Chest pathology identification using deep feature selection with non-medical training
- 4 May 2016
- journal article
- research article
- Published by Taylor & Francis in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
- Vol. 6 (3) , 259-263
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
This publication has 7 references indexed in Scilit:
- Chest pathology detection using deep learning with non-medical training2015
- Deep Learning: Methods and ApplicationsFoundations and Trends® in Signal Processing, 2014
- Deep Learning Based Imaging Data Completion for Improved Brain Disease Diagnosis2014
- Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks2013
- X-ray Categorization and Retrieval on the Organ and Pathology Level, Using Patch-Based Visual WordsIEEE Transactions on Medical Imaging, 2010
- Computer-aided diagnosis in chest radiography: Beyond nodulesEuropean Journal of Radiology, 2009
- Modeling the Shape of the Scene: A Holistic Representation of the Spatial EnvelopeInternational Journal of Computer Vision, 2001