{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T18:00:01Z","timestamp":1790704801704,"version":"4.1.0"},"reference-count":51,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Deep Learning (DL) has transformed cardiac image segmentation, yet its application to congenital heart disease (CHD) remains underexplored, with no prior systematic review in this emerging domain. This review evaluates current DL approaches for CHD CT segmentation, identifies best performing model architectures, assesses quality of reporting and highlights challenges for clinical implementation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>Following PRISMA guidelines, six databases: PubMed, IEEE Xplore, MDPI, Science Direct, Web of Science, and Scopus were searched (2004\u20132025). Extracted characteristics include source of dataset, ground truth labelling approach, DL architecture and evaluation methods. Reporting quality was evaluated using the Checklist for Artificial Intelligence in Medical imaging (CLAIM).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>14 studies met the inclusion criteria, reflecting the emergence of this research area. The UNet architecture and its variants dominated (8 studies). The highest reported Dice Similarity Coefficient (DSC) for cardiac structures segmentation was achieved utilising an advanced hybrid ResNet-based model (Aorta, DSC\u2009=\u20090.945). Well documented areas include the training approach (12 studies) and model description (all). Only two studies performed external validation, and two assessed inter- and intra-rater variability. No studies reported sample size determination and handing of missing data. Small vascular structures consistently underperformed compared to whole heart segmentation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Deep learning models show strong potential for CHD CT segmentation but remain limited by small datasets, inconsistent reporting and lack of clinical evaluation. Advancing this field requires multidisciplinary collaboration, standardised reporting, and integration of clinical co- design. As the first comprehensive review in this area, we provide a strong baseline for evaluating future studies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0357600","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T17:24:53Z","timestamp":1790702693000},"page":"e0357600","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning for cardiac CT segmentation for congenital heart disease: A systematic review"],"prefix":"10.1371","volume":"21","author":[{"given":"Sinling Tiffany","family":"Yu","sequence":"first","affiliation":[{"name":"Engineering for Health Research Centre, Aston University","place":["Aston Triangle, Birmingham, United Kingdom"]},{"name":"Aston Institute of Health & Neurodevelopment, Aston University","place":["Aston Triangle, Birmingham, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zahra","family":"Amini","sequence":"additional","affiliation":[{"name":"Engineering for Health Research Centre, Aston University","place":["Aston Triangle, Birmingham, United Kingdom"]},{"name":"Aston Institute of Health & Neurodevelopment, Aston University","place":["Aston Triangle, Birmingham, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shereen","family":"Fouad","sequence":"additional","affiliation":[{"name":"School of Computer Science and Digital Technologies, Aston University","place":["Aston Triangle, Birmingham, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5173-3608","authenticated-orcid":true,"given":"Jan","family":"Novak","sequence":"additional","affiliation":[{"name":"Aston Institute of Health & Neurodevelopment, Aston University","place":["Aston Triangle, Birmingham, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8894-461X","authenticated-orcid":true,"given":"Antonio","family":"Fratini","sequence":"additional","affiliation":[{"name":"Engineering for Health Research Centre, Aston University","place":["Aston Triangle, Birmingham, United Kingdom"]},{"name":"Aston Institute of Health & Neurodevelopment, Aston University","place":["Aston Triangle, Birmingham, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"key":"pone.0357600.ref001","doi-asserted-by":"crossref","first-page":"101249","DOI":"10.1016\/j.eclinm.2021.101249","article-title":"Global, regional, and national time trends in mortality for congenital heart disease, 1990\u20132019: An age-period-cohort analysis for the Global Burden of Disease 2019 study","volume":"43","author":"Z Su","year":"2022","journal-title":"eClinicalMedicine"},{"issue":"9","key":"pone.0357600.ref002","first-page":"1458","article-title":"Cardiovascular Risk Factors in Patients With Congenital Heart Disease","volume":"36","author":"J-L Bigras","year":"2020","journal-title":"Can J Cardiol"},{"issue":"1","key":"pone.0357600.ref003","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1186\/s12887-021-02997-2","article-title":"Major heart defects: the diagnostic evaluations of first-year-olds","volume":"21","author":"J Pavlicek","year":"2021","journal-title":"BMC Pediatr"},{"issue":"1","key":"pone.0357600.ref004","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1053\/j.pcsu.2013.01.004","article-title":"Low birth weight and very low birth weight neonates with congenital heart disease: timing of surgery, reasons for delaying or not delaying surgery","volume":"16","author":"VM Reddy","year":"2013","journal-title":"Semin Thorac Cardiovasc Surg Pediatr Card Surg Annu"},{"issue":"7","key":"pone.0357600.ref005","doi-asserted-by":"crossref","first-page":"3250","DOI":"10.1002\/mp.14107","article-title":"CT images with expert manual contours of thoracic cancer for benchmarking auto-segmentation accuracy","volume":"47","author":"J Yang","year":"2020","journal-title":"Med Phys"},{"issue":"10","key":"pone.0357600.ref006","doi-asserted-by":"crossref","first-page":"1034","DOI":"10.3390\/bioengineering11101034","article-title":"Advances in Medical Image Segmentation: A Comprehensive Review of Traditional, Deep Learning and Hybrid Approaches","volume":"11","author":"Y Xu","year":"2024","journal-title":"Bioengineering (Basel)"},{"key":"pone.0357600.ref007","doi-asserted-by":"crossref","DOI":"10.1186\/1532-429X-17-S1-P196","article-title":"3D printed cardiovascular models for surgical planning in complex congenital heart diseases","volume":"17","author":"I Valverde","year":"2015","journal-title":"Journal of Cardiovascular Magnetic Resonance"},{"key":"pone.0357600.ref008","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1558\/cam.28455","article-title":"Involving patients, families and medical staff in the evaluation of 3D printing models of congenital heart disease","volume":"12","author":"G Biglino","year":"2015","journal-title":"Commun Med"},{"key":"pone.0357600.ref009","article-title":"Future Proofing the Clinical Oncology Workforce","author":"TG Charlton","year":"2023","journal-title":"ScienceDirect"},{"issue":"2","key":"pone.0357600.ref010","doi-asserted-by":"crossref","DOI":"10.7861\/fhj.2021-0095","article-title":"Artificial intelligence in healthcare: transforming the practice of medicine","volume":"8","author":"J Bajwa","year":"2021","journal-title":"Future Healthc J"},{"issue":"4","key":"pone.0357600.ref011","article-title":"AI-Driven Clinical Decision Support Systems: An Ongoing Pursuit of Potential","volume":"16","author":"M Elhaddad","year":"2024","journal-title":"Cureus"},{"issue":"1","key":"pone.0357600.ref012","first-page":"83","article-title":"Intelligent oncology: The convergence of artificial intelligence and oncology","volume":"3","author":"B Lin","year":"2022","journal-title":"J Natl Cancer Cent"},{"key":"pone.0357600.ref013","doi-asserted-by":"crossref","first-page":"103627","DOI":"10.1016\/j.jbi.2020.103627","article-title":"A review on deep learning approaches in healthcare systems: Taxonomies, challenges, and open issues","volume":"113","author":"S Shamshirband","year":"2021","journal-title":"J Biomed Inform"},{"issue":"10","key":"pone.0357600.ref014","doi-asserted-by":"crossref","first-page":"1870","DOI":"10.3390\/cancers16101870","article-title":"Clinical Applications of Artificial Intelligence in Medical Imaging and Image Processing\u2014A Review","volume":"16","author":"R Obuchowicz","year":"2024","journal-title":"Cancers"},{"issue":"6","key":"pone.0357600.ref015","doi-asserted-by":"crossref","first-page":"667","DOI":"10.3390\/e23060667","article-title":"Deep Learning Methods for Heart Sounds Classification: A Systematic Review","volume":"23","author":"W Chen","year":"2021","journal-title":"Entropy (Basel)"},{"key":"pone.0357600.ref016","doi-asserted-by":"crossref","first-page":"102165","DOI":"10.1016\/j.artmed.2021.102165","article-title":"Artificial intelligence applied to support medical decisions for the automatic analysis of echocardiogram images: a systematic review","volume":"120","author":"VS de Siqueira","year":"2021","journal-title":"Artificial Intelligence in Medicine"},{"key":"pone.0357600.ref017","doi-asserted-by":"crossref","first-page":"106998","DOI":"10.1016\/j.compbiomed.2023.106998","article-title":"Automated diagnosis of cardiovascular diseases from cardiac magnetic resonance imaging using deep learning models: A review","volume":"160","author":"M Jafari","year":"2023","journal-title":"Comput Biol Med"},{"key":"pone.0357600.ref018","doi-asserted-by":"crossref","DOI":"10.3389\/fcvm.2020.00025","article-title":"Deep Learning for Cardiac Image Segmentation: A Review","volume":"7","author":"C Chen","year":"2020","journal-title":"Frontiers in Cardiovascular Medicine"},{"key":"pone.0357600.ref019","doi-asserted-by":"crossref","first-page":"1323461","DOI":"10.3389\/fcvm.2024.1323461","article-title":"Advancements in cardiac structures segmentation: a comprehensive systematic review of deep learning in CT imaging","volume":"11","author":"TN Alnasser","year":"2024","journal-title":"Front Cardiovasc Med"},{"issue":"4","key":"pone.0357600.ref020","doi-asserted-by":"crossref","DOI":"10.1148\/ryai.240300","article-title":"Checklist for Artificial Intelligence in Medical Imaging (CLAIM): 2024 Update","volume":"6","author":"AS Tejani","year":"2024","journal-title":"Radiology Artificial Intelligence"},{"issue":"8","key":"pone.0357600.ref021","doi-asserted-by":"crossref","first-page":"529","DOI":"10.7326\/0003-4819-155-8-201110180-00009","article-title":"QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies","volume":"155","author":"PF Whiting","year":"2011","journal-title":"Ann Intern Med"},{"key":"pone.0357600.ref022","article-title":"PROBAST+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods","volume":"388","author":"KGM Moons","year":"2025","journal-title":"BMJ"},{"issue":"1","key":"pone.0357600.ref023","doi-asserted-by":"crossref","first-page":"7558","DOI":"10.1038\/s41598-023-34013-1","article-title":"Graph matching and deep neural networks based whole heart and great vessel segmentation in congenital heart disease","volume":"13","author":"Z Yao","year":"2023","journal-title":"Sci Rep"},{"key":"pone.0357600.ref024","doi-asserted-by":"crossref","first-page":"100055","DOI":"10.1016\/j.ibmed.2022.100055","article-title":"Local integration of deep learning for advanced visualization in congenital heart disease surgical planning","volume":"6","author":"V Nainamalai","year":"2022","journal-title":"Intelligence-Based Medicine"},{"key":"pone.0357600.ref025","doi-asserted-by":"crossref","first-page":"101785","DOI":"10.1016\/j.compmedimag.2020.101785","article-title":"MMTLNet: Multi-Modality Transfer Learning Network with adversarial training for 3D whole heart segmentation","volume":"85","author":"X Liao","year":"2020","journal-title":"Comput Med Imaging Graph"},{"issue":"9","key":"pone.0357600.ref026","doi-asserted-by":"crossref","first-page":"3912","DOI":"10.3390\/app11093912","article-title":"Whole Heart Segmentation Using 3D FM-Pre-ResNet Encoder\u2013Decoder Based Architecture with Variational Autoencoder Regularization","volume":"11","author":"M Habijan","year":"2021","journal-title":"Applied Sciences"},{"key":"pone.0357600.ref027","doi-asserted-by":"crossref","first-page":"106074","DOI":"10.1016\/j.bspc.2024.106074","article-title":"A novel approach for multi-CHD prediction using IW-LNEF-DJRNN model based on 3D CT images","volume":"92","author":"TP Anish","year":"2024","journal-title":"Biomedical Signal Processing and Control"},{"key":"pone.0357600.ref028","doi-asserted-by":"crossref","first-page":"105782","DOI":"10.1016\/j.compbiomed.2022.105782","article-title":"Cardiac segmentation on CT Images through shape-aware contour attentions","volume":"147","author":"S Park","year":"2022","journal-title":"Comput Biol Med"},{"key":"pone.0357600.ref029","doi-asserted-by":"crossref","first-page":"101972","DOI":"10.1016\/j.cagd.2021.101972","article-title":"Binary segmentation of medical images using implicit spline representations and deep learning","volume":"85","author":"OJD Barrowclough","year":"2021","journal-title":"Computer Aided Geometric Design"},{"issue":"1","key":"pone.0357600.ref030","doi-asserted-by":"crossref","first-page":"11891","DOI":"10.1038\/s41598-025-96251-9","article-title":"A novel hybrid layer-based encoder-decoder framework for 3D segmentation in congenital heart disease","volume":"15","author":"Y Zhu","year":"2025","journal-title":"Sci Rep"},{"issue":"5","key":"pone.0357600.ref031","doi-asserted-by":"crossref","first-page":"991","DOI":"10.1007\/s11548-024-03281-1","article-title":"Double-mix pseudo-label framework: enhancing semi-supervised segmentation on category-imbalanced CT volumes","volume":"20","author":"L Zhang","year":"2025","journal-title":"Int J Comput Assist Radiol Surg"},{"issue":"8","key":"pone.0357600.ref032","doi-asserted-by":"crossref","first-page":"1597","DOI":"10.1007\/s11548-024-03182-3","article-title":"Heart and great vessels segmentation in congenital heart disease via CNN and conditioned energy function postprocessing","volume":"19","author":"J Liu","year":"2024","journal-title":"Int J Comput Assist Radiol Surg"},{"issue":"10","key":"pone.0357600.ref033","doi-asserted-by":"crossref","first-page":"7459","DOI":"10.1109\/JBHI.2025.3584074","article-title":"Whole heart segmentation based on 3D contour-guided multi-head attention network from CT and MRI images","volume":"29","author":"F Li","year":"2025","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"pone.0357600.ref034","doi-asserted-by":"crossref","first-page":"102163","DOI":"10.1016\/j.compmedimag.2022.102163","article-title":"Anatomical attention-based prediction of postoperative pulmonary venous obstruction via CTA images","volume":"103","author":"Y Pei","year":"2023","journal-title":"Comput Med Imaging Graph"},{"key":"pone.0357600.ref035","first-page":"100127","article-title":"Automated heart segmentation using U-Net in pediatric cardiac CT","volume":"18","author":"A Yoshida","year":"2021","journal-title":"Measurement: Sensors"},{"key":"pone.0357600.ref036","doi-asserted-by":"crossref","first-page":"102953","DOI":"10.1016\/j.media.2023.102953","article-title":"A clinically applicable AI system for diagnosis of congenital heart diseases based on computed tomography images","volume":"90","author":"X Xu","year":"2023","journal-title":"Med Image Anal"},{"key":"pone.0357600.ref037","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","author":"O Ronneberger","year":"2015","journal-title":"Lecture Notes in Computer Science"},{"issue":"8","key":"pone.0357600.ref038","doi-asserted-by":"crossref","first-page":"1597","DOI":"10.1007\/s11548-024-03182-3","article-title":"Heart and great vessels segmentation in congenital heart disease via CNN and conditioned energy function postprocessing","volume":"19","author":"J Liu","year":"2024","journal-title":"Int J Comput Assist Radiol Surg"},{"issue":"3","key":"pone.0357600.ref039","article-title":"Role of Artificial Intelligence in Congenital Heart Disease and Interventions","volume":"4","author":"DB Holt","year":"2025","journal-title":"Journal of the Society for Cardiovascular Angiography & Interventions"},{"key":"pone.0357600.ref040","first-page":"359","article-title":"What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use.","author":"S Tonekaboni","year":"2019","journal-title":"proceedingsmlrpress"},{"key":"pone.0357600.ref041","doi-asserted-by":"crossref","DOI":"10.1186\/s12911-024-02582-4","article-title":"Medical-informed machine learning: integrating prior knowledge into medical decision systems","volume":"24","author":"C Sirocchi","year":"2024","journal-title":"BMC Medical Informatics and Decision Making"},{"key":"pone.0357600.ref042","doi-asserted-by":"crossref","unstructured":"Fouad S, Hakobyan L, Kavakli-Thorne M, Atkins S, Fratini A, Bhatia B. CHERIE: User-Centred Development of an XAI System for Chest Radiology through Co-Design. 2024.","DOI":"10.14236\/ewic\/BCSHCI2024.19"},{"key":"pone.0357600.ref043","article-title":"Impact of Gold-Standard Label Errors on Evaluating Performance of Deep Learning Models in Diabetic Retinopathy Screening: Nationwide Real-World Validation Study","volume":"26","author":"Y Wang","year":"2024","journal-title":"J Med Internet Res"},{"issue":"2","key":"pone.0357600.ref044","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1167\/tvst.9.2.7","article-title":"A Clinician\u2019s Guide to Artificial Intelligence: How to Critically Appraise Machine Learning Studies","volume":"9","author":"L Faes","year":"2020","journal-title":"Transl Vis Sci Technol"},{"issue":"9","key":"pone.0357600.ref045","article-title":"Inconsistency in the use of the term \u201cvalidation\u201d in studies reporting the performance of deep learning algorithms in providing diagnosis from medical imaging","volume":"15","author":"DW Kim","year":"2020","journal-title":"PLoS One"},{"key":"pone.0357600.ref046","article-title":"Understanding the Difference between Training, Test, and Validation Sets in Machine Learning","author":"AL Duca","year":"2023","journal-title":"syntax-error"},{"issue":"10","key":"pone.0357600.ref047","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0308758","article-title":"Evaluating explainable artificial intelligence (XAI) techniques in chest radiology imaging through a human-centered lens","volume":"19","author":"E Ihongbe","year":"2024","journal-title":"PLOS ONE"},{"key":"pone.0357600.ref048","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103293","article-title":"SDF4CHD: Generative modeling of cardiac anatomies with congenital heart defects","volume":"97","author":"F Kong","year":"2024","journal-title":"Medical Image Analysis"},{"key":"pone.0357600.ref049","doi-asserted-by":"crossref","first-page":"101537","DOI":"10.1016\/j.media.2019.101537","article-title":"Evaluation of algorithms for Multi-Modality Whole Heart Segmentation: An open-access grand challenge","volume":"58","author":"X Zhuang","year":"2019","journal-title":"Med Image Anal"},{"key":"pone.0357600.ref050","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1007\/978-3-030-32245-8_53","article-title":"Whole heart and great vessel segmentation in congenital heart disease using deep neural networks and graph matching","author":"X Xu","year":"2019","journal-title":"Lecture Notes in Computer Science"},{"key":"pone.0357600.ref051","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/978-3-030-59719-1_8","article-title":"ImageCHD: A 3D Computed Tomography Image Dataset for Classification of Congenital Heart Disease","author":"X Xu","year":"2020","journal-title":"Lecture Notes in Computer Science"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0357600","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T17:25:03Z","timestamp":1790702703000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0357600"}},"subtitle":[],"editor":[{"given":"Francesco","family":"Bardozzo","sequence":"first","affiliation":[{"name":"University of Salerno: Universita degli Studi di Salerno","place":["ITALY"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":51,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,29]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0357600","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,29]]}}}