A cell phone app for facial acne severity assessment

Wang, Jiaoju1; Luo, Yan2; Wang, Zheng1,3; Hounye, Alphonse Houssou1; Cao, Cong1; Hou, Muzhou1; Zhang, Jianglin4,5

2022-07-01

10.1007/s10489-022-03774-z

APPLIED INTELLIGENCE   Impact Factor & Quartile

0924-669X

1573-7497

Acne vulgaris, the most common skin disease, can cause substantial economic and psychological impacts to the people it affects, and its accurate grading plays a crucial role in the treatment of patients. In this paper, we firstly proposed an acne grading criterion that considers lesion classifications and a metric for producing accurate severity ratings. Due to similar appearance of acne lesions with comparable severities and difficult-to-count lesions, severity assessment is a challenging task. We cropped facial skin images of several lesion patches and then addressed the acne lesion with a lightweight acne regular network (Acne-RegNet). Acne-RegNet was built by using a median filter and histogram equalization to improve image quality, a channel attention mechanism to boost the representational power of network, a region-based focal loss to handle classification imbalances and a model pruning and feature-based knowledge distillation to reduce model size. After the application of Acne-RegNet, the severity score is calculated, and the acne grading is further optimized by the metadata of the patients. The entire acne assessment procedure was deployed to a mobile device, and a phone app was designed. Compared with state-of-the-art lightweight models, the proposed Acne-RegNet significantly improves the accuracy of lesion classifications. The acne app demonstrated promising results in severity assessments (accuracy: 94.56%) and showed a dermatologist-level diagnosis on the internal clinical dataset.The proposed acne app could be a useful adjunct to assess acne severity in clinical practice and it enables anyone with a smartphone to immediately assess acne, anywhere and anytime.

Deep learning(DL) Acne vulgaris Cell phone app Severity assessment Acne regular network

SCI

English

Corresponding

Natural Science Foundation of Hunan Province,China[2022JJ30673] ; Scientific Research Fund of Hunan Provincial Education Department[20C0402] ; Hunan First Normal University[XYS16N03] ; National Natural Science Foundation of China["82073019","82073018"] ; Shenzhen Science and Technology Innovation Commission, China (Natural Science Foundation of Shenzhen)[JCYJ20210324113001005]

Computer Science

Computer Science, Artificial Intelligence

WOS:000832835500002

SPRINGER

ENGINEERING

Web of Science

1.Cent South Univ, Sch Math & Stat, Changsha 410083, Hunan, Peoples R China
2.Cent South Univ, Dept Dermatol, Xiangya Hosp, Changsha 410083, Hunan, Peoples R China
3.Hunan First Normal Univ, Sci & Engn Sch, Changsha 410083, Hunan, Peoples R China
4.Southern Univ Sci & Technol, Dept Dermatol, Affiliated Hosp 1, Shenzhen Peoples Hosp,Clin Med Coll 2,Jinan Unin, Shenzhen 518020, Guangdong, Peoples R China
5.Natl Clin Res Ctr Skin Dis, Candidate Branch, Shenzhen 518020, Guangdong, Peoples R China

Wang, Jiaoju,Luo, Yan,Wang, Zheng,et al. A cell phone app for facial acne severity assessment[J]. APPLIED INTELLIGENCE,2022.

Wang, Jiaoju.,Luo, Yan.,Wang, Zheng.,Hounye, Alphonse Houssou.,Cao, Cong.,...&Zhang, Jianglin.(2022).A cell phone app for facial acne severity assessment.APPLIED INTELLIGENCE.

Wang, Jiaoju,et al."A cell phone app for facial acne severity assessment".APPLIED INTELLIGENCE (2022).