TY - JOUR
T1 - Joint Learning for Pneumonia Classification and Segmentation on Medical Images
AU - Liu, Shaobo
AU - Zhong, Xin
AU - Shih, Frank Y.
N1 - Publisher Copyright:
© 2021 World Scientific Publishing Company.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020
Y1 - 2020
N2 - 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.
AB - 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.
KW - Deep learning
KW - morphological neural networks
KW - pneumonia classification
KW - segmentation
KW - VGG16
UR - http://www.scopus.com/inward/record.url?scp=85097526205&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097526205&partnerID=8YFLogxK
U2 - 10.1142/S0218001421570032
DO - 10.1142/S0218001421570032
M3 - Article
AN - SCOPUS:85097526205
JO - International Journal of Pattern Recognition and Artificial Intelligence
JF - International Journal of Pattern Recognition and Artificial Intelligence
SN - 0218-0014
M1 - 2157003
ER -