Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/27117
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lei, T | - |
dc.contributor.author | Sun, R | - |
dc.contributor.author | Du, X | - |
dc.contributor.author | Fu, H | - |
dc.contributor.author | Zhang, C | - |
dc.contributor.author | Nandi, AK | - |
dc.date.accessioned | 2023-09-03T11:04:39Z | - |
dc.date.available | 2023-09-03T11:04:39Z | - |
dc.date.issued | 2023-01-19 | - |
dc.identifier | ORCID iDs: Tao Lei https://orcid.org/0000-0002-2104-9298; Rui Sun https://orcid.org/0000-0003-4342-7103; Xiaogang Du https://orcid.org/0000-0002-9702-5524; Huazhu Fu https://orcid.org/0000-0002-9702-5524; Changqing Zhang https://orcid.org/0000-0003-1410-6650; Asoke K. Nandi https://orcid.org/0000-0001-6248-2875. | - |
dc.identifier.citation | Lei, T. et al. (2023) 'SGU-Net: Shape-Guided Ultralight Network for Abdominal Image Segmentation', IEEE Journal of Biomedical and Health Informatics, 27 (3), pp. 1431 - 1442. doi: 10.1109/JBHI.2023.3238183. | en_US |
dc.identifier.issn | 2168-2194 | - |
dc.identifier.uri | https://bura.brunel.ac.uk/handle/2438/27117 | - |
dc.description.abstract | Copyright © The Author(s) 2023. 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. | en_US |
dc.description.sponsorship | 10.13039/501100001809-National Natural Science Foundation of China (Grant Number: 62271296, 61871259 and 61861024); Natural Science Basic Research Program of Shaanxi (Grant Number: 2021JC-47); 10.13039/501100015401-Key Research and Development Projects of Shaanxi Province (Grant Number: 2022GY-436 and 2021ZDLGY08-07); Natural Science Basic Research Program of Shaanxi (Grant Number: 2022JQ-634 and 2022JQ-018); Shaanxi Joint Laboratory of Artificial Intelligence (Grant Number: 2020SS-03); Huazhu Fu's A*STAR Central Research Fund; AISG Tech Challenge Funding (Grant Number: AISG2-TC-2021-003). | en_US |
dc.format.extent | 1431 - 1442 | - |
dc.format.medium | Print-Electronic | - |
dc.language | English | - |
dc.language.iso | en_US | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | en_US |
dc.rights | Copyright © The Author(s) 2023. Published by Institute of Electrical and Electronics Engineers (IEEE). This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ | - |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | - |
dc.subject | medical image segmentation | en_US |
dc.subject | deep learning | en_US |
dc.subject | ultralight convolution | en_US |
dc.subject | adversarial shape-constraint | en_US |
dc.title | SGU-Net: Shape-Guided Ultralight Network for Abdominal Image Segmentation | en_US |
dc.type | Article | en_US |
dc.identifier.doi | https://doi.org/10.1109/JBHI.2023.3238183 | - |
dc.relation.isPartOf | IEEE Journal of Biomedical and Health Informatics | - |
pubs.issue | 3 | - |
pubs.publication-status | Published | - |
pubs.volume | 27 | - |
dc.identifier.eissn | 2168-2208 | - |
dc.rights.holder | The Author(s) | - |
Appears in Collections: | Dept of Electronic and Electrical Engineering Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
FullText.pdf | Copyright © The Author(s) 2023. Published by Institute of Electrical and Electronics Engineers (IEEE). This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ | 3.16 MB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License