Abstract：
BACKGROUND: Onychomycosis is a common disease. Emerging noninvasive, real-time techniques such as dermoscopy and deep convolutional neural networks have been proposed for the diagnosis of onychomycosis. However, deep learning application in dermoscopic images has not been reported.
OBJECTIVE: To explore the establishment of deep learning-based diagnostic models for onychomycosis in dermoscopy to improve the diagnostic efficiency and accuracy.
METHODS: We evaluated the dermoscopic patterns of onychomycosis diagnosed at Sun Yat-sen Memorial Hospital, Guangzhou, China, from May 2019 to February 2021 and included nail psoriasis and traumatic onychodystrophy as control groups. Based on the dermoscopic images and the characteristic dermoscopic patterns of onychomycosis, we gain the faster region-based convolutional neural networks to distinguish between nail disorder and normal nail, onychomycosis and non-mycological nail disorder (nail psoriasis and traumatic onychodystrophy). The diagnostic performance is compared between deep learning-based diagnosis models and dermatologists.
RESULTS: All of 1,155 dermoscopic images were collected, including onychomycosis (603 images), nail psoriasis (221 images), traumatic onychodystrophy (104 images) and normal cases (227 images). Statistical analyses revealed subungual keratosis, distal irregular termination, longitudinal striae, jagged edge, and marble-like turbid area, and cone-shaped keratosis were of high specificity (>82%) for onychomycosis diagnosis. The deep learning-based diagnosis models (ensemble model) showed test accuracy /specificity/ sensitivity /Youden index of (95.7%/98.8%/82.1%/0.809) and (87.5%/93.0%/78.5%/0.715) for nail disorder and onychomycosis. The diagnostic performance for onychomycosis using ensemble model was superior to 54 dermatologists.
CONCLUSIONS: Our study demonstrated that onychomycosis had distinctive dermoscopic patterns, compared with nail psoriasis and traumatic onychodystrophy. The deep learning-based diagnosis models showed a diagnostic accuracy of onychomycosis, superior to dermatologists.
OBJECTIVE: To explore the establishment of deep learning-based diagnostic models for onychomycosis in dermoscopy to improve the diagnostic efficiency and accuracy.
METHODS: We evaluated the dermoscopic patterns of onychomycosis diagnosed at Sun Yat-sen Memorial Hospital, Guangzhou, China, from May 2019 to February 2021 and included nail psoriasis and traumatic onychodystrophy as control groups. Based on the dermoscopic images and the characteristic dermoscopic patterns of onychomycosis, we gain the faster region-based convolutional neural networks to distinguish between nail disorder and normal nail, onychomycosis and non-mycological nail disorder (nail psoriasis and traumatic onychodystrophy). The diagnostic performance is compared between deep learning-based diagnosis models and dermatologists.
RESULTS: All of 1,155 dermoscopic images were collected, including onychomycosis (603 images), nail psoriasis (221 images), traumatic onychodystrophy (104 images) and normal cases (227 images). Statistical analyses revealed subungual keratosis, distal irregular termination, longitudinal striae, jagged edge, and marble-like turbid area, and cone-shaped keratosis were of high specificity (>82%) for onychomycosis diagnosis. The deep learning-based diagnosis models (ensemble model) showed test accuracy /specificity/ sensitivity /Youden index of (95.7%/98.8%/82.1%/0.809) and (87.5%/93.0%/78.5%/0.715) for nail disorder and onychomycosis. The diagnostic performance for onychomycosis using ensemble model was superior to 54 dermatologists.
CONCLUSIONS: Our study demonstrated that onychomycosis had distinctive dermoscopic patterns, compared with nail psoriasis and traumatic onychodystrophy. The deep learning-based diagnosis models showed a diagnostic accuracy of onychomycosis, superior to dermatologists.
摘要：
背景：甲真菌病是一种常见病。新兴的非侵入性，皮肤镜和深度卷积神经网络等实时技术已被提出用于甲癣的诊断。然而,深度学习在皮肤镜图像中的应用尚未见报道。
目的：探索建立基于深度学习的甲真菌病皮肤镜检诊断模型，以提高诊断效率和准确性。
方法：我们评估了在孙逸仙纪念医院诊断的甲真菌病的皮肤镜模式，广州,中国,从2019年5月至2021年2月，包括指甲牛皮癣和创伤性甲营养不良作为对照组。根据甲真菌病的皮肤镜图像和特征性皮肤镜模式，我们获得了更快的基于区域的卷积神经网络来区分指甲疾病和正常指甲，甲真菌病和非真菌学指甲疾病（指甲牛皮癣和创伤性甲营养不良）。在基于深度学习的诊断模型和皮肤科医生之间比较诊断性能。
结果：收集了所有1,155张皮肤图像，包括甲癣（603图像），指甲牛皮癣（221张图片），外伤性甲营养不良（104张图像）和正常病例（227张图像）。统计分析显示甲下角化病，远端不规则终止，纵向条纹，锯齿状边缘，和大理石般的混浊区域，和锥形角化病对甲癣的诊断具有高度特异性(>82%)。基于深度学习的诊断模型（集成模型）显示，指甲疾病和甲癣的测试准确性/特异性/敏感性/Youden指数分别为（95.7％/98.8％/82.1％/0.809）和（87.5％/93.0％/78.5％/0.715）。使用集合模型对甲癣的诊断性能优于54位皮肤科医生。
结论：我们的研究表明甲癣有独特的皮肤镜下模式，与指甲牛皮癣和外伤性甲营养不良相比。基于深度学习的诊断模型显示了甲真菌病的诊断准确性，优于皮肤科医生。
目的：探索建立基于深度学习的甲真菌病皮肤镜检诊断模型，以提高诊断效率和准确性。
方法：我们评估了在孙逸仙纪念医院诊断的甲真菌病的皮肤镜模式，广州,中国,从2019年5月至2021年2月，包括指甲牛皮癣和创伤性甲营养不良作为对照组。根据甲真菌病的皮肤镜图像和特征性皮肤镜模式，我们获得了更快的基于区域的卷积神经网络来区分指甲疾病和正常指甲，甲真菌病和非真菌学指甲疾病（指甲牛皮癣和创伤性甲营养不良）。在基于深度学习的诊断模型和皮肤科医生之间比较诊断性能。
结果：收集了所有1,155张皮肤图像，包括甲癣（603图像），指甲牛皮癣（221张图片），外伤性甲营养不良（104张图像）和正常病例（227张图像）。统计分析显示甲下角化病，远端不规则终止，纵向条纹，锯齿状边缘，和大理石般的混浊区域，和锥形角化病对甲癣的诊断具有高度特异性(>82%)。基于深度学习的诊断模型（集成模型）显示，指甲疾病和甲癣的测试准确性/特异性/敏感性/Youden指数分别为（95.7％/98.8％/82.1％/0.809）和（87.5％/93.0％/78.5％/0.715）。使用集合模型对甲癣的诊断性能优于54位皮肤科医生。
结论：我们的研究表明甲癣有独特的皮肤镜下模式，与指甲牛皮癣和外伤性甲营养不良相比。基于深度学习的诊断模型显示了甲真菌病的诊断准确性，优于皮肤科医生。
