Joint Learning for Pneumonia Classification and Segmentation on Medical Images
Document Type
Article
Publication Date
4-1-2021
Abstract
Chest X-ray images are notoriously difficult to analyze due to the noisy nature. Automatic identification of pneumonia on medical images has attracted intensive study recently. In this paper, a novel joint-Task architecture that can learn pneumonia classification and segmentation simultaneously is presented. Two modules, including an image preprocessing module and an attention module, are developed to improve both the classification and segmentation accuracies. Results from the experiments performed on the massive dataset of the Radiology Society of North America have confirmed its superiority over the other existing methods. The classification test accuracy is improved from 0.89 to 0.95, and the segmentation model achieves an improved mean precision result of 0.58-0.78. Finally, two weakly supervised learning methods, class-saliency map and Grad-CAM, are used to highlight the corresponding pixels or areas which have significant influence on the classification model, such that the refined segmentation can focus on the correct areas with high confidence.
Identifier
85097526205 (Scopus)
Publication Title
International Journal of Pattern Recognition and Artificial Intelligence
External Full Text Location
https://doi.org/10.1142/S0218001421570032
ISSN
02180014
Issue
5
Volume
35
Fund Ref
National Science Foundation
Recommended Citation
Liu, Shaobo; Zhong, Xin; and Shih, Frank Y., "Joint Learning for Pneumonia Classification and Segmentation on Medical Images" (2021). Faculty Publications. 4201.
https://digitalcommons.njit.edu/fac_pubs/4201