Efficient diagnosis of psoriasis and lichen planus cutaneous diseases using deep learning approach.
Deep learning in dermatology
Diagnosis
Lichen planus
Psoriasis
ResNet-50 model
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
27 Apr 2024
27 Apr 2024
Historique:
received:
01
11
2023
accepted:
24
04
2024
medline:
28
4
2024
pubmed:
28
4
2024
entrez:
27
4
2024
Statut:
epublish
Résumé
The tendency of skin diseases to manifest in a unique and yet similar appearance, absence of enough competent dermatologists, and urgency of diagnosis and classification on time and accurately, makes the need of machine aided diagnosis blatant. This study is conducted with the purpose of broadening the research in skin disease diagnosis with computer by traversing the capabilities of deep Learning algorithms to classify two skin diseases noticeably close in appearance, Psoriasis and Lichen Planus. The resemblance between these two skin diseases is striking, often resulting in their classification within the same category. Despite this, there is a dearth of research focusing specifically on these diseases. A customized 50 layers ResNet-50 architecture of convolutional neural network is used and the results are validated through fivefold cross-validation, threefold cross-validation, and random split. By utilizing advanced data augmentation and class balancing techniques, the diversity of the dataset has increased, and the dataset imbalance has been minimized. ResNet-50 has achieved an accuracy of 89.07%, sensitivity of 86.46%, and specificity of 86.02%. With their promising results, these algorithms make the potential of machine aided diagnosis clear. Deep Learning algorithms could provide assistance to physicians and dermatologists by classification of skin diseases, with similar appearance, in real-time.
Identifiants
pubmed: 38678100
doi: 10.1038/s41598-024-60526-4
pii: 10.1038/s41598-024-60526-4
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
9715Informations de copyright
© 2024. The Author(s).
Références
Zhu, C. Y. et al. A deep learning based framework for diagnosing multiple skin diseases in a clinical environment. Front. Med. 8, 25 (2021).
Kermany, D. S. et al. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172(5), 1122–1131 (2018).
doi: 10.1016/j.cell.2018.02.010
pubmed: 29474911
Litjens, G. et al. A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017).
doi: 10.1016/j.media.2017.07.005
pubmed: 28778026
Onsoi, W., Chaiyarit, J. & Techasatian, L. Common misdiagnoses and prevalence of dermatological disorders at a pediatric tertiary care center. J. Int. Med. Res. 48(2), 0300060519873490 (2020).
doi: 10.1177/0300060519873490
pubmed: 31537142
Nwako-Mohamadi, M. K. et al. Dermoscopic features of psoriasis, lichen planus, and pityriasis rosea in patients with skin type IV and darker attending the Regional Dermatology Training Centre in Northern Tanzania. Dermatol. Pract. Concept. 9(1), 44 (2019).
doi: 10.5826/dpc.0901a11
pubmed: 30775148
pmcid: 6368079
Armstrong, A. W. et al. Psoriasis prevalence in adults in the United States. JAMA Dermatol. 157(8), 940–946 (2021).
doi: 10.1001/jamadermatol.2021.2007
pubmed: 34190957
Uppala, R. et al. “Autoinflammatory psoriasis”—genetics and biology of pustular psoriasis. Cell. Mol. Immunol. 18(2), 307–317 (2021).
doi: 10.1038/s41423-020-0519-3
pubmed: 32814870
Le Cleach, L. & Chosidow, O. Lichen planus. N. Engl. J. Med. 366(8), 723–732 (2012).
doi: 10.1056/NEJMcp1103641
pubmed: 22356325
Katta, R. Lichen planus. Am. Fam. Physician 61(11), 3319–3324 (2000).
pubmed: 10865927
Raychaudhuri, S. K., Maverakis, E. & Raychaudhuri, S. P. Diagnosis and classification of psoriasis. Autoimmun. Rev. 13(4–5), 490–495 (2014).
doi: 10.1016/j.autrev.2014.01.008
pubmed: 24434359
Usatine, R. & Tinitigan, M. Diagnosis and treatment of lichen planus. Am. Fam. Physician 84(1), 53–60 (2011).
pubmed: 21766756
Van der Meij, E. H. & Van der Waal, I. Lack of clinicopathologic correlation in the diagnosis of oral lichen planus based on the presently available diagnostic criteria and suggestions for modifications. J. Oral Pathol. Med. 32(9), 507–512 (2003).
doi: 10.1034/j.1600-0714.2003.00125.x
pubmed: 12969224
Health Jade Team. (2018, April 5). Lichen planus. Health Jade. https://healthjade.net/lichen-planus/ .
Capella, G. L. & Finzi, A. F. Psoriasis, lichen planus, and disorders of keratinization: unapproved treatments or indications. Clin. Dermatol. 18(2), 159–169 (2000).
doi: 10.1016/S0738-081X(99)00106-6
pubmed: 10742624
Vázquez-López, F. et al. Dermoscopic features of plaque psoriasis and lichen planus: New observations. Dermatology 207(2), 151–156 (2003).
doi: 10.1159/000071785
pubmed: 12920364
Lallas, A. et al. Accuracy of dermoscopic criteria for the diagnosis of psoriasis, dermatitis, lichen planus and pityriasis rosea. Br. J. Dermatol. 166(6), 1198–1205 (2012).
doi: 10.1111/j.1365-2133.2012.10868.x
pubmed: 22296226
Awake, P., Dewang, S., Chandravathi, P. L. & Ali, M. M. Clinical, pathological and dermoscopic correlation of non-infectious papulosquamous disorders (psoriasis, eczema, lichen planus and pityriasis rosea) of skin-A cross-sectional study. J. Pak. Assoc. Dermatol. 30(4), 563–573 (2020).
Yang, Y. et al. A convolutional neural network trained with dermoscopic images of psoriasis performed on par with 230 dermatologists. Comput. Biol. Med. 139, 104924 (2021).
doi: 10.1016/j.compbiomed.2021.104924
pubmed: 34688173
Zhao, S. et al. Smart identification of psoriasis by images using convolutional neural networks: a case study in China. J. Eur. Acad. Dermatol. Venereol. 34(3), 518–524 (2020).
doi: 10.1111/jdv.15965
pubmed: 31541556
Bajwa, M. N. et al. Computer-aided diagnosis of skin diseases using deep neural networks. Appl. Sci. 10(7), 2488 (2020).
doi: 10.3390/app10072488
Gunwant, H., Joshi, A., Sharma, M., & Gupta, D. Automated medical diagnosis and classification of skin diseases using efficinetnet-B0 convolutional neural network, in New Perspectives on Hybrid Intelligent System Design based on Fuzzy Logic, Neural Networks and Metaheuristics (pp. 3–19). Springer (2022).
Skin Diseases Image Dataset, Ismail Hossain. 2021. https://www.kaggle.com/datasets/ismailpromus/skin-diseases-image-dataset . Accessed February 9, 2024.
Hammad, M., Pławiak, P., ElAffendi, M., El-Latif, A. A. A. & Latif, A. A. A. Enhanced deep learning approach for accurate eczema and psoriasis skin detection. Sensors 23(16), 7295 (2023).
doi: 10.3390/s23167295
pubmed: 37631831
pmcid: 10457904
Nieniewski, M., Chmielewski, L. J., Patrzyk, S. & Woźniacka, A. Studies in differentiating psoriasis from other dermatoses using small data set and transfer learning. EURASIP J. Image Video Process. 2023(1), 1–20 (2023).
doi: 10.1186/s13640-023-00607-y
About us. (n.d.). Dermatology Education. Retrieved February 8, 2022, from http://www.dermnet.com/about-us/ .
Wen, L., Li, X. & Gao, L. A transfer convolutional neural network for fault diagnosis based on ResNet-50. Neural Comput. Appl. 32(10), 256 (2020).
doi: 10.1007/s00521-019-04097-w
Team, K. (n.d.-b). Keras documentation: ResNet and ResNetV2. Keras.Io. Retrieved December 14, 2021, from https://keras.io/api/applications/resnet/#resnet50-function .
Uppari, R. R. Comparison between KERAS library and FAST. AI library using convolution neural network (image classification) model. Doctoral dissertation, Dublin Business School (2020).
Team, K. (n.d.). Keras documentation: About Keras. Keras.Io. Retrieved December 14, 2021, from https://keras.io/about/ .
Kingma, D. P., & Ba, J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).
Team, K. (n.d.-b). Keras documentation: Keras Applications. Keras.Io. Retrieved December 14, 2021, from https://keras.io/api/applications/ .
Prathanrat, P., & Polprasert, C. Performance prediction of Jupyter notebook in JupyterHub using machine learning, in 2018 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS) (Vol. 3, pp. 157–162). IEEE (2018).