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

Autor: Samuel Joseph Withey, Giovanni Montana, Robert Bakewell, Vicky Goh, Petros-Pavlos Ypsilantis, Emanuele Pesce
Rok vydání: 2019
Předmět:
Lung Diseases
Image classification
Computer science
Radiography
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Datasets as Topic
Health Informatics
030218 nuclear medicine & medical imaging
03 medical and health sciences
0302 clinical medicine
Picture archiving and communication system
X-rays
Humans
Visual attention
Reinforcement learning
Radiology
Nuclear Medicine and imaging
Diagnosis
Computer-Assisted
Radiological and Ultrasound Technology
Artificial neural network
Contextual image classification
business.industry
Deep learning
Object localisation
Pattern recognition
Computer Graphics and Computer-Aided Design
Softmax function
Radiographic Image Interpretation
Computer-Assisted
Radiography
Thoracic
Neural Networks
Computer
Computer Vision and Pattern Recognition
Artificial intelligence
Lung cancer
business
Algorithms
030217 neurology & neurosurgery
Zdroj: Pesce, E, Joseph Withey, S, Ypsilantis, P P, Bakewell, R, Goh, V & Montana, G 2019, ' Learning to detect chest radiographs containing pulmonary lesions using visual attention networks ', Medical Image Analysis, vol. 53, pp. 26-38 . https://doi.org/10.1016/j.media.2018.12.007
ISSN: 1361-8415
DOI: 10.1016/j.media.2018.12.007
Popis: 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.
Databáze: OpenAIRE
Externí odkaz: