Accuracy of automated machine learning in classifying retinal pathologies from ultra-widefield pseudocolour fundus images
Accuracy of automated machine learning in classifying retinal pathologies from ultra-widefield pseudocolour fundus images
复制标题
DOI：
10.1136/bjophthalmol-2021-319030
复制
发表时间：
2021-08-02
影响因子：
4.1
通讯作者：
Duval, Renaud
中科院分区：
文献类型：
--
作者：
Antaki, Fares;Coussa, Razek Georges;Duval, Renaud
自动机器学习（AutoML）是人工智能（AI）领域的一种新工具。本研究使用超宽视野（UWF）假彩色眼底图像评估AutoML在区分视网膜静脉阻塞（RVO）、视网膜色素变性（RP）和视网膜脱离（RD）与正常眼底方面的区分性能。方法两名无编码经验的眼科医生使用公开的图像数据集（2137张标记图像）进行AutoML模型设计。该数据集经过了低质量和错误标记图像的审查，然后上传到Google Cloud AutoML Vision平台进行训练和测试。我们设计了多个二元模型来区分RVO，RP和RD与正常眼底，并将其与从文献中获得的定制模型进行比较。然后，我们设计了一个多类模型来检测RVO，RP和RD。显着地图，以评估模型的可解释性。AutoML模型在二进制分类任务中表现出较高的诊断性能，通常与定制的深度学习模型相当（精确召回曲线下面积（AUPRC）0.921-1，灵敏度84.91%-89.77%，特异性78.72%-100%）。多类AutoML模型的AUPRC为0.876，灵敏度为77.93%，阳性预测值为82.59%。符合诊断标准的敏感性和特异性分别为：眼底正常（91.49%，86.75%）、RVO（83.02%，92.50%）、RP（72.00%，100%）和RD（79.55%，96.80%）。结论由没有编码经验的眼科医生创建的AutoML模型可以检测UWF图像中的RVO、RP和RD，具有很好的诊断准确性。其性能与人工智能专家为RVO和RP而不是RD开发的定制深度学习模型相当。
Aims Automated machine learning (AutoML) is a novel tool in artificial intelligence (AI). This study assessed the discriminative performance of AutoML in differentiating retinal vein occlusion (RVO), retinitis pigmentosa (RP) and retinal detachment (RD) from normal fundi using ultra-widefield (UWF) pseudocolour fundus images. Methods Two ophthalmologists without coding experience carried out AutoML model design using a publicly available image data set (2137 labelled images). The data set was reviewed for low-quality and mislabeled images and then uploaded to the Google Cloud AutoML Vision platform for training and testing. We designed multiple binary models to differentiate RVO, RP and RD from normal fundi and compared them to bespoke models obtained from the literature. We then devised a multiclass model to detect RVO, RP and RD. Saliency maps were generated to assess the interpretability of the model. Results The AutoML models demonstrated high diagnostic properties in the binary classification tasks that were generally comparable to bespoke deep-learning models (area under the precision-recall curve (AUPRC) 0.921-1, sensitivity 84.91%-89.77%, specificity 78.72%-100%). The multiclass AutoML model had an AUPRC of 0.876, a sensitivity of 77.93% and a positive predictive value of 82.59%. The per-label sensitivity and specificity, respectively, were normal fundi (91.49%, 86.75%), RVO (83.02%, 92.50%), RP (72.00%, 100%) and RD (79.55%,96.80%). Conclusion AutoML models created by ophthalmologists without coding experience can detect RVO, RP and RD in UWF images with very good diagnostic accuracy. The performance was comparable to bespoke deep-learning models derived by AI experts for RVO and RP but not for RD.