Learning to detect chest radiographs containing pulmonary lesions using visual attention networks

Emanuele Pesce, Samuel Joseph Withey, Petros Pavlos Ypsilantis, Robert Bakewell, Vicky Goh, Giovanni Montana*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

68 Citations (Scopus)
464 Downloads (Pure)

Abstract

Machine learning approaches hold great potential for the automated detection of lung nodules on chest radiographs, but training algorithms requires very large amounts of manually annotated radiographs, which are difficult to obtain. The increasing availability of PACS (Picture Archiving and Communication System), is laying the technological foundations needed to make available large volumes of clinical data and images from hospital archives. Binary labels indicating whether a radiograph contains a pulmonary lesion can be extracted at scale, using natural language processing algorithms. In this study, we propose two novel neural networks for the detection of chest radiographs containing pulmonary lesions. Both architectures make use of a large number of weakly-labelled images combined with a smaller number of manually annotated x-rays. The annotated lesions are used during training to deliver a type of visual attention feedback informing the networks about their lesion localisation performance. The first architecture extracts saliency maps from high-level convolutional layers and compares the inferred position of a lesion against the true position when this information is available; a localisation error is then back-propagated along with the softmax classification error. The second approach consists of a recurrent attention model that learns to observe a short sequence of smaller image portions through reinforcement learning; the reward function penalises the exploration of areas, within an image, that are unlikely to contain nodules. Using a repository of over 430,000 historical chest radiographs, we present and discuss the proposed methods over related architectures that use either weakly-labelled or annotated images only.

Original languageEnglish
Pages (from-to)26-38
JournalMedical Image Analysis
Volume53
Early online date9 Jan 2019
DOIs
Publication statusPublished - Apr 2019

Keywords

  • Deep learning
  • Image classification
  • Lung cancer
  • Object localisation
  • Visual attention
  • X-rays

Fingerprint

Dive into the research topics of 'Learning to detect chest radiographs containing pulmonary lesions using visual attention networks'. Together they form a unique fingerprint.

Cite this