前节生物测量参数解释深度学习分类器检测房角镜房角关闭的误分类
本研究基于华人美国人眼研究(CHES)的AS-OCT图像,分析深度学习分类器检测房角镜房角关闭时误分类的生物测量参数原因。584张图像中真阳性271、真阴性224、假阳性77、假阴性12。假阳性在前节参数上类似真阳性(更陡的虹膜曲率、更高的晶状体拱高),但在房角参数上类似真阴性(更宽的房角开放距离)。检测假阳性和假阴性的模型将分类器准确率从84.8%提升至89.0%。
要点
- 误分类源于前节参数与房角参数之间的不一致。
- 假阳性前节参数类似真阳性,但房角参数类似真阴性。
- 检测误分类的模型可提升分类器准确率至89.0%。
核心结论
- 基于OCT的深度学习分类器检测房角镜房角关闭的误分类可由前节参数与房角参数之间的不一致解释。
研究设计与样本
- 华人美国人眼研究(CHES)参与者接受房角镜和AS-OCT每个房角象限检查,部分AS-OCT图像用深度学习分类器分析。
- 共分析127名参与者的584张图像,分为真阳性271、真阴性224、假阳性77、假阴性12四类。
主要发现
- 前节参数包括虹膜曲率(IC)和晶状体拱高(LV),房角参数包括房角开放距离(AOD),各预测类别间测量值差异p<0.001。
- 假阳性在前节参数上更接近真阳性(更陡的IC和更高的LV),但在房角参数上更接近真阴性(更宽的AOD)。
- 检测假阳性的模型AUC=0.752,检测假阴性的模型AUC=0.838,将分类器准确率从84.8%提升至89.0%。
关键数值与推荐
- 深度学习分类器基于参考人类检查者的手动房角镜结果检测房角关闭阳性。
- 假阳性检测模型AUC=0.752,假阴性检测模型AUC=0.838。
- 分类器准确率从84.8%提升至89.0%。
临床怎么用
- 可利用前节与房角参数的不一致来识别和纠正深度学习分类器的误分类,提升检测性能。
- 需注意房角镜与AS-OCT对房角关闭定义之间的差异。
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/AIMS: To identify biometric parameters that explain misclassifications by a deep learning classifier for detecting gonioscopic angle closure in anterior segment optical coherence tomography (AS-OCT) images. METHODS: Chinese American Eye Study (CHES) participants underwent gonioscopy and AS-OCT of each angle quadrant. A subset of CHES AS-OCT images were analysed using a deep learning classifier to detect positive angle closure based on manual gonioscopy by a reference human examiner. Parameter measurements were compared between four prediction classes: true positives (TPs), true negatives (TNs), false positives (FPs) and false negatives (FN). Logistic regression models were developed to differentiate between true and false predictions. Performance was assessed using area under the receiver operating curve (AUC) and classifier accuracy metrics. RESULTS: 584 images from 127 participants were analysed, yielding 271 TPs, 224 TNs, 77 FPs and 12 FNs. Parameter measurements differed (p<0.001) between prediction classes among anterior segment parameters, including iris curvature (IC) and lens vault (LV), and angle parameters, including angle opening distance (AOD). FP resembled TP more than FN and TN in terms of anterior segment parameters (steeper IC and higher LV), but resembled TN more than TP and FN in terms of angle parameters (wider AOD). Models for detecting FP (AUC=0.752) and FN (AUC=0.838) improved classifier accuracy from 84.8% to 89.0%. CONCLUSIONS: Misclassifications by an OCT-based deep learning classifier for detecting gonioscopic angle closure are explained by disagreement between anterior segment and angle parameters. This finding could be used to improve classifier performance and highlights differences between gonioscopic and AS-OCT definitions of angle closure.
引用
- Shen A, Chiang M, Pardeshi AA, et al. Anterior segment biometric measurements explain misclassifications by a deep learning classifier for detecting gonioscopic angle closure. Br J Ophthalmol. 2021. PMID: 34615666. doi:10.1136/bjophthalmol-2021-319058
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。