{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T22:13:38Z","timestamp":1757456018582,"version":"3.37.3"},"reference-count":37,"publisher":"Wiley","license":[{"start":{"date-parts":[[2021,5,17]],"date-time":"2021-05-17T00:00:00Z","timestamp":1621209600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"STPF","award":["2019H0016","ZQN-PY411","11771160"],"award-info":[{"award-number":["2019H0016","ZQN-PY411","11771160"]}]},{"name":"Fund of HQU","award":["2019H0016","ZQN-PY411","11771160"],"award-info":[{"award-number":["2019H0016","ZQN-PY411","11771160"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2019H0016","ZQN-PY411","11771160"],"award-info":[{"award-number":["2019H0016","ZQN-PY411","11771160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computational and Mathematical Methods in Medicine"],"published-print":{"date-parts":[[2021,5,17]]},"abstract":"<jats:p>Semantic segmentation plays a crucial role in cardiac magnetic resonance (MR) image analysis. Although supervised deep learning methods have made significant performance improvements, they highly rely on a large amount of pixel-wise annotated data, which are often unavailable in clinical practices. Besides, top-performing methods usually have a vast number of parameters, which result in high computation complexity for model training and testing. This study addresses cardiac image segmentation in scenarios where few labeled data are available with a lightweight cross-consistency network named LCC-Net. Specifically, to reduce the risk of overfitting on small labeled datasets, we substitute computationally intensive standard convolutions with a lightweight module. To leverage plenty of unlabeled data, we introduce extreme consistency learning, which enforces equivariant constraints on the predictions of different perturbed versions of the input image. Cutting and mixing different training images, as an extreme perturbation on both the labeled and unlabeled data, are utilized to enhance the robust representation learning. Extensive comparisons demonstrate that the proposed model shows promising performance with high annotation- and computation-efficiency. With only two annotated subjects for model training, the LCC-Net obtains a performance gain of 14.4% in the mean Dice over the baseline U-Net trained from scratch.<\/jats:p>","DOI":"10.1155\/2021\/9960199","type":"journal-article","created":{"date-parts":[[2021,5,17]],"date-time":"2021-05-17T23:20:09Z","timestamp":1621293609000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["LCC-Net: A Lightweight Cross-Consistency Network for Semisupervised Cardiac MR Image Segmentation"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1564-1049","authenticated-orcid":true,"given":"Lai","family":"Song","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Huaqiao University, Xiamen 361021, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3849-6753","authenticated-orcid":true,"given":"Jiajin","family":"Yi","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Huaqiao University, Xiamen 361021, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1797-0762","authenticated-orcid":true,"given":"Jialin","family":"Peng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Huaqiao University, Xiamen 361021, China"},{"name":"Xiamen Key Laboratory of Computer Vision and Pattern Recognition, Huaqiao University, Xiamen 361021, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation","author":"J. Long","key":"1"},{"first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"O. Ronneberger","key":"2"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2020.00025"},{"key":"4","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume-title":"Workshop on Challenges in Representation Learning","author":"D.-H. Lee","year":"2013"},{"volume-title":"Semi-Supervised Learning by Entropy Minimization","year":"2005","author":"Y. Grandvalet","key":"5"},{"first-page":"12674","article-title":"Semi-supervised semantic segmentation with cross-consistency training","author":"Y. Ouali","key":"6"},{"first-page":"542","article-title":"Semi-supervised learning","author":"O. Chapelle","key":"7"},{"volume-title":"Semi-Supervised Learning with Ladder Networks","year":"2015","author":"A. Rasmus","key":"8"},{"volume-title":"Mean Teachers Are Better Role Models: Weight-Averaged Consistency Targets Improve Semi-Supervised Deep Learning Results","year":"2017","author":"A. Tarvainen","key":"9"},{"article-title":"Temporal ensembling for semi-supervised learning","year":"2016","author":"S. Laine","key":"10"},{"first-page":"1580","article-title":"Ghostnet: more features from cheap operations","author":"K. Han","key":"11"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2837502"},{"first-page":"632","article-title":"Cardiac MRI segmentation with strong anatomical guarantees","author":"N. Painchaud","key":"13"},{"author":"D. P. Kingma","key":"14","article-title":"Auto-encoding variational bayes"},{"key":"15","first-page":"140","article-title":"Densely Connected Fully Convolutional Network for Short-Axis Cardiac Cine MR Image Segmentation and Heart Diagnosis Using Random Forest","volume-title":"International Workshop on Statistical Atlases and Computational Models of the Heart","author":"M. Khened","year":"2017"},{"first-page":"82","article-title":"Densenet: densely connected convolutional networks","author":"G. Huang","key":"16"},{"key":"17","first-page":"152","article-title":"Class-Balanced Deep Neural Network for Automatic Ventricular Structure Segmentation","volume-title":"International Workshop on Statistical Atlases and Computational Models of the Heart","author":"X. Yang","year":"2017"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3013351"},{"key":"19","first-page":"120","article-title":"Automatic Cardiac Disease Assessment on Cine-MRI via Time-Series Segmentation and Domain Specific Features","volume-title":"International Workshop on Statistical Atlases and Computational Models of the Heart","author":"F. Isensee","year":"2017"},{"author":"T. N. Kipf","key":"20","article-title":"Semi-supervised classification with graph convolutional networks"},{"author":"B. Liu","key":"21","article-title":"Deep metric transfer for label propagation with limited annotated data"},{"first-page":"605","article-title":"Uncertainty-aware self-ensembling model for semi-supervised 3d left atrium segmentation","author":"L. Yu","key":"22"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"article-title":"Adversarial learning for semi-supervised semantic segmentation","year":"2018","author":"W.-C. Hung","key":"24"},{"first-page":"370","article-title":"Asdnet: Attention based semi-supervised deep networks for medical image segmentation","author":"D. Nie","key":"25"},{"issue":"8","key":"26","doi-asserted-by":"crossref","first-page":"1979","DOI":"10.1109\/TPAMI.2018.2858821","article-title":"Virtual adversarial training: a regularization method for supervised and semi-supervised learning","volume":"41","author":"T. Miyato","year":"2019","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"first-page":"810","article-title":"Semi-supervised medical image segmentation via learning consistency under transformations","author":"G. Bortsova","key":"27"},{"article-title":"mixup: beyond empirical risk minimization","year":"2017","author":"H. Zhang","key":"28"},{"first-page":"6023","article-title":"Cutmix: regularization strategy to train strong classifiers with localizable features","author":"S. Yun","key":"29"},{"article-title":"Yolov4: optimal speed and accuracy of object detection","year":"2020","author":"A. Bochkovskiy","key":"30"},{"article-title":"Consistency regularization and cutmix for semi-supervised semantic segmentation","year":"2019","author":"G. French","key":"31"},{"first-page":"1251","article-title":"Xception: deep learning with depthwise separable convolutions","author":"F. Chollet","key":"32"},{"key":"33","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"A. Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"first-page":"4373","article-title":"Interleaved group convolutions","author":"T. Zhang","key":"34"},{"article-title":"Mobilenets: efficient convolutional neural networks for mobile vision applications","year":"2017","author":"A. G. Howard","key":"35"},{"first-page":"6848","article-title":"Shufflenet: an extremely efficient convolutional neural network for mobile devices","author":"X. Zhang","key":"36"},{"author":"A. Paszke","key":"37","article-title":"Automatic differentiation in pytorch"}],"container-title":["Computational and Mathematical Methods in Medicine"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cmmm\/2021\/9960199.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cmmm\/2021\/9960199.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cmmm\/2021\/9960199.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,17]],"date-time":"2021-05-17T23:20:23Z","timestamp":1621293623000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/cmmm\/2021\/9960199\/"}},"subtitle":[],"editor":[{"given":"Yuankai","family":"Huo","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,5,17]]},"references-count":37,"alternative-id":["9960199","9960199"],"URL":"https:\/\/doi.org\/10.1155\/2021\/9960199","relation":{},"ISSN":["1748-6718","1748-670X"],"issn-type":[{"type":"electronic","value":"1748-6718"},{"type":"print","value":"1748-670X"}],"subject":[],"published":{"date-parts":[[2021,5,17]]}}}