Automatic body part identification in real-world clinical dermatological images using machine learning.

Autor: Sitaru S; Technical University of Munich, School of Medicine, Department of Dermatology and Allergy, Munich, Germany., Oueslati T; Technical University of Munich, School of Medicine, Department of Dermatology and Allergy, Munich, Germany., Schielein MC; Technical University of Munich, School of Medicine, Department of Dermatology and Allergy, Munich, Germany., Weis J; Technical University of Munich, School of Medicine, Department of Dermatology and Allergy, Munich, Germany., Kaczmarczyk R; Technical University of Munich, School of Medicine, Department of Dermatology and Allergy, Munich, Germany., Rueckert D; Technical University of Munich, School of Medicine, Institute of AI and Informatics in Medicine, Munich, Germany.; Biomedical Image Analysis Group, Department of Computing, Imperial College London, London, UK., Biedermann T; Technical University of Munich, School of Medicine, Department of Dermatology and Allergy, Munich, Germany., Zink A; Technical University of Munich, School of Medicine, Department of Dermatology and Allergy, Munich, Germany.; Division of Dermatology and Venereology, Department of Medicine Solna, Karolinska Institutet, Stockholm, Sweden.
Jazyk: angličtina
Zdroj: Journal der Deutschen Dermatologischen Gesellschaft = Journal of the German Society of Dermatology : JDDG [J Dtsch Dermatol Ges] 2023 Aug; Vol. 21 (8), pp. 863-869. Date of Electronic Publication: 2023 Jun 12.
DOI: 10.1111/ddg.15113
Abstrakt: Background: Dermatological conditions are prevalent across all population sub-groups. The affected body part is of importance to their diagnosis, therapy, and research. The automatic identification of body parts in dermatological clinical pictures could therefore improve clinical care by providing additional information for clinical decision-making algorithms, discovering hard-to-treat areas, and research by identifying new patterns of disease.
Patients and Methods: In this study, we used 6,219 labelled dermatological images from our clinical database, which were used to train and validate a convolutional neural network. As a use case, qualitative heatmaps for the body part distribution in common dermatological conditions was generated using this system.
Results: The algorithm reached a mean balanced accuracy of 89% (range 74.8%-96.5%). Non-melanoma skin cancer photos were mostly of the face and torso, while hotspots of eczema and psoriasis image distribution included the torso, legs, and hands.
Conclusions: The accuracy of this system is comparable to the best to-date published algorithms for image classification challenges, suggesting this algorithm could boost diagnosis, therapy, and research of dermatological conditions.
(© 2023 The Authors. Journal der Deutschen Dermatologischen Gesellschaft published by John Wiley & Sons Ltd on behalf of Deutsche Dermatologische Gesellschaft.)
Databáze: MEDLINE
Externí odkaz: