Journal article
Design and Assessment of Convolutional Neural Network Based Methods for Vitiligo Diagnosis
Frontiers in medicine, Vol.8, pp.754202-754202
10/18/2021
DOI: 10.3389/fmed.2021.754202
PMCID: PMC8558218
PMID: 34733869
Abstract
Background:
Today's machine-learning based dermatologic research has largely focused on pigmented/non-pigmented lesions concerning skin cancers. However, studies on machine-learning-aided diagnosis of depigmented non-melanocytic lesions, which are more difficult to diagnose by unaided eye, are very few.
Objective:
We aim to assess the performance of deep learning methods for diagnosing vitiligo by deploying Convolutional Neural Networks (CNNs) and comparing their diagnosis accuracy with that of human raters with different levels of experience.
Methods:
A Chinese in-house dataset (2,876 images) and a world-wide public dataset (1,341 images) containing vitiligo and other depigmented/hypopigmented lesions were constructed. Three CNN models were trained on close-up images in both datasets. The results by the CNNs were compared with those by 14 human raters from four groups: expert raters (>10 years of experience), intermediate raters (5–10 years), dermatology residents, and general practitioners. F1 score, the area under the receiver operating characteristic curve (AUC), specificity, and sensitivity metrics were used to compare the performance of the CNNs with that of the raters.
Results:
For the in-house dataset, CNNs achieved a comparable F1 score (mean [standard deviation]) with expert raters (0.8864 [0.005] vs. 0.8933 [0.044]) and outperformed intermediate raters (0.7603 [0.029]), dermatology residents (0.6161 [0.068]) and general practitioners (0.4964 [0.139]). For the public dataset, CNNs achieved a higher F1 score (0.9684 [0.005]) compared to the diagnosis of expert raters (0.9221 [0.031]).
Conclusion:
Properly designed and trained CNNs are able to diagnose vitiligo without the aid of Wood's lamp images and outperform human raters in an experimental setting.
Details
- Title: Subtitle
- Design and Assessment of Convolutional Neural Network Based Methods for Vitiligo Diagnosis
- Creators
- Li Zhang - Qingdao Women and Children's HospitalSuraj Mishra - University of Notre DameTianyu Zhang - Hong Kong Polytechnic UniversityYue Zhang - China Medical UniversityDuo Zhang - Central Hospital Affiliated to Shenyang Medical CollegeYalin Lv - Qingdao UniversityMingsong Lv - Hong Kong Polytechnic UniversityNan Guan - City University of Hong KongXiaobo Sharon Hu - University of Notre DameDanny Ziyi Chen - University of Notre DameXiuping Han - China Medical University
- Resource Type
- Journal article
- Publication Details
- Frontiers in medicine, Vol.8, pp.754202-754202
- Publisher
- Frontiers Media S.A
- DOI
- 10.3389/fmed.2021.754202
- PMID
- 34733869
- PMCID
- PMC8558218
- ISSN
- 2296-858X
- eISSN
- 2296-858X
- Language
- English
- Date published
- 10/18/2021
- Academic Unit
- Computer Science
- Record Identifier
- 9984696727802771
Metrics
3 Record Views