TY - GEN
T1 - Global-Local Framework for Medical Image Segmentation with Intra-class Imbalance Problem
AU - Zhou, Yifan
AU - Yang, Bing
AU - Lin, Xiaolu
AU - Higashita, Risa
AU - Liu, Jiang
N1 - Publisher Copyright:
© 2023 ACM.
PY - 2023/3/17
Y1 - 2023/3/17
N2 - Deep learning methods have been demonstrated effective in medical image segmentation tasks. The results are affected by data imbalance problems. The inter-class imbalance is often considered, while the intra-class imbalance is not. The intra-class imbalance usually occurs in medical images due to external influences such as noise interference and changes in camera angle, resulting in insufficient discriminative representations within classes. Deep learning methods are easy to segment regions without complex textures and varied appearances. They are susceptible to the intra-class imbalance problem in medical images. In this paper, we propose a two-stage global-local framework to solve the intra-class imbalance problem and increase segmentation accuracy. The framework consists of (1) an auxiliary task network(ATN), (2) a local patch network(LPN), and (3) a fusion module. The ATN has a shared encoder and two separate decoders that perform global segmentation and key points localization. The key points guide to generating the fuzzy patches for the LPN. The LPN focuses on challenging patches to get a more accurate result. The fusion module generates the final output according to the global and local segmentation results. Furthermore, we have performed experiments on a private iris dataset with 290 images and a public CAMUS dataset with 1800 images. Our method achieves an IoU of 0.9280 on the iris dataset and an IoU of 0.8511 on the CAMUS dataset. The results on both datasets show that our method achieves superior performance over U-Net, CE-Net, and U-Net++.
AB - Deep learning methods have been demonstrated effective in medical image segmentation tasks. The results are affected by data imbalance problems. The inter-class imbalance is often considered, while the intra-class imbalance is not. The intra-class imbalance usually occurs in medical images due to external influences such as noise interference and changes in camera angle, resulting in insufficient discriminative representations within classes. Deep learning methods are easy to segment regions without complex textures and varied appearances. They are susceptible to the intra-class imbalance problem in medical images. In this paper, we propose a two-stage global-local framework to solve the intra-class imbalance problem and increase segmentation accuracy. The framework consists of (1) an auxiliary task network(ATN), (2) a local patch network(LPN), and (3) a fusion module. The ATN has a shared encoder and two separate decoders that perform global segmentation and key points localization. The key points guide to generating the fuzzy patches for the LPN. The LPN focuses on challenging patches to get a more accurate result. The fusion module generates the final output according to the global and local segmentation results. Furthermore, we have performed experiments on a private iris dataset with 290 images and a public CAMUS dataset with 1800 images. Our method achieves an IoU of 0.9280 on the iris dataset and an IoU of 0.8511 on the CAMUS dataset. The results on both datasets show that our method achieves superior performance over U-Net, CE-Net, and U-Net++.
KW - Deep Learning
KW - Intra-class imbalance
KW - Medical image segmentation
UR - http://www.scopus.com/inward/record.url?scp=85162851354&partnerID=8YFLogxK
U2 - 10.1145/3590003.3590071
DO - 10.1145/3590003.3590071
M3 - Conference contribution
AN - SCOPUS:85162851354
T3 - ACM International Conference Proceeding Series
SP - 366
EP - 370
BT - CACML 2023 - Conference Proceedings 2023 2nd Asia Conference on Algorithms, Computing and Machine Learning
PB - Association for Computing Machinery
T2 - 2nd Asia Conference on Algorithms, Computing and Machine Learning, CACML 2023
Y2 - 17 March 2023 through 19 March 2023
ER -