文献速递皮肤肿瘤

基于内容的皮肤镜图像检索与深度分类特征的诊断准确性

Diagnostic accuracy of content-based dermatoscopic image retrieval with deep classification features.
PubMed 文献 · Br J Dermatol · 2018-10-17

研究比较基于内容的图像检索(CBIR)与神经网络softmax预测在皮肤镜图像上的诊断准确性。在三个回顾性数据集(分别含888、2750和16691张图像)中,CBIR评估16张最相似图像的皮肤癌预测AUC与softmax预测相似,多分类准确率相当,且三分类网络用CBIR在八分类数据集上表现更好。结论认为CBIR在常规临床中可能比softmax分类器更有助于提高诊断准确性。

要点

  • CBIR检索16张最相似图像的皮肤癌预测AUC与softmax预测相似,差异无统计学显著。
  • CBIR的多分类准确率与softmax预测相当。
  • 三分类网络用CBIR在八分类数据集上mAP优于softmax预测。

核心结论

  • 基于神经网络特征的视觉相似图像展示与卷积神经网络softmax概率诊断准确性相当。
  • CBIR在常规临床中可能比softmax分类器更有助于提高临床医生的诊断准确性。

研究设计与样本

  • 神经网络在三个回顾性收集的皮肤镜图像数据集上训练,分别含888、2750和16691张图像。
  • 诊断预测基于视觉相似图像中最常见的诊断或网络softmax输出的top-1类预测。
  • 结局指标为预测恶性病变的受试者工作特征曲线下面积(AUC)、多分类准确率和平均平均精度(mAP),在对应数据集的未见测试图像上测量。

主要发现

  • 三个数据集中,CBIR(评估16张最相似图像)的皮肤癌预测AUC与softmax预测相似:分别为0.842、0.806、0.852 vs. 0.830、0.810、0.847,所有P > 0.99。
  • CBIR的多分类准确率与softmax预测相当。
  • 与softmax预测相比,仅检测三类的网络在使用CBIR时在八类数据集上表现更好(mAP 0.184 vs. 0.368 和 0.198 vs. 0.403)。

临床怎么用

  • 原文结论指出CBIR在常规临床中可能比softmax分类器更有助于提高临床医生的诊断准确性。

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: Automated classification of medical images through neural networks can reach high accuracy rates but lacks interpretability. OBJECTIVES: To compare the diagnostic accuracy obtained by using content-based image retrieval (CBIR) to retrieve visually similar dermatoscopic images with corresponding disease labels against predictions made by a neural network. METHODS: A neural network was trained to predict disease classes on dermatoscopic images from three retrospectively collected image datasets containing 888, 2750 and 16 691 images, respectively. Diagnosis predictions were made based on the most commonly occurring diagnosis in visually similar images, or based on the top-1 class prediction of the softmax output from the network. Outcome measures were area under the receiver operating characteristic curve (AUC) for predicting a malignant lesion, multiclass-accuracy and mean average precision (mAP), measured on unseen test images of the corresponding dataset. RESULTS: In all three datasets the skin cancer predictions from CBIR (evaluating the 16 most similar images) showed AUC values similar to softmax predictions (0·842, 0·806 and 0·852 vs. 0·830, 0·810 and 0·847, respectively; P > 0·99 for all). Similarly, the multiclass-accuracy of CBIR was comparable with softmax predictions. Compared with softmax predictions, networks trained for detecting only three classes performed better on a dataset with eight classes when using CBIR (mAP 0·184 vs. 0·368 and 0·198 vs. 0·403, respectively). CONCLUSIONS: Presenting visually similar images based on features from a neural network shows comparable accuracy with the softmax probability-based diagnoses of convolutional neural networks. CBIR may be more helpful than a softmax classifier in improving diagnostic accuracy of clinicians in a routine clinical setting.

来源:Br J Dermatol,查看原文。版权归原作者所有。

引用

  1. Tschandl P, Argenziano G, Razmara M, et al. Diagnostic accuracy of content-based dermatoscopic image retrieval with deep classification features. Br J Dermatol. 2018. PMID: 30207594. doi:10.1111/bjd.17189

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。