深度学习在非肿瘤性皮肤病中的应用进展

doi:10.35541/cjd.20220660

Abstract

Abstract: 【Abstract】 With the emergence of the era of big data and the development of computer science, the application of deep learning in dermatology has expanded from the differentiation between benign and malignant cutaneous tumors to the assistance in the diagnosis, severity assessment and treatment of various non-neoplastic dermatoses. This review summarizes recent advances in the application of deep learning in the auxiliary diagnosis and treatment of psoriasis, atopic dermatitis/eczema, onychomycosis, acne vulgaris, etc., so as to raise dermatologists′ understanding of this field and promote the development of related research.

Key words: Artificial intelligence, Psoriasis, Dermatitis, atopic, Onychomycosis, Acne vulgaris, Diagnosis, Deep learning, Non-neoplastic dermatoses, Disease severity assessment, Treatment

Wang Yukun, Liu Jie. Application of deep learning in non-neoplastic dermatoses[J]. Chinese Journal of Dermatology,2024,e20220660. doi:10.35541/cjd.20220660

References ［34］

［1］	刘洁, 邹先彪. 实用皮肤镜学［M］. 北京:人民卫生出版社, 2021.
［2］	Liu J, Zou XB. Practical dermoscopy［M］. Singapore: Springer Singapore, 2022.
［3］	Esteva A, Kuprel B, Novoa RA, et al. Dermatologist⁃level classification of skin cancer with deep neural networks［J］. Nature, 2017,542（7639）:115⁃118. doi: 10.1038/nature21056.
［4］	Zhao S, Xie B, Li Y, et al. Smart identification of psoriasis by images using convolutional neural networks: a case study in China［J］. J Eur Acad Dermatol Venereol, 2020,34（3）:518⁃524. doi: 10.1111/jdv.15965.
［5］	Yang Y, Wang J, Xie F, et al. A convolutional neural network trained with dermoscopic images of psoriasis performed on par with 230 dermatologists［J］. Comput Biol Med, 2021,139:104924. doi: 10.1016/j.compbiomed.2021.104924.
［6］	Aijaz SF, Khan SJ, Azim F, et al. Deep learning application for effective classification of different types of psoriasis［J］. J Healthc Eng, 2022,2022:7541583. doi: 10.1155/2022/7541583.
［7］	Meienberger N, Anzengruber F, Amruthalingam L, et al. Observer⁃independent assessment of psoriasis⁃affected area using machine learning［J］. J Eur Acad Dermatol Venereol, 2020,34（6）:1362⁃1368. doi: 10.1111/jdv.16002.
［8］	Pal A, Garain U, Chandra A, et al. Psoriasis skin biopsy image segmentation using Deep Convolutional Neural Network［J］. Comput Methods Programs Biomed, 2018,159:59⁃69. doi: 10. 1016/j.cmpb.2018.01.027.
［9］	Schaap MJ, Cardozo NJ, Patel A, et al. Image⁃based automated psoriasis area severity index scoring by convolutional neural networks［J］. J Eur Acad Dermatol Venereol, 2022,36（1）:68⁃75. doi: 10.1111/jdv.17711.
［10］	Okamoto T, Kawai M, Ogawa Y, et al. Artificial intelligence for the automated single⁃shot assessment of psoriasis severity［J］. J Eur Acad Dermatol Venereol, 2022,36（12）:2512⁃2515. doi: 10.1111/jdv.18354.
［11］	Damiani G, Conic R, Pigatto P, et al. Predicting secukinumab fast⁃responder profile in psoriatic patients: advanced application of artificial⁃neural⁃networks （ANNs）［J］. J Drugs Dermatol, 2020,19（12）:1241⁃1246. doi: 10.36849/JDD.2020.5006.
［12］	Guimarães P, Batista A, Zieger M, et al. Artificial intelligence in multiphoton tomography: atopic dermatitis diagnosis［J］. Sci Rep, 2020,10（1）:7968. doi: 10.1038/s41598⁃020⁃64937⁃x.
［13］	Rasheed A, Umar AI, Shirazi SH, et al. Automatic eczema classification in clinical images based on hybrid deep neural network［J］. Comput Biol Med, 2022,147:105807. doi: 10.1016/j.compbiomed.2022.105807.
［14］	Bang CH, Yoon JW, Ryu JY, et al. Automated severity scoring of atopic dermatitis patients by a deep neural network［J］. Sci Rep, 2021,11（1）:6049. doi: 10.1038/s41598⁃021⁃85489⁃8.
［15］	Wang Y, Qin D, Jin L, et al. Caffeoyl malic acid is a potential dual inhibitor targeting TNFα/IL⁃4 evaluated by a combination strategy of network analysis⁃deep learning⁃molecular simulation［J］. Comput Biol Med, 2022,145:105410. doi: 10.1016/j.compbiomed.2022.105410.
［16］	中华医学会皮肤性病学分会特应性皮炎研究中心, 中华医学会皮肤性病学分会儿童学组. 度普利尤单抗治疗特应性皮炎专家共识［J］. 中华皮肤科杂志, 2022,55（6）:465⁃470. doi: 10.35541/cjd.20210885.
［17］	Han SS, Park GH, Lim W, et al. Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: automatic construction of onychomycosis datasets by region⁃based convolutional deep neural network［J］. PLoS One, 2018,13（1）:e0191493. doi: 10.1371/journal.pone. 0191493.
［18］	Kim YJ, Han SS, Yang HJ, et al. Prospective, comparative evaluation of a deep neural network and dermoscopy in the diagnosis of onychomycosis［J］. PLoS One, 2020,15（6）:e0234334. doi: 10.1371/journal.pone.0234334.
［19］	Decroos F, Springenberg S, Lang T, et al. A deep learning approach for histopathological diagnosis of onychomycosis: not inferior to analogue diagnosis by histopathologists［J］. Acta Derm Venereol, 2021,101（8）:adv00532. doi: 10.2340/00015555⁃3893.
［20］	Zhu X, Zheng B, Cai W, et al. Deep learning⁃based diagnosis models for onychomycosis in dermoscopy［J］. Mycoses, 2022,65（4）:466⁃472. doi: 10.1111/myc.13427.
［21］	Yilmaz A, Göktay F, Varol R, et al. Deep convolutional neural networks for onychomycosis detection using microscopic images with KOH examination［J］. Mycoses, 2022,65（12）:1119⁃1126. doi: 10.1111/myc.13498.
［22］	Shen X, Zhang J, Yan C, et al. An automatic diagnosis method of facial acne vulgaris based on convolutional neural network［J］. Sci Rep, 2018,8（1）:5839. doi: 10.1038/s41598⁃018⁃24204⁃6.
［23］	Lim ZV, Akram F, Ngo CP, et al. Automated grading of acne vulgaris by deep learning with convolutional neural networks［J］. Skin Res Technol, 2020,26（2）:187⁃192. doi: 10.1111/srt.12794.
［24］	Yang Y, Guo L, Wu Q, et al. Construction and evaluation of a deep learning model for assessing acne vulgaris using clinical images［J］. Dermatol Ther （Heidelb）, 2021,11（4）:1239⁃1248. doi: 10.1007/s13555⁃021⁃00541⁃9.
［25］	Seité S, Khammari A, Benzaquen M, et al. Development and accuracy of an artificial intelligence algorithm for acne grading from smartphone photographs［J］. Exp Dermatol, 2019,28（11）:1252⁃1257. doi: 10.1111/exd.14022.
［26］	Wang J, Luo Y, Wang Z, et al. A cell phone app for facial acne severity assessment［J］. Appl Intell （Dordr）, 2023,53（7）:7614⁃7633. doi: 10.1007/s10489⁃022⁃03774⁃z.
［27］	Phan DT, Ta QB, Huynh TC, et al. A smart LED therapy device with an automatic facial acne vulgaris diagnosis based on deep learning and internet of things application［J］. Comput Biol Med, 2021,136:104610. doi: 10.1016/j.compbiomed.2021.104610.
［28］	Binol H, Plotner A, Sopkovich J, et al. Ros⁃NET: a deep convolutional neural network for automatic identification of rosacea lesions［J］. Skin Res Technol, 2020,26（3）:413⁃421. doi: 10.1111/srt.12817.
［29］	Zhao Z, Wu CM, Zhang S, et al. A novel convolutional neural network for the diagnosis and classification of rosacea: usability study［J］. JMIR Med Inform, 2021,9（3）:e23415. doi: 10.2196/23415.
［30］	Wu H, Yin H, Chen H, et al. A deep learning⁃based smartphone platform for cutaneous lupus erythematosus classification assistance: simplifying the diagnosis of complicated diseases［J］. J Am Acad Dermatol, 2021,85（3）:792⁃793. doi: 10.1016/j.jaad. 2021.02.043.
［31］	Yang Y, Ge Y, Guo L, et al. Development and validation of two artificial intelligence models for diagnosing benign, pigmented facial skin lesions［J］. Skin Res Technol, 2021,27（1）:74⁃79. doi: 10.1111/srt.12911.
［32］	Guo L, Yang Y, Ding H, et al. A deep learning⁃based hybrid artificial intelligence model for the detection and severity assessment of vitiligo lesions［J］. Ann Transl Med, 2022,10（10）:590. doi: 10.21037/atm⁃22⁃1738.
［33］	Lee S, Lee JW, Choe SJ, et al. Clinically applicable deep learning framework for measurement of the extent of hair loss in patients with alopecia areata［J］. JAMA Dermatol, 2020,156（9）:1018⁃1020. doi: 10.1001/jamadermatol.2020.2188.
［34］	Gao M, Wang Y, Xu H, et al. Deep learning⁃based trichoscopic image analysis and quantitative model for predicting basic and specific classification in male androgenetic alopecia［J］. Acta Derm Venereol, 2022,102:adv00635. doi: 10.2340/actadv.v101. 564.

[1]	Huang Hejin, Li Xinya, He Ziqing, Xi Wenwen, Tang Yujun, Zhang Jianfei, Xiao Xia, Jiang Bin, Yang Feng. Postoperative complications in 3 000 patients with axillary osmidrosis after minimally invasive rotary cutting surgery: a retrospective study [J]. Chinese Journal of Dermatology, 2026, 59(1): 62-64.
[2]	Xue Tianping, Lu Zhenzhong, Wang Hongsheng. Relationship between the pathogenesis of psoriasis and microbial flora [J]. Chinese Journal of Dermatology, 2026, 59(1): 89-92.
[3]	Writing committee of “Chinese expert consensus on the diagnosis and treatment of scabies （ edition）”. Chinese expert consensus on the diagnosis and treatment of scabies （2026 edition） [J]. Chinese Journal of Dermatology, 2026, 59(1): 1-8.
[4]	Wang Su, Wu Jintong, Li Wenyu, Zhang Cheng, Li Chengxin, Wang Rui. Efficacy and safety of cold atmospheric plasma in the treatment of non-open Staphylococcus aureus skin infections in mice [J]. Chinese Journal of Dermatology, 2026, 59(1): 44-50.
[5]	Xiang Leihong, Xu Zhongyi . Diagnosis and treatment of acquired dermal macular hyperpigmentation: challenges and strategies [J]. Chinese Journal of Dermatology, 2026, 59(1): 74-76.
[6]	Jiang Qian, Hu Bin, Chen Yao, Chen Liuqing. Acquired facial hyperpigmented macules in children: a retrospective analysis of clinical and skin imaging features in 131 cases [J]. Chinese Journal of Dermatology, 2025, 58(9): 843-847.
[7]	Xu Zhongyi, Xing Xiaoxue, Dong Yaqi, Zhang Chengfeng, Xiang Leihong. Retrospective analysis of clinical manifestations and treatment outcomes in 254 patients with melasma in a tertiary grade-A hospital in Shanghai [J]. Chinese Journal of Dermatology, 2025, 58(9): 808-815.
[8]	Zhu Tingting, Li Weiran, Pan Zhaobing, Liu Hao, Tang Xianfa, Zhu Caihong, Huang Hequn, Duan Dawei, Zhang Ruochen, Chen Xiaojian, Wang Yang, Xue Qian, Zhang Jurui, Yang Lijing, Zhang Xuejun, Huang He, Zhang Bo, . Efficacy of baricitinib combined with ruxolitinib cream in the treatment of six patients with progressive nonsegmental vitiligo: a clinical observation [J]. Chinese Journal of Dermatology, 2025, 58(9): 856-859.
[9]	Zhou Miaoni, Sheng Anqi, Fu Lifang, Jin Rong, Xu Wen, Wei Xiaodong, Xu Ai′e . Efficacy and safety of an antioxidant gel containing tea polyphenols combined with narrow-band ultraviolet B in the treatment of vitiligo: a single-center randomized controlled trial [J]. Chinese Journal of Dermatology, 2025, 58(9): 834-838.
[10]	Acne Study Group of China Dermatologist Association, Dermatology Professional Committee of Chinese Research Hospital Association, Acne Study Group of Dermatology and Venereology Professional Committee of Chinese Association of Integrative Medicine. Chinese expert consensus on clinical severity grading and therapeutic evaluation of acne vulgaris （2025 edition） [J]. Chinese Journal of Dermatology, 2025, 58(8): 709-714.
[11]	Xue Ke, Chen Jia, Li Bin. Targeted therapy for systemic lupus erythematosus [J]. Chinese Journal of Dermatology, 2025, 58(8): 781-784.
[12]	Chinese Society of Dermatology, China Dermatologist Association. Expert consensus on the diagnosis and treatment of localized scleroderma （2025 edition） [J]. Chinese Journal of Dermatology, 2025, 58(8): 699-708.
[13]	Lyu Shuying, Wang Ying, Lin Wenjun, Yang Dingquan. Efficacy of combination therapy with tofacitinib in the treatment of alopecia ophiasis: a retrospective analysis of 21 cases [J]. Chinese Journal of Dermatology, 2025, 58(7): 630-635.
[14]	Hair Research Group, Chinese Society of Dermatology. Chinese expert consensus on the diagnosis and treatment of lichen planopilaris/frontal fibrosing alopecia （2025 edition） [J]. Chinese Journal of Dermatology, 2025, 58(7): 583-590.
[15]	Zhang Fengyuan, Chen Sihan, Zhou Zizhen, Zhou Meng, Zeng Rong, Chen Xu, Lian Ni, Li Min. Cutibacterium acnes promotes inflammation in acne by inducing Gasdermin E-mediated pyroptosis in keratinocytes [J]. Chinese Journal of Dermatology, 2025, 58(7): 623-629.

Application of deep learning in non-neoplastic dermatoses

PDF

PDF (Mobile)

Knowledge

Abstract

Cite this article

share this article

References ［34］

Related Articles 15

Metrics

Comments

Recommended 10