Pneumothorax detection in chest radiographs using convolutional neural networks

Aviel Blumenfeld; Eli Konen; Hayit Greenspan

doi:10.1117/12.2292540

27 February 2018 Pneumothorax detection in chest radiographs using convolutional neural networks

Aviel Blumenfeld, Eli Konen, Hayit Greenspan

Proceedings Volume 10575, Medical Imaging 2018: Computer-Aided Diagnosis; 1057504 (2018) https://doi.org/10.1117/12.2292540
Event: SPIE Medical Imaging, 2018, Houston, Texas, United States

Abstract

This study presents a computer assisted diagnosis system for the detection of pneumothorax (PTX) in chest radiographs based on a convolutional neural network (CNN) for pixel classification. Using a pixel classification approach allows utilization of the texture information in the local environment of each pixel while training a CNN model on millions of training patches extracted from a relatively small dataset. The proposed system uses a pre-processing step of lung field segmentation to overcome the large variability in the input images coming from a variety of imaging sources and protocols. Using a CNN classification, suspected pixel candidates are extracted within each lung segment. A postprocessing step follows to remove non-physiological suspected regions and noisy connected components. The overall percentage of suspected PTX area was used as a robust global decision for the presence of PTX in each lung. The system was trained on a set of 117 chest x-ray images with ground truth segmentations of the PTX regions. The system was tested on a set of 86 images and reached diagnosis accuracy of AUC=0.95. Overall preliminary results are promising and indicate the growing ability of CAD based systems to detect findings in medical imaging on a clinical level accuracy.

Citation Download Citation

Aviel Blumenfeld, Eli Konen, and Hayit Greenspan "Pneumothorax detection in chest radiographs using convolutional neural networks", Proc. SPIE 10575, Medical Imaging 2018: Computer-Aided Diagnosis, 1057504 (27 February 2018); https://doi.org/10.1117/12.2292540

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available