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

Abstract

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.

Keywords:

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

Notes

No potential conflict of interest was reported by the authors.

Additional information

Funding

Dr. Greenspan Lab is funded in part for Deep Learning in Medical Imaging by the INTEL Collaborative Research Institute for Computational Intelligence (ICRI-CI).