Affiliations: [a] College of Computer Science and Technology, Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education, Jilin University, Changchun, Jilin, China | [b] Department of Dermatology and Venereology, The First Hospital of Jilin University, Changchun, Jilin, China | [c] Department of Epidemiology and Biostatistics, School of Public Health, Jilin University, Changchun, Jilin, China | [d] Beijing Dr. of Acne Medical Research Institute, Beijing, China | [e] College of Information Technology (Smart Agriculture Research Institute), Jilin Agricultural University, Changchun, Jilin, China
Correspondence:
[*]
Corresponding author: Fengfeng Zhou, College of Computer Science and Technology, Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education, Jilin University, Changchun, Jilin, China. E-mails: FengfengZhou@gmail.com and ffzhou@jlu.edu.cn.
Abstract: BACKGROUND: Acne is a skin lesion type widely existing in adolescents, and poses computational challenges for automatic diagnosis. Computer vision algorithms are utilized to detect and determine different subtypes of acne. Most of the existing acne detection algorithms are based on the facial natural images, which carry noisy factors like illuminations. OBJECTIVE: In order to tackle this issue, this study collected a dataset ACNEDer of dermoscopic acne images with annotations. Deep learning methods have demonstrated powerful capabilities in automatic acne diagnosis, and they usually release the training epoch with the best performance as the delivered model. METHODS: This study proposes a novel self-ensemble and stacking-based framework AcneTyper for diagnosing the acne subtypes. Instead of delivering the best epoch, AcneTyper consolidates the prediction results of all training epochs as the latent features and stacks the best subset of these latent features for distinguishing different acne subtypes. RESULTS: The proposed AcneTyper framework achieves a promising detection performance of acne subtypes and even outperforms a clinical dermatologist with two-year experiences by 6.8% in accuracy. CONCLUSION: The method we proposed is used to determine different subtypes of acne and outperforms inexperienced dermatologists and contributes to reducing the probability of misdiagnosis.
Keywords: Acne subtype, deep learning, self-ensemble, stacking, classification
