A novel automatic acne detection and severity quantification scheme using deep learning

Wang, Jiaoju1; Wang, Chong2; Wang, Zheng1,3; Hounye, Alphonse Houssou1; Li, Zhaoying1; Kong, MengLin1; Hou, Muzhou1; Zhang, Jianglin4,5,6; Qi, Min7

2023-07-01

10.1016/j.bspc.2023.104803

BIOMEDICAL SIGNAL PROCESSING AND CONTROL   影响因子和分区

1746-8094

1746-8108

Accurate detection and severity quantification of acne are of great significance in the precise treatment of patients. Due to the similar appearance of acne with close severity, it is challenging for dermatologists to grade acne accurately and efficiently. This study aims to propose an accurate and efficient scheme based on deep learning (DL) to assist dermatologists in acne detection and severity quantification. The proposed frame consists of two steps: the Localization deep learning (Localization-DL) model and the Class segmentation (ClassSeg) model. The first model uses the distilled lightweight convolution network as the backbone and extracts multi-scale features through a pyramid pooling module for facial region localization and distinction. The second model is a unified framework that combines a Class module to distinguish background and facial skin sub-images and a segmentation (Seg) module to perform segmentation for different classes to obtain lesion masks. The facial skin segmentation branch of the ClassSeg model is built based on a high-resolution network (HRNet) and modified by mask-aware attention, shuffle attention, and conditional channel weight block. The experiments show that the two models achieve promising results and demonstrate effectiveness in lesion detection compared to other methods. The proposed scheme shows excellent results in acne severity quantification and yields a comparable performance with dermatologists (accuracy: 0.9091 for ours, 0.9301 for SDerms, 0.8741 for IDerms, and 0.7483 for JDerms). The assessment performance also outperforms the existing approaches. This work opens new avenues for acne severity quantification and provides valuable diagnosis evidence for dermatologists in clinical practice.

Deep learning (DL) Acne lesion Severity quantification Segmentation

SCI

英语

通讯

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

Engineering

Engineering, Biomedical

WOS:000962499100001

ELSEVIER SCI LTD

Web of Science

1.Cent South Univ, Sch Math & Stat, Changsha 410083, Peoples R China
2.Cent South Univ, Xiangya Hosp, Dept Dermatol, Changsha 410008, Peoples R China
3.Hunan First Normal Univ, Sch Comp Sci, Changsha 410205, Peoples R China
4.Jinan Univ, Dept Dermatol, Shenzhen Peoples Hosp, Clin Med Coll 2, Shenzhen 518020, Guangdong, Peoples R China
5.Southern Univ Sci & Technol, Affiliated Hosp 1, Shenzhen 518020, Guangdong, Peoples R China
6.Natl Clin Res Ctr Skin Dis, Beijing, Peoples R China
7.Cent South Univ, Xiangya Hosp, Dept Plast Surg, Changsha 410008, Peoples R China

Wang, Jiaoju,Wang, Chong,Wang, Zheng,et al. A novel automatic acne detection and severity quantification scheme using deep learning[J]. BIOMEDICAL SIGNAL PROCESSING AND CONTROL,2023,84.

Wang, Jiaoju.,Wang, Chong.,Wang, Zheng.,Hounye, Alphonse Houssou.,Li, Zhaoying.,...&Qi, Min.(2023).A novel automatic acne detection and severity quantification scheme using deep learning.BIOMEDICAL SIGNAL PROCESSING AND CONTROL,84.

Wang, Jiaoju,et al."A novel automatic acne detection and severity quantification scheme using deep learning".BIOMEDICAL SIGNAL PROCESSING AND CONTROL 84(2023).