Automatic body part identification in real-world clinical dermatological images using machine learning.
General dermatology
artificial intelligence
image classification
machine learning
medical dermatology
Journal
Journal der Deutschen Dermatologischen Gesellschaft = Journal of the German Society of Dermatology : JDDG
ISSN: 1610-0387
Titre abrégé: J Dtsch Dermatol Ges
Pays: Germany
ID NLM: 101164708
Informations de publication
Date de publication:
08 2023
08 2023
Historique:
received:
07
11
2022
accepted:
30
03
2023
medline:
15
8
2023
pubmed:
12
6
2023
entrez:
12
6
2023
Statut:
ppublish
Résumé
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. 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. 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. 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.
Sections du résumé
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.
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
863-869Informations de copyright
© 2023 The Authors. Journal der Deutschen Dermatologischen Gesellschaft published by John Wiley & Sons Ltd on behalf of Deutsche Dermatologische Gesellschaft.
Références
Hay RJ, Johns NE, Williams HC, et al. The Global Burden of Skin Disease in 2010: An Analysis of the Prevalence and Impact of Skin Conditions. J Invest Dermatol. 2014;134(6):1527-1534 .
Schielein MC, Tizek L, Ziehfreund S, et al. Stigmatization caused by hair loss - a systematic literature review. J Dtsch Dermatol Ges. 2020;18(12):1357-1368.
Tizek L, Schielein M C, Seifert F, et al. Skin diseases are more common than we think: screening results of an unreferred population at the Munich Oktoberfest. J Eur Acad Dermatol Venereol. 2019;33(7):1421-1428.
Efimenko M, Ignatev A, Koshechkin K. Review of medical image recognition technologies to detect melanomas using neural networks. BMC Bioinformatics. 2020;21(Suppl 11):270.
Ashton R, Leppard B. Differential Diagnosis in Dermatology. CRC Press, 2020.
Gross G E, Eisert L, Doerr HW, et al. S2k-Leitlinie zur Diagnostik und Therapie des Zoster und der Postzosterneuralgie. GMS Infect Dis. 2020;8:Doc01
Giannotti B. Current Treatment Guidelines for Topical Corticosteroids: Drugs. 1988;36(Supplement 5):9-14.
Mori M, Pimpinelli N, Giannotti B. Topical Corticosteroids and Unwanted Local Effects: Improving the Benefit/Risk Ratio. Drug Saf. 1994;10(5):406-412.
Smolle J. [Predilection sites of the skin]. J Dtsch Dermatol Ges. 2003;1(8):646-651;quiz 652,654
Hjuler K F, Iversen L, Rasmussen MK, et al. Localization of treatment-resistant areas in patients with psoriasis on biologics. Br J Dermatol. 2019;181(2):332-337.
Liu Y, Jain A, Eng C, et al. A deep learning system for differential diagnosis of skin diseases. Nat Med. 2020;26(6):900-908.
Dicken V, Lindow B, Bornemann L, et al. Rapid image recognition of body parts scanned in computed tomography datasets. Int J Comput Assist Radiol Surg. 2010;5:527-535.
Andrási E, Varga I, Dózsa A, et al. Classification of human brain parts using pattern recognition based on inductively coupled plasma atomic emission spectroscopy and instrumental neutron activation analysis. Chemom Intell Lab Syst. 1994;22(1):107-114.
Zhou X. Automatic Segmentation of Multiple Organs on 3D CT Images by Using Deep Learning Approaches. Adv Exp Med Biol. 2020;1213:135-147.
Shebiah R N, Sangari AA. Classification of human body parts using histogram of oriented gradients. in 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS). 2019:958-961.
Argenziano G, Soyer HP, Chimenti S, et al. Dermoscopy of pigmented skin lesions: results of a consensus meeting via the Internet. J Am Acad Dermatol. 2003;48(5):679-693.
Goutsu Y, Takano W, Nakamura Y. Classification of Multi-class Daily Human Motion using Discriminative Body Parts and Sentence Descriptions. Int J Comput Vis. 2018;126(5):495-514.
Chollet F. Xception: Deep Learning with Depthwise Separable Convolutions. ArXiv161002357 Cs 2017.
Kingma DP, Ba J. Adam: A Method for Stochastic Optimization. ArXiv14126980 Cs 2017.
Oliveira GL, Valada A, Bollen C, et al. Deep learning for human part discovery in images. IEEE International Conference on Robotics and Automation (ICRA), Stockholm, Sweden, 2016;1634-1641.
Schaap MJ, Cardozo NJ, Patel A, et al. Image-based automated Psoriasis Area Severity Index scoring by Convolutional Neural Networks. J Eur Acad Dermatol Venereol. 2022;36(1):68-75.
Dai Z, Liu H, Le QV, Tan M. CoAtNet: Marrying Convolution and Attention for All Data Sizes. ArXiv210604803 Cs 2021.
Griffiths CE, Barker JN. Pathogenesis and clinical features of psoriasis. Lancet. 2007;370(9583):263-271.
Mrowietz U, Prinz JC. Psoriasis. In: Plewig G, Ruzicka T, Kaufmann R, Hertl M. (eds) Braun-Falco's Dermatologie, Venerologie und Allergologie. Springer Reference Medizin. Berlin, Heidelberg: Springer. 2018:677-702.
Homey B, Ruzicka T, Wollenberg A. Atopisches Ekzem. In: Plewig G, Ruzicka T, Kaufmann R, Hertl M. (eds) Braun-Falco's Dermatologie, Venerologie und Allergologie. Berlin, Heidelberg: Springer Reference Medizin, Springer. 2018:549-568.
Buda M, Maki A, Mazurowski MA. A systematic study of the class imbalance problem in convolutional neural networks. Neural Netw. 2018;106:249-259
Guo C, Pleiss G, Sun Y, Weinberger KQ. On Calibration of Modern Neural Networks. ArXiv170604599 Cs 2017.
Schielein MC, Tizek L, Schuster B, et al. Genital psoriasis and associated factors of sexual avoidance - a people-centered cross-sectional study in Germany. Acta Derm Venereol. 2020;100(10):adv00151.
Ryan C. Genital psoriasis: the failure of dermatologists to identify genital involvement. Br J Dermatol. 2019;180(3):460-461.
Rutjes C, Torrano J, Soyer HP. A 3D total-body photography research network: the Australian experiment. Hautarzt. 2022;73:236-240.
Warnat-Herresthal S, Schultze H, Shastry K L, et al. Swarm Learning for decentralized and confidential clinical machine learning. Nature. 2021;594(7862):265-270.