Combining LSTM and DenseNet for Automatic Annotation and Classification of Chest X-Ray Images

Abstract

The chest X-ray is a simple and economical medical aid for auxiliary diagnosis and therefore hasbecomearoutineitemforresidents’physicalexaminations.Basedon40167imagesofchestradiographs and corresponding reports, we explore the abnormality classification problem of chest X-rays by taking advantage of deep learning techniques. First of all, since the radiology reports are generally templatized by theaberrantphysicalregions,weproposeanannotationmethodaccordingtotheabnormalpartintheimages. Second, building on a small number of reports that are manually annotated by professional radiologists, we employ the long short-term memory (LSTM) model to automatically annotate the remaining unlabeled data.Theresultshowsthattheprecisionvaluereaches0.88inaccuratelyannotatingimages,therecallvalue reaches 0.85, and the F1-score reaches 0.86. Finally, we classify the abnormality in the chest X-rays by training convolutional neural networks, and the results show that the average AUC value reaches 0.835.