Lei, T., Sun, R., Du, X., Fu, H., Zhang, C., & Nandi, A. K. (2023). SGU-Net: Shape-Guided Ultralight Network for Abdominal Image Segmentation. IEEE Journal of Biomedical and Health Informatics, 27(3), 1431–1442. https://doi.org/10.1109/jbhi.2023.3238183
Abstract:
Convolutional neural networks (CNNs) have achieved significant success in medical image segmentation. However, they also suffer from the requirement of a large number of parameters, leading to a difficulty of deploying CNNs to low-source hardwares, e.g., embedded systems and mobile devices. Although some compacted or small memory-hungry models have been reported, most of them may cause degradation in segmentation accuracy. To address this issue, we propose a shape-guided ultralight network (SGU-Net) with extremely low computational costs. The proposed SGU-Net includes two main contributions: it first presents an ultralight convolution that is able to implement double separable convolutions simultaneously, i.e., asymmetric convolution and depthwise separable convolution. The proposed ultralight convolution not only effectively reduces the number of parameters but also enhances the robustness of SGU-Net. Secondly, our SGU-Net employs an additional adversarial shape-constraint to let the network learn shape representation of targets, which can significantly improve the segmentation accuracy for abdomen medical images using self-supervision. The SGU-Net is extensively tested on four public benchmark datasets, LiTS, CHAOS, NIH-TCIA and 3Dircbdb. Experimental results show that SGU-Net achieves higher segmentation accuracy using lower memory costs, and outperforms state-of-the-art networks. Moreover, we apply our ultralight convolution into a 3D volume segmentation network, which obtains a comparable performance with fewer parameters and memory usage.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - Central Research Fund
Grant Reference no. : NA
This research / project is supported by the AISG - Tech Challenge Funding
Grant Reference no. : AISG2-TC-2021-003
This work was supported in part by the National Natural Science Foundation of China under Grants 62271296, 61871259, and 61861024, in part by the Natural Science Basic Research Program of Shaanxi under Grant 2021JC-47, in part by the Key Research and Development Program of Shaanxi under Grants 2022GY-436 and 2021ZDLGY08-07, in part by the Natural Science Basic Research Program of Shaanxi under Grants 2022JQ-634 and 2022JQ-018, in part by the Shaanxi Joint Laboratory of Artificial Intelligence under Grant 2020SS-03