Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/25717
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lei, T | - |
dc.contributor.author | Zhang, D | - |
dc.contributor.author | Du, X | - |
dc.contributor.author | Wang, X | - |
dc.contributor.author | Wan, Y | - |
dc.contributor.author | Nandi, AK | - |
dc.date.accessioned | 2023-01-04T18:07:01Z | - |
dc.date.available | 2023-01-04T18:07:01Z | - |
dc.date.issued | 2022-11-30 | - |
dc.identifier | ORCID iDs: Tao Lei https://orcid.org/0000-0002-2104-9298; Xiaogang Du https://orcid.org/0000-0002-0612-6064 ; Xuan Wang https://orcid.org/0000-0002-0842-6511; Asoke K. Nandi https://orcid.org/0000-0001-6248-2875. | - |
dc.identifier.citation | Lei, T. et al. (2022) 'Semi-supervised medical image segmentation using adversarial consistency learning and dynamic convolution network', IEEE Transactions on Medical Imaging, 42 (5), pp. 1265 - 1277. doi: 10.1109/TMI.2022.3225687. | en_US |
dc.identifier.issn | 0278-0062 | - |
dc.identifier.uri | https://bura.brunel.ac.uk/handle/2438/25717 | - |
dc.description.abstract | © Copyright The Authors 2022. Popular semi-supervised medical image segmentation networks often suffer from error supervision from unlabeled data since they usually use consistency learning under different data perturbations to regularize model training. These networks ignore the relationship between labeled and unlabeled data, and only compute single pixel-level consistency leading to uncertain prediction results. Besides, these networks often require a large number of parameters since their backbone networks are designed depending on supervised image segmentation tasks. Moreover, these networks often face a high over-fitting risk since a small number of training samples are popular for semi-supervised image segmentation. To address the above problems, in this paper, we propose a novel adversarial self-ensembling network using dynamic convolution (ASE-Net) for semi-supervised medical image segmentation. First, we use an adversarial consistency training strategy (ACTS) that employs two discriminators based on consistency learning to obtain prior relationships between labeled and unlabeled data. The ACTS can simultaneously compute pixel-level and image-level consistency of unlabeled data under different data perturbations to improve the prediction quality of labels. Second, we design a dynamic convolution-based bidirectional attention component (DyBAC) that can be embedded in any segmentation network, aiming at adaptively adjusting the weights of ASE-Net based on the structural information of input samples. This component effectively improves the feature representation ability of ASE-Net and reduces the overfitting risk of the network. The proposed ASE-Net has been extensively tested on three publicly available datasets, and experiments indicate that ASE-Net is superior to state-of-the-art networks, and reduces computational costs and memory overhead. The code is available at: https://github.com/SUST-reynole/ASE-Net. | en_US |
dc.description.sponsorship | 10.13039/501100001809-National Natural Science Foundation of China (Grant Number: 62271296, 61871259 and 61861024); 10.13039/501100017596-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); Shaanxi Joint Laboratory of Artificial Intelligence (Grant Number: 2020SS-03). | en_US |
dc.format.extent | 1265 - 1277 | - |
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 Authors 2022. Published by IEEE. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/ | - |
dc.rights.uri | https://creativecommons.org/licenses/by-nc-nd/4.0/ | - |
dc.subject | semi-supervised learning | en_US |
dc.subject | medical image | en_US |
dc.subject | segmentation | en_US |
dc.subject | dynamic convolution | en_US |
dc.subject | adversarial learning | en_US |
dc.title | Semi-supervised medical image segmentation using adversarial consistency learning and dynamic convolution network | en_US |
dc.type | Article | en_US |
dc.identifier.doi | https://doi.org/10.1109/TMI.2022.3225687 | - |
dc.relation.isPartOf | IEEE Transactions on Medical Imaging | - |
pubs.issue | 5 | - |
pubs.publication-status | Published | - |
pubs.volume | 42 | - |
dc.identifier.eissn | 1558-254X | - |
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 Authors 2022. Published by IEEE. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/ | 3.64 MB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License