Reproducible naevus counts using 3D total body photography and convolutional neural networks
Authors
Betz-Stablein, B.D'Alessandro, B.
Koh, U.
Plasmeijer, E.
Janda, M.
Menzies, S. W.
Hofmann-Wellenhof, R.
Green, Adèle C
Soyer, H. P.
Affiliation
QIMR Berghofer Medical Research Institute, Cancer and Population Studies, Brisbane, Queensland, Australia.Issue Date
2021
Metadata
Show full item recordAbstract
Background: The number of naevi on a person is the strongest risk factor for melanoma; however, naevus counting is highly variable due to lack of consistent methodology and lack of inter-rater agreement. Machine learning has been shown to be a valuable tool for image classification in dermatology. Objectives: To test whether automated, reproducible naevus counts are possible through the combination of convolutional neural networks (CNN) and three-dimensional (3D) total body imaging. Methods: Total body images from a study of naevi in the general population were used for the training (82 subjects, 57,742 lesions) and testing (10 subjects; 4,868 lesions) datasets for the development of a CNN. Lesions were labelled as naevi, or not ("non-naevi"), by a senior dermatologist as the gold standard. Performance of the CNN was assessed using sensitivity, specificity, and Cohen's kappa, and evaluated at the lesion level and person level. Results: Lesion-level analysis comparing the automated counts to the gold standard showed a sensitivity and specificity of 79% (76-83%) and 91% (90-92%), respectively, for lesions ≥2 mm, and 84% (75-91%) and 91% (88-94%) for lesions ≥5 mm. Cohen's kappa was 0.56 (0.53-0.59) indicating moderate agreement for naevi ≥2 mm, and substantial agreement (0.72, 0.63-0.80) for naevi ≥5 mm. For the 10 individuals in the test set, person-level agreement was assessed as categories with 70% agreement between the automated and gold standard counts. Agreement was lower in subjects with numerous seborrhoeic keratoses. Conclusion: Automated naevus counts with reasonable agreement to those of an expert clinician are possible through the combination of 3D total body photography and CNNs. Such an algorithm may provide a faster, reproducible method over the traditional in person total body naevus counts.Citation
Betz-Stablein B, D’Alessandro B, Koh U, Plasmeijer E, Janda M, Menzies SW, et al. Reproducible Naevus Counts Using 3D Total Body Photography and Convolutional Neural Networks. Dermatology. 2021 Jul 8;1–8.Journal
DermatologyDOI
10.1159/000517218PubMed ID
34237739Additional Links
https://dx.doi.org/10.1159/000517218Type
ArticleLanguage
enae974a485f413a2113503eed53cd6c53
10.1159/000517218
Scopus Count
Collections
Related articles
- 'Mind your Moles' study: protocol of a prospective cohort study of melanocytic naevi.
- Authors: Koh U, Janda M, Aitken JF, Duffy DL, Menzies S, Sturm RA, Schaider H, Betz-Stablein B, Prow T, Soyer HP, Green AC
- Issue date: 2018 Sep 19
- Indicators for the total number of melanocytic naevi: an adjunct for screening campaigns. Observational study on 292 patients.
- Authors: Echeverría B, Bulliard JL, Guillén C, Nagore E
- Issue date: 2014 Jan
- Accuracy and reliability of naevus self-counts.
- Authors: Fiessler C, Pfahlberg A, Li J, Uter W, Gefeller O
- Issue date: 2014 Dec
- The naevus count on the arms as a predictor of the number of melanocytic naevi on the whole body.
- Authors: Fariñas-Alvarez C, Ródenas JM, Herranz MT, Delgado-Rodríguez M
- Issue date: 1999 Mar
- High naevus count and MC1R red hair alleles contribute synergistically to increased melanoma risk.
- Authors: Duffy DL, Lee KJ, Jagirdar K, Pflugfelder A, Stark MS, McMeniman EK, Soyer HP, Sturm RA
- Issue date: 2019 Nov