An Unsupervised Domain Adaptation Model Based on Multi-Level Joint Alignment for Multi-Modal Cardiac Image Segmentation
Authors: 
Jiapeng Li, Yimou Lv, Lisheng Xu, Lin QiAuthors Info & Claims
Jiapeng Li, Yimou Lv, Lisheng Xu, Lin QiAuthors Info & ClaimsAbstract
Unsupervised Domain Adaptation has greatly boosted the performance of multi-modal medical segmentation when there are only source domain labels and no labels in the target domain. Many previous work relies on Convolutional Neural Networks for distribution or instance alignment, however, the receptive field of CNN makes it overly concerned with texture and local semantic information of images, while losing the global style information and semantic information and lacking relationships between local and global semantics. In order to address these issues, we propose a two-stage, multi-level framework for unsupervised domain adaptation, which consists of an image translation network and a Transformer-based domain adaptation segmentation network, jointly aligning the data distribution in the source and target domains from the image, feature and output level through adversarial learning. Experimental results indicate that our method can achieve satisfactory results and outperform other state-of-the-art medical image segmentation methods.
References
[1]
Adam Timmis, Panos Vardas, Nick Townsend, Aleksandra Torbica, Hugo Katus, Delphine De Smedt, Chris P Gale, Aldo P Maggioni, Stefen E Petersen, Radu Huculeci, et al., European society of cardiology: cardiovascular disease statistics 2021, European Heart Journal 43 (8) (2022) 716–799.
[2]
Daniel Flores-Araiza, Francisco Lopez-Tiro, Jonathan El-Beze, Jacques Hubert, Miguel Gonzalez-Mendoza, Gilberto Ochoa-Ruiz, Christian Daul, Deep prototypical-parts ease morphological kidney stone identification and are competitively robust to photometric perturbations, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 295–304. pagesJune.
[3]
Daqiang Dong, Guanghui Fu, Jianqiang Li, Yan Pei, Yueda Chen, An unsupervised domain adaptation brain ct segmentation method across image modalities and diseases, Expert Systems with Applications 207 (2022).
[4]
Changhwa Park, Jonghyun Lee, Jaeyoon Yoo, Minhoe Hur, Sungroh Yoon, Joint contrastive learning for unsupervised domain adaptation, arXiv preprint (2020) arXiv:2006.10297.
[5]
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio, Generative adversarial networks, Communications of the ACM 63 (11) (2020) 139–144.
[6]
Guoqiang Wei, Cuiling Lan, Wenjun Zeng, Zhizheng Zhang, Zhibo Chen, Toalign: task-oriented alignment for unsupervised domain adaptation, Advances in Neural Information Processing Systems 34 (2021) 13834–13846.
[7]
Jinyu Yang, Jingjing Liu, Ning Xu, Junzhou Huang, Tvt: Transferable vision transformer for unsupervised domain adaptation, in: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 520–530. pages.
[8]
Robin Strudel, Ricardo Garcia, Ivan Laptev, Cordelia Schmid, Segmenter: Transformer for semantic segmentation, in: Proceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 7262–7272. pages.
[9]
Sulaiman Vesal, Mingxuan Gu, Ronak Kosti, Andreas Maier, Nishant Ravikumar, Adapt everywhere: Unsupervised adaptation of point-clouds and entropy minimization for multi-modal cardiac image segmentation, IEEE Transactions on Medical Imaging 40 (7) (2021) 1838–1851.
[10]
Víctor M. Campello, etc. Gkontra, Multi-centre, multi-vendor and multi-disease cardiac segmentation: The mms challenge, IEEE Transactions on Medical Imaging 40 (12) (2021) 3543–3554.
[11]
Fuping Wu, Xiahai Zhuang, Cf distance: a new domain discrepancy metric and application to explicit domain adaptation for cross-modality cardiac image segmentation, IEEE Transactions on Medical Imaging 39 (12) (2020) 4274–4285.
[12]
Chenhao Pei, Fuping Wu, Liqin Huang, Xiahai Zhuang, Disentangle domain features for cross-modality cardiac image segmentation, Medical Image Analysis 71 (2021).
[13]
Buntheng Ly, Hubert Cochet, Maxime Sermesant, Style data augmentation for robust segmentation of multi-modality cardiac mri, Statistical Atlases and Computational Models of the Heart. Multi-Sequence CMR Segmentation, CRT-EPiggy and LV Full Quantification Challenges: 10th International Workshop, STACOM 2019, Held in Conjunction with MICCAI 2019, Springer, Shenzhen, China, 2020, pp. 197–208. October 13, 2019, Revised Selected Papers 10, pages.
[14]
Cian M Scannell, Amedeo Chiribiri, and Mitko Veta. Domain-adversarial learning for multi-centre, multi-vendor, and multi-disease cardiac mr image segmentation. In Statistical Atlases and Computational Models of the Heart. M&Ms and EMIDEC Challenges: 11th International Workshop, STACOM 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4, 2020, Revised Selected Papers 11, pages 228–237. Springer, 2021.
[15]
Firas Khader, Justus Schock, Daniel Truhn, Fabian Morsbach, Christoph Haarburger, Adaptive preprocessing for generalization in cardiac mr image segmentation, Statistical Atlases and Computational Models of the Heart. M&Ms and EMIDEC Challenges: 11th International Workshop, STACOM 2020, Held in Conjunction with MICCAI 2020, Springer, Lima, Peru, 2021, pp. 269–276. October 4, 2020, Revised Selected Papers 11, pages.
[16]
Adam Carscadden, Michelle Noga, and Kumaradevan Punithakumar. A deep convolutional neural network approach for the segmentation of cardiac structures from mri sequences. In Statistical Atlases and Computational Models of the Heart. M&Ms and EMIDEC Challenges: 11th International Workshop, STACOM 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4, 2020, Revised Selected Papers 11, pages 250–258. Springer, 2021.
[17]
Olaf Ronneberger, Philipp Fischer, Thomas Brox, U-net: Convolutional networks for biomedical image segmentation, in: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Springer, Munich, Germany, 2015, pp. 234–241. October 5-9, 2015, Proceedings, Part III 18, pages.
[18]
Fabian Isensee, Paul F Jaeger, Simon AA Kohl, Jens Petersen, Klaus H Maier-Hein, nnu-net: a self-confguring method for deep learning-based biomedical image segmentation, Nature methods 18 (2) (2021) 203–211.
[19]
Yue Cao, Shigang Liu, Yali Peng, Jun Li, Denseunet: densely connected unet for electron microscopy image segmentation, IET Image Processing 14 (12) (2020) 2682–2689.
[20]
Tarun Kalluri, Manmohan Chandraker, Cluster-to-adapt: Few shot domain adaptation for semantic segmentation across disjoint labels, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 4121–4131. pagesJune.
[21]
Tarun Kalluri, Astuti Sharma, Manmohan Chandraker, Memsac: Memory augmented sample consistency for large scale domain adaptation, in: European Conference on Computer Vision, Springer, 2022, pp. 550–568. pages.
[22]
Xiahai Zhuang, Jiahang Xu, Xinzhe Luo, Chen Chen, Cheng Ouyang, Daniel Rueckert, Victor M Campello, Karim Lekadir, Sulaiman Vesal, Nishant RaviKumar, et al., Cardiac segmentation on late gadolinium enhancement mri: a benchmark study from multi-sequence cardiac mr segmentation challenge, Medical Image Analysis 81 (2022).
[23]
Mark Hamilton, Zhoutong Zhang, Bharath Hariharan, Noah Snavely, William T Freeman, Unsupervised semantic segmentation by distilling feature correspondences, arXiv preprint (2022) arXiv:2203.08414.
Index Terms
- An Unsupervised Domain Adaptation Model Based on Multi-Level Joint Alignment for Multi-Modal Cardiac Image Segmentation
Index terms have been assigned to the content through auto-classification.
Recommendations
Unsupervised domain adaptation for cross-modality liver segmentation via joint adversarial learning and self-learning
AbstractLiver segmentation on images acquired using computed tomography (CT) and magnetic resonance imaging (MRI) plays an important role in clinical management of liver diseases. Compared to MRI, CT images of liver are more abundant and ...
Highlights- An unsupervised domain adaptation method via joint adversarial learning and self-learning for medical image segmentation.
Unsupervised Domain Adaptation with Self-selected Active Learning for Cross-domain OCT Image Segmentation
Neural Information ProcessingAbstractSegmentation of optical coherence tomography (OCT) images of retinal tissue has become an important task for the diagnosis and management of eye diseases. Deep convolutional neural networks have shown great success in retinal image segmentation. ...
Unsupervised domain adaptation for the segmentation of breast tissue in mammography images
Highlights- We demonstrate the effectiveness of adversarial-based UDA for breast tissue segmentation, which has not been shown before.
AbstractBackground and Objective: Breast density refers to the proportion of glandular and fatty tissue in the breast and is recognized as a useful factor assessing breast cancer risk. Moreover, the segmentation of the high-density glandular ...
Comments
Information & Contributors
Information
Published In
Copyright © 2023.
Publisher
Elsevier Science Publishers B. V.
Netherlands
Publication History
Published: 01 January 2023
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 26 Jan 2025