Chest pathology identification using deep feature selection with non-medical training

Yaniv Bar, Idit Diamant, Lior Wolf, Sivan Lieberman, Eli Konen, Hayit Greenspan*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

42 Scopus citations


We demonstrate the feasibility of detecting pathology in chest X-rays using deep learning approaches based on non-medical learning. Convolutional neural networks (CNN) learn higher level image representations. In this work, we explore the features extracted from layers of the CNN along with a set of classical features, including GIST and bag-of-words. We show results of classification using each feature set as well as fusing among the features. Finally, we perform feature selection on the collection of features to show the most informative feature set for the task. Results of 0.78–0.95 AUC for various pathologies are shown on a data-set of more than 600 radiographs. This study shows the strength and robustness of the CNN features. We conclude that deep learning with large-scale non- medical image databases may be a good substitute, or addition to domain-specific representations which are yet to be available for general medical image recognition tasks.

Original languageEnglish
Pages (from-to)259-263
Number of pages5
JournalComputer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization
Issue number3
StatePublished - 4 May 2018


FundersFunder number
Intel Collaboration Research Institute for Computational Intelligence


    • CNN
    • Radiography
    • chest X-rays
    • computer-aided diagnosis
    • deep learning
    • feature selection


    Dive into the research topics of 'Chest pathology identification using deep feature selection with non-medical training'. Together they form a unique fingerprint.

    Cite this