{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:11:58Z","timestamp":1775074318450,"version":"3.50.1"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T00:00:00Z","timestamp":1669075200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Cardiac computed tomography angiography (CTA) is an emerging imaging modality for assessing coronary artery as well as various cardiovascular structures. Recently, deep learning (DL) methods have been successfully applied to many applications of medical image analysis including cardiac CTA structure segmentation. However, DL requires a large amounts of data and high-quality labels for training which can be burdensome to obtain due to its labor-intensive nature. In this study, we aim to develop a fully automatic artificial intelligence (AI) system, named DeepHeartCT, for accurate and rapid cardiac CTA segmentation based on DL. The proposed system was trained using a large clinical dataset with computer-generated labels to segment various cardiovascular structures including left and right ventricles (LV, RV), left and right atria (LA, RA), and LV myocardium (LVM). This new system was trained directly using high-quality computer labels generated from our previously developed multi-atlas based AI system. In addition, a reverse ranking strategy was proposed to assess the segmentation quality in the absence of manual reference labels. This strategy allowed the new framework to assemble optimal computer-generated labels from a large dataset for effective training of a deep convolutional neural network (CNN). A large clinical cardiac CTA studies (<jats:italic>n<\/jats:italic> = 1,064) were used to train and validate our framework. The trained model was then tested on another independent dataset with manual labels (<jats:italic>n<\/jats:italic> = 60). The Dice score, Hausdorff distance and mean surface distance were used to quantify the segmentation accuracy. The proposed DeepHeartCT framework yields a high median Dice score of 0.90 [interquartile range (IQR), 0.90\u20130.91], a low median Hausdorff distance of 7 mm (IQR, 4\u201315 mm) and a low mean surface distance of 0.80 mm (IQR, 0.57\u20131.29 mm) across all segmented structures. An additional experiment was conducted to evaluate the proposed DL-based AI framework trained with a small vs. large dataset. The results show our framework also performed well when trained on a small optimal training dataset (<jats:italic>n<\/jats:italic> = 110) with a significantly reduced training time. These results demonstrated that the proposed DeepHeartCT framework provides accurate and rapid cardiac CTA segmentation that can be readily generalized for handling large-scale medical imaging applications.<\/jats:p>","DOI":"10.3389\/frai.2022.1059007","type":"journal-article","created":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T09:07:18Z","timestamp":1677229638000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["DeepHeartCT: A fully automatic artificial intelligence hybrid framework based on convolutional neural network and multi-atlas segmentation for multi-structure cardiac computed tomography angiography image segmentation"],"prefix":"10.3389","volume":"5","author":[{"given":"Vy","family":"Bui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li-Yueh","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin-Ching","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"An-Yu","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Loc","family":"Tran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sujata M.","family":"Shanbhag","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wunan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nehal N.","family":"Mehta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcus Y.","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2022,11,22]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","article-title":"SLIC superpixels compared to state-of-the-art superpixel methods","volume":"34","author":"Achanta","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1163","DOI":"10.1016\/j.jcmg.2019.08.025","article-title":"Identification and quantification of cardiovascular structures from CCTA: an end-to-end, rapid, pixel-wise, deep-learning method","volume":"13","author":"Baskaran","year":"2020","journal-title":"JACC Cardiovasc Imaging"},{"key":"B3","doi-asserted-by":"crossref","first-page":"1352","DOI":"10.1109\/ISBI.2018.8363822","article-title":"\u201cAn automatic random walk based method for 3D segmentation of the heart in cardiac computed tomography images,\u201d","author":"Bui","year":"2018","journal-title":"IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.104019","article-title":"Improving multi-atlas cardiac structure segmentation of computed tomography angiography: a performance evaluation based on a heterogeneous dataset","author":"Bui","year":"","journal-title":"Comput. Biol. Med"},{"key":"B5","doi-asserted-by":"publisher","first-page":"16187","DOI":"10.1109\/ACCESS.2020.2966985","article-title":"Simultaneous multi-structure segmentation of the heart and peripheral tissues in contrast enhanced cardiac computed tomography angiography","volume":"8","author":"Bui","year":"","journal-title":"IEEE Access"},{"key":"B6","first-page":"424","article-title":"\u201c3D U-net: learning dense volumetric segmentation from sparse annotation,\u201d","author":"\u00c7i\u00e7ek","year":"2016","journal-title":"Medical Image Computing and Computer-Assisted Intervention \u2013MICCAI"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2020.101764","article-title":"CAB U-Net: an end-to-end category attention boosting algorithm for segmentation","author":"Ding","year":"2020","journal-title":"Comput. Med. Imaging Graph"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1768","DOI":"10.1109\/TPAMI.2006.233","article-title":"Random walks for image segmentation","volume":"28","author":"Grady","year":"2006","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B9","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1007\/s13239-020-00494-8","article-title":"Overview of the whole heart and heart chamber segmentation methods","volume":"11","author":"Habijan","year":"2020","journal-title":"Cardiovasc. Eng. Technol"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.1109\/TMI.2013.2246577","article-title":"MRF-based deformable registration and ventilation estimation of lung CT","volume":"32","author":"Heinrich","year":"2013","journal-title":"IEEE Trans. Med Imaging"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101759","article-title":"Deep learning with noisy labels: exploring techniques and remedies in medical image analysis","author":"Karimi","year":"2020","journal-title":"Med. Image Anal"},{"key":"B12","article-title":"\u201cHashing-based atlas ranking and selection for multiple-atlas segmentation,\u201d","author":"Katouzian","year":"2018","journal-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI. Lecture Notes in Computer Science, Vol. 11073"},{"key":"B13","article-title":"\u201cAdam: a method for stochastic optimization,\u201d","author":"Kingma","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"B14","doi-asserted-by":"publisher","first-page":"6279","DOI":"10.1118\/1.3512795","article-title":"Evaluation of a multi-atlas based method for segmentation of cardiac CTA data: a large-scale, multicenter, and multivendor study","volume":"37","author":"Kiri\u015fli","year":"2010","journal-title":"Med Phys"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102222","article-title":"A deep-learning approach for direct whole-heart mesh reconstruction","author":"Kong","year":"2021","journal-title":"Med. Image Anal"},{"key":"B16","article-title":"\u201cDual-teacher: integrating intra-domain and inter-domain teachers for annotation-efficient cardiac segmentation,\u201d","author":"Li","year":"2020","journal-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI. Lecture Notes in Computer Science, Vol. 12261"},{"key":"B17","doi-asserted-by":"publisher","first-page":"2771","DOI":"10.1109\/TMI.2020.3038828","article-title":"Dual-teacher++: exploiting intra-domain and inter-domain knowledge with reliable transfer for cardiac segmentation","volume":"40","author":"Li","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B18","doi-asserted-by":"publisher","first-page":"83628","DOI":"10.1109\/ACCESS.2019.2923318","article-title":"Automatic whole heart segmentation using a two-stage U-net framework and an adaptive threshold window","volume":"7","author":"Liu","year":"2019","journal-title":"IEEE Access"},{"key":"B19","article-title":"\u201cAutomatic differentiation in pytorch,\u201d","author":"Paszke","year":"2017","journal-title":"Neural Information Processing Systems (NIPS) Workshop"},{"key":"B20","article-title":"\u201cMulti-label whole heart segmentation using CNNs and anatomical label configurations,\u201d","author":"Payer","year":"2017","journal-title":"Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges. STACOM. Lecture Notes in Computer Science"},{"key":"B21","article-title":"\u201cU-net: convolutional networks for biomedical image segmentation,\u201d","author":"Ronneberger","year":"2015","journal-title":"Medical Image Computing and Computer-Assisted Intervention \u2013MICCAI. Lecture Notes in Computer Science, Vol. 9351"},{"key":"B22","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1146\/annurev-bioeng-071516-044442","article-title":"Deep learning in medical image analysis","volume":"19","author":"Shen","year":"2017","journal-title":"Annu. Rev. Biomed. Eng"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1597","DOI":"10.1109\/TMI.2017.2665165","article-title":"Reverse classification accuracy: predicting segmentation performance in the absence of ground truth","volume":"36","author":"Valindria","year":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B24","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.media.2009.10.001","article-title":"Adaptive local multi-atlas segmentation: application to the heart and the caudate nucleus","volume":"14","author":"van Rikxoort","year":"2010","journal-title":"Med. Image Anal"},{"key":"B25","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.media.2018.05.008","article-title":"\u03a9-net (omega-net): fully automatic, multi-view cardiac MR detection, orientation, and segmentation with deep neural networks","volume":"48","author":"Vigneault","year":"2018","journal-title":"Med. Image. Anal"},{"key":"B26","first-page":"1","article-title":"\u201cEffective training of convolutional networks using noisy web images,\u201d","author":"Vo","year":"2015","journal-title":"13th International Workshop on Content-Based Multimedia Indexing (CBMI)"},{"key":"B27","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.compmedimag.2018.05.002","article-title":"Fast anatomy segmentation by combining coarse scale multi-atlas label fusion with fine scale corrective learning","volume":"68","author":"Wang","year":"2018","journal-title":"Comput. Med. Imaging Graph"},{"key":"B28","doi-asserted-by":"publisher","first-page":"2629","DOI":"10.1109\/TMI.2021.3053008","article-title":"Few-shot learning by a cascaded framework with shape-constrained pseudo label assessment for whole heart segmentation","volume":"40","author":"Wang","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1371","DOI":"10.1109\/TMI.2021.3140140","article-title":"Robust medical image classification from noisy labeled data with global and local representation guided co-training","volume":"41","author":"Xue","year":"2022","journal-title":"IEEE Trans. Med. Imag."},{"key":"B30","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1109\/ISBI.2014.6867896","article-title":"\u201cAutomatic left ventricle segmentation based on multiatlas registration in 4D CT images,\u201d","author":"Yang","year":"2014","journal-title":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)"},{"key":"B31","article-title":"\u201cAutomatic whole heart segmentation in CT images based on multi-atlas image registration,\u201d","author":"Yang","year":"2017","journal-title":"Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges. STACOM. Lecture Notes in Computer Science"},{"key":"B32","article-title":"\u201cHybrid loss guided convolutional networks for whole heart parsing,\u201d","author":"Yang","year":"2017","journal-title":"Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges. STACOM. Lecture Notes in Computer Science"},{"key":"B33","doi-asserted-by":"publisher","first-page":"23421","DOI":"10.1109\/ACCESS.2019.2899635","article-title":"Multi-depth fusion network for whole-heart CT image segmentation","volume":"7","author":"Ye","year":"2019","journal-title":"IEEE Access"},{"key":"B34","doi-asserted-by":"publisher","first-page":"57881","DOI":"10.1109\/ACCESS.2019.2912467","article-title":"Accurate segmentation of heart volume in CTA with landmark-based registration and fully convolutional network","volume":"7","author":"Zhao","year":"2019","journal-title":"IEEE Access"},{"key":"B35","doi-asserted-by":"publisher","first-page":"3822","DOI":"10.1118\/1.4921366","article-title":"Multiatlas whole heart segmentation of CT data using conditional entropy for atlas ranking and selection","volume":"42","author":"Zhuang","year":"2015","journal-title":"Med. Phys"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101537","article-title":"Evaluation of algorithms for multi-modality whole heart segmentation: an open-access grand challenge","author":"Zhuang","year":"2019","journal-title":"Med. Image Anal"},{"key":"B37","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/j.media.2016.02.006","article-title":"Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI","volume":"31","author":"Zhuang","year":"2016","journal-title":"Med Image Anal"},{"key":"B38","article-title":"\u201cMulti-atlas propagation whole heart segmentation from MRI and CTA using a local normalised correlation coefficient criterion,\u201d","author":"Zuluaga","year":"2013","journal-title":"Functional Imaging and Modeling of the Heart. FIMH. Lecture Notes in Computer Science, Vol. 7945"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2022.1059007\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T09:07:31Z","timestamp":1677229651000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2022.1059007\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,22]]},"references-count":38,"alternative-id":["10.3389\/frai.2022.1059007"],"URL":"https:\/\/doi.org\/10.3389\/frai.2022.1059007","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,22]]},"article-number":"1059007"}}