{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T17:24:15Z","timestamp":1771262655674,"version":"3.50.1"},"reference-count":19,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2024,8,21]],"date-time":"2024-08-21T00:00:00Z","timestamp":1724198400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2020M2D9A1093989"],"award-info":[{"award-number":["2020M2D9A1093989"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2024,11]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Multi\u2010organ segmentation is a critical task in medical imaging, with wide\u2010ranging applications in both clinical practice and research. Accurate delineation of organs from high\u2010resolution 3D medical images, such as CT scans, is essential for radiation therapy planning, enhancing treatment outcomes, and minimizing radiation toxicity risks. Additionally, it plays a pivotal role in quantitative image analysis, supporting various medical research studies. Despite its significance, manual segmentation of multiple organs from 3D images is labor\u2010intensive and prone to low reproducibility due to high interoperator variability. Recent advancements in deep learning have led to several automated segmentation methods, yet many rely heavily on labeled data and human anatomy expertise.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>In this study, our primary objective is to address the limitations of existing semi\u2010supervised learning (SSL) methods for abdominal multi\u2010organ segmentation. We aim to introduce a novel SSL approach that leverages unlabeled data to enhance the performance of deep neural networks in segmenting abdominal organs. Specifically, we propose a method that incorporates a redrawing network into the segmentation process to correct errors and improve accuracy.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Our proposed method comprises three interconnected neural networks: a segmentation network for image segmentation, a teacher network for consistency regularization, and a redrawing network for object redrawing. During training, the segmentation network undergoes two rounds of optimization: basic training and readjustment. We adopt the Mean\u2010Teacher model as our baseline SSL approach, utilizing labeled and unlabeled data. However, recognizing significant errors in abdominal multi\u2010organ segmentation using this method alone, we introduce the redrawing network to generate redrawn images based on CT scans, preserving original anatomical information. Our approach is grounded in the generative process hypothesis, encompassing segmentation, drawing, and assembling stages. Correct segmentation is crucial for generating accurate images. In the basic training phase, the segmentation network is trained using both labeled and unlabeled data, incorporating consistency learning to ensure consistent predictions before and after perturbations. The readjustment phase focuses on reducing segmentation errors by optimizing the segmentation network parameters based on the differences between redrawn and original CT images.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We evaluated our method using two publicly available datasets: the beyond the cranial vault (BTCV) segmentation dataset (training: 44, validation: 6) and the abdominal multi\u2010organ segmentation (AMOS) challenge 2022 dataset (training:138, validation:16). Our results were compared with state\u2010of\u2010the\u2010art SSL methods, including MT and dual\u2010task consistency (DTC), using the Dice similarity coefficient (DSC) as an accuracy metric. On both datasets, our proposed SSL method consistently outperformed other methods, including supervised learning, achieving superior segmentation performance for various abdominal organs. These findings demonstrate the effectiveness of our approach, even with a limited number of labeled data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Our novel semi\u2010supervised learning approach for abdominal multi\u2010organ segmentation addresses the challenges associated with this task. By integrating a redrawing network and leveraging unlabeled data, we achieve remarkable improvements in accuracy. Our method demonstrates superior performance compared to existing SSL and supervised learning methods. This approach holds great promise in enhancing the precision and efficiency of multi\u2010organ segmentation in medical imaging applications.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.17364","type":"journal-article","created":{"date-parts":[[2024,8,21]],"date-time":"2024-08-21T23:27:49Z","timestamp":1724282869000},"page":"8334-8347","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Semi\u2010supervised abdominal multi\u2010organ segmentation by object\u2010redrawing"],"prefix":"10.1002","volume":"51","author":[{"given":"Min Jeong","family":"Cho","sequence":"first","affiliation":[{"name":"Interdisciplinary Program in Bioengineering Seoul National University Graduate School  Seoul South Korea"},{"name":"Artificial Intelligence Institute Seoul National University  Seoul South Korea"},{"name":"Integrated Major in Innovative Medical Science Seoul National University College of Medicine  Seoul South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jae Sung","family":"Lee","sequence":"additional","affiliation":[{"name":"Interdisciplinary Program in Bioengineering Seoul National University Graduate School  Seoul South Korea"},{"name":"Artificial Intelligence Institute Seoul National University  Seoul South Korea"},{"name":"Integrated Major in Innovative Medical Science Seoul National University College of Medicine  Seoul South Korea"},{"name":"Department of Nuclear Medicine Seoul National University College of Medicine  Seoul South Korea"},{"name":"Brightonix Imaging Inc.  Seoul South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2024,8,21]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4947484"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2021.05.003"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-019-06195-8"},{"key":"e_1_2_8_5_1","article-title":"Class\u2010incremental learning for multi\u2010organ segmentation","author":"Chen J","year":"2022","journal-title":"Soc Nuclear Med"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2806309"},{"key":"e_1_2_8_7_1","doi-asserted-by":"crossref","unstructured":"ZhangJ XieY XiaY DoDNetShenC :Learning to segment multi\u2010organ and tumors from multiple partially labeled datasets.2021:1195\u20101204.","DOI":"10.1109\/CVPR46437.2021.00125"},{"key":"e_1_2_8_8_1","unstructured":"TangH LiuX HanK et\u00a0al.Spatial context\u2010aware self\u2010attention model for multi\u2010organ segmentation.2021:939\u2010949."},{"key":"e_1_2_8_9_1","unstructured":"LaineS AilaT Temporal ensembling for semi\u2010supervised learning. arXiv preprint arXiv:161002242.2016;"},{"key":"e_1_2_8_10_1","article-title":"Mean teachers are better role models: weight\u2010averaged consistency targets improve semi\u2010supervised deep learning results","volume":"30","author":"Tarvainen A","year":"2017","journal-title":"Proc Int Conf Neural Inf Process Syst"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2960224"},{"key":"e_1_2_8_12_1","doi-asserted-by":"crossref","unstructured":"LuoX ChenJ SongT WangG Semi\u2010supervised medical image segmentation through dual\u2010task consistency.2021:8801\u20108809.","DOI":"10.1609\/aaai.v35i10.17066"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00020"},{"key":"e_1_2_8_14_1","unstructured":"ChenM Arti\u00e8resT DenoyerL Unsupervised object segmentation by redrawing. Advances in neural information processing systems.2019;32"},{"key":"e_1_2_8_15_1","unstructured":"LandmanB XuZ IgelsiasJ StynerM LangerakT KleinA Miccai multi\u2010atlas labeling beyond the cranial vault\u2013workshop and challenge.2015:12."},{"key":"e_1_2_8_16_1","first-page":"36722","article-title":"Amos: a large\u2010scale abdominal multi\u2010organ benchmark for versatile medical image segmentation","volume":"35","author":"Ji Y","year":"2022","journal-title":"Proc Int Conf Neural Inf Process Syst"},{"key":"e_1_2_8_17_1","first-page":"424","volume-title":"3D U\u2010Net: Learning Dense Volumetric Segmentation from Sparse Annotation","author":"\u00c7i\u00e7ek \u00d6","year":"2016"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-40710-7"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13534-020-00179-0"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13534-020-00178-1"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.17364","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T20:02:53Z","timestamp":1733169773000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.17364"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,21]]},"references-count":19,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["10.1002\/mp.17364"],"URL":"https:\/\/doi.org\/10.1002\/mp.17364","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,21]]},"assertion":[{"value":"2024-01-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}