Combining LSTM and DenseNet for Automatic Annotation and Classification of Chest X-Ray Images
Open Access
- 3 June 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 74181-74189
Abstract
The chest X-ray is a simple and economical medical aid for auxiliary diagnosis, therefore has becomes a routine item for residents’ physical examinations. Based on 40,167 images of chest radiographs and corresponding reports, we explore the abnormality classification problem of chest X-rays by taking the advantage of deep learning techniques. First of all, since the radiology reports are generally templatized by the aberrant physical regions, we propose an annotation method according to the abnormal part in the images. Secondly, building on a small number of reports which are manually annotated by professional radiologists, we employ the Long-Short Term Memory (LSTM) model to automatically annotate the remaining unlabeled data. The result shows that the precision value reaches 0.88 in accurately annotating images, the recall value reaches 0.85, and the F1-score reaches 0.86. Finally, we classify the abnormality in chest X-rays by training convolutional neural networks, and the results show that the average AUC value reaches 0.835.Keywords
Funding Information
- Science and Technology Commission of Shanghai Municipality (16511102800)
- Fundamental Research Funds for the Central Universities (22120180117)
This publication has 18 references indexed in Scilit:
- Annotation of Chest Radiology Reports for Indexing and RetrievalLecture Notes in Computer Science, 2015
- Understanding and Confronting Our Mistakes: The Epidemiology of Error in Radiology and Strategies for Error ReductionRadioGraphics, 2015
- Preparing a collection of radiology examinations for distribution and retrievalJournal of the American Medical Informatics Association, 2015
- Convolutional Neural Networks for Sentence Classification2014
- Lung Segmentation in Chest Radiographs Using Anatomical Atlases With Nonrigid RegistrationIEEE Transactions on Medical Imaging, 2013
- Automatic Localization and Identification of Vertebrae in Arbitrary Field-of-View CT Scans2012
- A guided tour to approximate string matchingACM Computing Surveys, 2001
- Long Short-Term MemoryNeural Computation, 1997
- The DICOM standardThe International Journal of Cardiovascular Imaging, 1995
- Algorithm AS 136: A K-Means Clustering AlgorithmJournal of the Royal Statistical Society Series C: Applied Statistics, 1979