin cancer, has seen a steady increase in incidence rates worldwide, posing a significant challenge to dermatologists. Early detection is crucial for improving patient survival rates. However, performing total body screening (TBS), i.e., identifying suspicious lesions or ugly ducklings (UDs) by visual inspection, can be challenging and often requires sound expertise in pigmented lesions. To assist users of varying expertise levels, an artificial intelligence (AI) decision support tool was developed. Our solution identifies and characterizes UDs from real-world wide-field patient images. It employs a state-of-the-art object detection algorithm to locate and isolate all skin lesions present in a patient's total body images. These lesions are then sorted based on their level of suspiciousness using a self-supervised AI approach, tailored to the specific context of the patient under examination. A clinical validation study was conducted to evaluate the tool's performance. The results demonstrated an average sensitivity of 95% for the top-10 AI-identified UDs on skin lesions selected by the majority of experts in pigmented skin lesions. The study also found that the tool increased dermatologists' confidence when formulating a diagnosis, and the average majority agreement with the top-10 AI-identified UDs reached 100% when assisted by our tool. With the development of this AI-based decision support tool, we aim to address the shortage of specialists, enable faster consultation times for patients, and demonstrate the impact and usability of AI-assisted screening. Future developments will include expanding the dataset to include histologically confirmed melanoma and validating the tool for additional body regions.
Identifiants
pubmed: 38830890
doi: 10.1038/s41598-024-61681-4
pii: 10.1038/s41598-024-61681-4
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
12697Informations de copyright
© 2024. The Author(s).
Références
Arnold, M. et al. Global burden of cutaneous melanoma in 2020 and projections to 2040. JAMA Dermatol. 158, 495–503 (2022).
doi: 10.1001/jamadermatol.2022.0160
pubmed: 35353115
pmcid: 8968696
Badertscher, N., Rosemann, T., Tandjung, R. & Braun, R. P. minskin does a multifaceted intervention improve the competence in the diagnosis of skin cancer by general practitioners? Study protocol for a randomised controlled trial. Trials 12, 165. https://doi.org/10.1186/1745-6215-12-165 (2011).
doi: 10.1186/1745-6215-12-165
pubmed: 21718520
pmcid: 3161866
Badertscher, N. et al. A multifaceted intervention: No increase in general practitioners’ competence to diagnose skin cancer (minSKIN): Randomized controlled trial. J. Eur. Acad. Dermatol. Venereol. 29, 1493–1499 (2015).
doi: 10.1111/jdv.12886
pubmed: 25491768
The international skin imaging collaboration. https://www.isic-archive.com/ . Accessed 18 Oct 2022.
Esteva, A. et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115–118. https://doi.org/10.1038/nature21056 (2017).
doi: 10.1038/nature21056
pubmed: 28117445
pmcid: 8382232
Grob, J. J. The ugly duckling sign: Identification of the common characteristics of nevi in an individual as a basis for melanoma screening. Arch. Dermatol. 134, 103–104. https://doi.org/10.1001/archderm.134.1.103-a (1998).
doi: 10.1001/archderm.134.1.103-a
pubmed: 9449921
Soenksen, L. R. et al. Using deep learning for dermatologist-level detection of suspicious pigmented skin lesions from wide-field images. Sci. Transl. Med. 13, 3652. https://doi.org/10.1126/scitranslmed.abb3652 (2021).
doi: 10.1126/scitranslmed.abb3652
Mohseni, M., Yap, J., Yolland, W., Koochek, A. & Atkins, M. S. Can self-training identify suspicious ugly duckling lesions? 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 1829–1836. https://doi.org/10.1109/CVPRW53098.2021.00202 (2021).
Wang, C., Yeh, I. & Liao, H. M. You only learn one representation: Unified network for multiple tasks. CoRR abs/2105.04206 (2021).
Bradski, G. The OpenCV Library. Dr. Dobb’s Journal of Software Tools (2000).
Kang, J., Tariq, S., Oh, H. & Woo, S. S. A survey of deep learning-based object detection methods and datasets for overhead imagery. IEEE Access 10, 20118–20134. https://doi.org/10.1109/ACCESS.2022.3149052 (2022).
doi: 10.1109/ACCESS.2022.3149052
Strzelecki, M. H. et al. Skin lesion detection algorithms in whole body images. Sensors. https://doi.org/10.3390/s21196639 (2021).
doi: 10.3390/s21196639
pubmed: 34833558
pmcid: 8618739
Caron, M. et al. Emerging properties in self-supervised vision transformers. http://arxiv.org/abs/2104.14294v2 (2021).
Susmelj, I., Heller, M., Wirth, P., Prescott, J. & Lightly, M. E. GitHub.. https://github.com/lightly-ai/lightly (2020).