文献速递皮肤感染自身免疫性与大疱性皮肤病银屑病与炎症性皮肤病

皮肤科异常值检测:不同卷积神经网络在炎症性皮肤病二分类中的性能

Outlier detection in dermatology: Performance of different convolutional neural networks for binary classification of inflammatory skin diseases.
PubMed 文献 · J Eur Acad Dermatol Venereol · 2023-01-27

本研究评估六种卷积神经网络架构在五种皮肤病临床图像上的二分类性能,使用五个数据子集(包括两位皮肤科医生筛选的数据),共评估多达4051张图像上的150个网络。甲真菌病准确率最高(1.000),大疱性类天疱疮为0.951,红斑狼疮为0.912。资深医师提供的数据集与符合两位皮肤科医生共同标准的数据集平均表现最佳(准确率=0.910)。

要点

  • 甲真菌病二分类准确率最高(1.000),其次为大疱性类天疱疮(0.951)和红斑狼疮(0.912)。
  • InceptionV3、Xception和ResNet50分别在25个数据集中9、8、6个达到最佳准确率(36.0%、32.0%、24.0%)。
  • 资深医师筛选及符合两位皮肤科医生共同标准的数据集平均准确率最佳(0.910)。

核心结论

  • 该AI异常值检测方法代表首批评估不同CNN在非黑色素瘤皮肤病临床非皮肤镜图像二分类中性能的研究之一。
  • 经验丰富的皮肤科医生在预处理阶段筛选图像对CNN性能有实质性益处。
  • 这些比较结果可能指导未来皮肤科诊断的AI方法,所评估的CNN可能适用于未来皮肤科住院医师的培训。

研究设计与样本

  • 评估六种最先进的CNN架构,针对五种皮肤病和五个数据子集(包括由两位分别有5年和11年临床经验的皮肤科医生筛选的数据)计算准确率、敏感性和特异性。
  • 共评估150个CNN,使用多达4051张临床图像。

主要发现

  • 甲真菌病准确率最高(准确率=1.000),其次为大疱性类天疱疮(准确率=0.951)和红斑狼疮(准确率=0.912)。
  • CNN InceptionV3、Xception和ResNet50分别在25个数据集中的9、8、6个达到最佳准确率(36.0%、32.0%、24.0%)。
  • 资深医师提供的数据集与符合两位皮肤科医生共同标准的数据集平均表现最佳(准确率=0.910)。

临床怎么用

  • 作者认为,经验丰富的皮肤科医生在预处理阶段筛选图像对CNN性能有实质性益处。
  • 作者认为,这些比较结果可能指导未来皮肤科诊断的AI方法,所评估的CNN可能适用于未来皮肤科住院医师的培训。

局限性

  • 原文未报告局限性

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: Artificial intelligence (AI) and convolutional neural networks (CNNs) represent rising trends in modern medicine. However, comprehensive data on the performance of AI practices in clinical dermatologic images are non-existent. Furthermore, the role of professional data selection for training remains unknown. OBJECTIVES: The aims of this study were to develop AI applications for outlier detection of dermatological pathologies, to evaluate CNN architectures' performance on dermatological images and to investigate the role of professional pre-processing of the training data, serving as one of the first anchor points regarding data selection criteria in dermatological AI-based binary classification tasks of non-melanoma pathologies. METHODS: Six state-of-the-art CNN architectures were evaluated for their accuracy, sensitivity and specificity for five dermatological diseases and using five data subsets, including data selected by two dermatologists, one with 5 and the other with 11 years of clinical experience. RESULTS: Overall, 150 CNNs were evaluated on up to 4051 clinical images. The best accuracy was reached for onychomycosis (accuracy = 1.000), followed by bullous pemphigoid (accuracy = 0.951) and lupus erythematosus (accuracy = 0.912). The CNNs InceptionV3, Xception and ResNet50 achieved the best accuracy in 9, 8 and 6 out of 25 data sets, respectively (36.0%, 32.0% and 24.0%). On average, the data set provided by the senior physician and the data set provided in accordance with both dermatologists performed the best (accuracy = 0.910). CONCLUSIONS: This AI approach for the detection of outliers in dermatological diagnoses represents one of the first studies to evaluate the performance of different CNNs for binary decisions in clinical non-dermatoscopic images of a variety of dermatological diseases other than melanoma. The selection of images by an experienced dermatologist during pre-processing had substantial benefits for the performance of the CNNs. These comparative results might guide future AI approaches to dermatology diagnostics, and the evaluated CNNs might be applicable for the future training of dermatology residents.

来源:J Eur Acad Dermatol Venereol,查看原文。版权归原作者所有。

引用

  1. Schielein MC, Christl J, Sitaru S, et al. Outlier detection in dermatology: Performance of different convolutional neural networks for binary classification of inflammatory skin diseases. J Eur Acad Dermatol Venereol. 2023. PMID: 36606561. doi:10.1111/jdv.18853

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。