Deep learning with non-medical training used for chest pathology identification

Yaniv Bar, Idit Diamant, Lior Wolf, Hayit Greenspan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


In this work, we examine the strength of deep learning approaches for pathology detection in chest radiograph data. Convolutional neural networks (CNN) deep architecture classification approaches have gained popularity due to their ability to learn mid and high level image representations. We explore the ability of a CNN to identify different types of pathologies in chest X-ray images. Moreover, since very large training sets are generally not available in the medical domain, we explore the feasibility of using a deep learning approach based on non-medical learning. We tested our algorithm on a dataset of 93 images. We use a CNN that was trained with ImageNet, a well-known large scale nonmedical image database. The best performance was achieved using a combination of features extracted from the CNN and a set of low-level features. We obtained an area under curve (AUC) of 0.93 for Right Pleural Effusion detection, 0.89 for Enlarged heart detection and 0.79 for classification between healthy and abnormal chest X-ray, where all pathologies are combined into one large class. This is a first-of-its-kind experiment that shows that deep learning with large scale non-medical image databases may be sufficient for general medical image recognition tasks.

Original languageEnglish
Title of host publicationMedical Imaging 2015
Subtitle of host publicationComputer-Aided Diagnosis
EditorsLubomir M. Hadjiiski, Lubomir M. Hadjiiski, Georgia D. Tourassi, Georgia D. Tourassi
ISBN (Electronic)9781628415049, 9781628415049
StatePublished - 2015
EventSPIE Medical Imaging Symposium 2015: Computer-Aided Diagnosis - Orlando, United States
Duration: 22 Feb 201525 Feb 2015

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
ISSN (Print)1605-7422


ConferenceSPIE Medical Imaging Symposium 2015: Computer-Aided Diagnosis
Country/TerritoryUnited States


  • Deep learning
  • chest X-rays
  • classification
  • convolutional neural networks


Dive into the research topics of 'Deep learning with non-medical training used for chest pathology identification'. Together they form a unique fingerprint.

Cite this