Hagberg Eva, Hagerman David, Johansson Richard, Hosseini Nasser, Liu Jan, Björnsson Elin, Alvén Jennifer, Hjelmgren Ola
Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden; Region Västra Götaland, Sahlgrenska University Hospital, Department of Clinical Physiology, Gothenburg, Sweden.
Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden; Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden.
Comput Biol Med. 2022 Apr;143:105282. doi: 10.1016/j.compbiomed.2022.105282. Epub 2022 Feb 15.
We created a deep learning model, trained on text classified by natural language processing (NLP), to assess right ventricular (RV) size and function from echocardiographic images. We included 12,684 examinations with corresponding written reports for text classification. After manual annotation of 1489 reports, we trained an NLP model to classify the remaining 10,651 reports. A view classifier was developed to select the 4-chamber or RV-focused view from an echocardiographic examination (n = 539). The final models were two image classification models trained on the predicted labels from the combined manual annotation and NLP models and the corresponding echocardiographic view to assess RV function (training set n = 11,008) and size (training set n = 9951. The text classifier identified impaired RV function with 99% sensitivity and 98% specificity and RV enlargement with 98% sensitivity and 98% specificity. The view classification model identified the 4-chamber view with 92% accuracy and the RV-focused view with 73% accuracy. The image classification models identified impaired RV function with 93% sensitivity and 72% specificity and an enlarged RV with 80% sensitivity and 85% specificity; agreement with the written reports was substantial (both κ = 0.65). Our findings show that models for automatic image assessment can be trained to classify RV size and function by using model-annotated data from written echocardiography reports. This pipeline for auto-annotation of the echocardiographic images, using a NLP model with medical reports as input, can be used to train an image-assessment model without manual annotation of images and enables fast and inexpensive expansion of the training dataset when needed.
我们创建了一个深度学习模型，该模型基于通过自然语言处理（NLP）分类的文本进行训练，以从超声心动图图像评估右心室（RV）大小和功能。我们纳入了12,684例检查以及用于文本分类的相应书面报告。在对1489份报告进行人工标注后，我们训练了一个NLP模型来对其余10,651份报告进行分类。开发了一个视图分类器，用于从超声心动图检查中选择四腔心视图或右心室重点视图（n = 539）。最终模型是两个图像分类模型，它们基于人工标注和NLP模型的预测标签以及相应的超声心动图视图进行训练，以评估右心室功能（训练集n = 11,008）和大小（训练集n = 9951）。文本分类器识别右心室功能受损的灵敏度为99%，特异性为98%，识别右心室扩大的灵敏度为98%，特异性为98%。视图分类模型识别四腔心视图的准确率为92%，识别右心室重点视图的准确率为73%。图像分类模型识别右心室功能受损的灵敏度为93%，特异性为72%，识别右心室扩大的灵敏度为80%，特异性为85%；与书面报告的一致性很强（κ均为0.65）。我们的研究结果表明，可以通过使用来自超声心动图书面报告的模型标注数据来训练自动图像评估模型，以对右心室大小和功能进行分类。这种以医学报告作为输入的NLP模型对超声心动图图像进行自动标注的流程，可用于训练无需对图像进行人工标注的图像评估模型，并在需要时实现训练数据集的快速且低成本扩展。
