{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T04:17:19Z","timestamp":1773893839387,"version":"3.50.1"},"reference-count":50,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T00:00:00Z","timestamp":1768348800000},"content-version":"vor","delay-in-days":13,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Coarctation of the aorta (CoA) is a common congenital cardiovascular disorder. Severe cases may cause neonatal shock or heart failure. Accurate prenatal diagnosis is critical to reducing mortality and enabling timely medical intervention. Fetal echocardiography is widely used for prenatal CoA detection, but its diagnostic performance is limited by relatively high false\u2010positive and false\u2010negative rates. Recent advances have proposed deep learning to assist diagnosis. However, current approaches struggle to extract meaningful features from the complex distributions of fetal echocardiographic images. These limitations emphasize the urgent need for more advanced methodologies to improve diagnostic accuracy in this field.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To develop a deep learning network that effectively integrates local and global features for extracting discriminative characteristics from fetal echocardiograms, thereby enabling precise prenatal diagnosis of fetal CoA.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      This study introduces CoA\u2010Net, a multi\u2010stage deep learning network for prenatal CoA diagnosis through local\u2010global feature integration. CoA\u2010Net includes four sequential stages, each equipped with a local feature extractor and a global feature extractor to ensure comprehensive feature extraction. The local extractor adopts lightweight convolutional layers and a local attention mechanism\u2014this mechanism assigns input\u2010adaptive importance weights, allowing accurate lesion localization and detailed local feature extraction. The global extractor incorporates a sparse global attention mechanism to capture the most discriminative global features, supporting reliable contextual modeling between the aortic arch and adjacent structures. To validate CoA\u2010Net, a dataset of 488 samples (including CoA cases and healthy controls) was constructed, with five\u2010fold cross\u2010validation for train\u2010test partitioning. Extensive experiments were conducted on this dataset to evaluate model performance, using multiple state\u2010of\u2010the\u2010art deep learning classification methods. Results were also compared with clinician diagnoses. Cross\u2010validation\n                      <jats:italic>t<\/jats:italic>\n                      \u2010tests were used to determine significant differences between CoA\u2010Net and other approaches, and the Benjamini\u2013Hochberg False Discovery Rate (BH\u2010FDR) method was applied to correct for multiple comparisons when analyzing significant results.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      CoA\u2010Net outperforms other state\u2010of\u2010the\u2010art networks, with statistically significant improvements in balanced accuracy, F1 score, and Matthews correlation coefficient (MCC) (\n                      <jats:italic>p<\/jats:italic>\n                      \u00a0&lt;\u00a00.05 after BH\u2010FDR correction) and a large effect size (Effect Size\u00a0&gt;\u00a00.8). This indicates CoA\u2010Net not only has statistical superiority but also delivers substantial, perceptible improvements in CoA diagnostic accuracy. Specifically, CoA\u2010Net achieves 82.63% balanced accuracy, 68.81% F1 score, 69.73% MCC, and 0.867 area under the curve (AUC). To further evaluate the clinical utility of CoA\u2010Net, we compared its performance against diagnoses made by experienced clinicians. The clinicians achieved a balanced accuracy of 77.11%, an F1 score of 53.76%, an MCC of 44.54%, and an AUC of 0.863. Notably, CoA\u2010Net demonstrated comparable or even superior performance across these metrics, underscoring its potential as an effective decision\u2010support tool in real\u2010world clinical settings. Finally, ablation studies conclusively validated the indispensable role of the proposed local and global feature extractors, confirming that their synergistic contribution is critical to the model's overall high performance.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study proposes CoA\u2010Net for fetal CoA diagnosis. The model exhibits excellent classification performance and holds potential to support clinicians in achieving more precise and reliable fetal CoA diagnoses.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.70230","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T09:50:03Z","timestamp":1768384203000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A multi\u2010stage deep learning network for prenatal diagnosis of coarctation of the aorta"],"prefix":"10.1002","volume":"53","author":[{"given":"Wenhan","family":"Wang","sequence":"first","affiliation":[{"name":"School of Instrumentation and Optoelectronics Engineering Beihang University  Beijing P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiande","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Echocardiography, Fuwai Hospital, National Center for Cardiovascular Diseases Chinese Academy of Medical Sciences and Peking Union Medical College, Xicheng District  Beijing P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Instrumentation and Optoelectronics Engineering Beihang University  Beijing P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muzi","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Echocardiography, Fuwai Hospital, National Center for Cardiovascular Diseases Chinese Academy of Medical Sciences and Peking Union Medical College, Xicheng District  Beijing P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiling","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Echocardiography Fuwai Yunnan Cardiovascular Hospital Kunming  Kunming P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiwei","family":"Xing","sequence":"additional","affiliation":[{"name":"School of Instrumentation and Optoelectronics Engineering Beihang University  Beijing P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shangchun","family":"Fan","sequence":"additional","affiliation":[{"name":"School of Instrumentation and Optoelectronics Engineering Beihang University  Beijing P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolei","family":"Qu","sequence":"additional","affiliation":[{"name":"School of Instrumentation and Optoelectronics Engineering Beihang University  Beijing P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Meng","sequence":"additional","affiliation":[{"name":"Department of Echocardiography, Fuwai Hospital, National Center for Cardiovascular Diseases Chinese Academy of Medical Sciences and Peking Union Medical College, Xicheng District  Beijing P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1161\/circulationaha.114.008821"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.5603\/cj.2011.0003"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/s0003\u20104975(99)01280\u20101"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00246\u2010021\u201002634\u2010w"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1590\/1806\u20109282.65.2.240"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1080\/14767058.2018.1510913"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1161\/circulationaha.116.024068"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/chd.12648"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamacardio.2018.2009"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.echo.2022.07.010"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1080\/14767058.2020.1849109"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/8831107"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11036\u2010020\u201001672\u20107"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultrasmedbio.2024.11.014"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102430"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jiixd.2024.01.002"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591\u2010021\u201001342\u20105"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.3390\/jcm11216454"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.jmi.4.1.014502"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1515\/jce\u20102017\u20100015"},{"key":"e_1_2_8_22_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition. In:2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas NV USA 2016. doi:10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_8_23_1","doi-asserted-by":"crossref","unstructured":"HuangG LiuZ Van Der MaatenL WeinbergerKQ.Densely connected convolutional networks. In:2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu HI USA 2017. doi:10.1109\/cvpr.2017.243","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_2_8_24_1","article-title":"An image is worth 16\u00d716 words: transformers for image recognition at scale","author":"Dosovitskiy A","year":"2021","journal-title":"Int Conf Learn Represent"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12887\u2010024\u201004851\u20107"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.03167"},{"key":"e_1_2_8_27_1","unstructured":"GlorotX BordesA BengioY.Deep sparse rectifier neural networks.Proceedings of the fourteenth international conference on artificial intelligence and statistics.JMLR Workshop Conf Proceed.2011:315\u2010323."},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-6168-2_11"},{"key":"e_1_2_8_29_1","doi-asserted-by":"crossref","unstructured":"GaoZ WangL WuG.LIP: local importance\u2010based pooling. In:2019 IEEE\/CVF International Conference on Computer Vision (ICCV).2019:3354\u20103363. doi:10.1109\/iccv.2019.00345","DOI":"10.1109\/ICCV.2019.00345"},{"key":"e_1_2_8_30_1","unstructured":"VaswaniA.Attention is all you need.31st Conference on Neural Information Processing Systems (NIPS 2017).Long Beach CA USA;2017. doi:10.48550\/arXiv.1706.03762"},{"key":"e_1_2_8_31_1","doi-asserted-by":"crossref","unstructured":"LiX DongJ TangJ PanJ.DLGSANet: lightweight dynamic local and global self\u2010attention network for image super\u2010resolution. In:2023 IEEE\/CVF International Conference on Computer Vision (ICCV).Paris France;2023. doi:10.1109\/iccv51070.2023.01175","DOI":"10.1109\/ICCV51070.2023.01175"},{"key":"e_1_2_8_32_1","first-page":"8024","article-title":"PyTorch: an imperative style, high\u2010performance deep learning library","volume":"32","author":"Paszke A","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1378\/chest.114.3.946\u2010a"},{"key":"e_1_2_8_34_1","volume-title":"Statistical Power Analysis for the Behavioral Sciences","author":"Cohen J","year":"1988"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9863-7_1215"},{"key":"e_1_2_8_36_1","first-page":"1","article-title":"Very deep convolutional networks for large\u2010scale image recognition","author":"Simonyan K","year":"2015","journal-title":"Int Conf Learn Represent"},{"key":"e_1_2_8_37_1","doi-asserted-by":"crossref","unstructured":"SandlerM HowardA ZhuM ZhmoginovA ChenLC.MobileNetV2: inverted residuals and linear bottlenecks. In:2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2018:4510\u20104520. doi:10.1109\/cvpr.2018.00474","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_2_8_38_1","doi-asserted-by":"crossref","unstructured":"CholletF.Xception: deep learning with depthwise separable convolutions. In:2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2017:1800\u20101807. doi:10.1109\/cvpr.2017.195","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_2_8_39_1","doi-asserted-by":"crossref","unstructured":"LiuZ LinY CaoY et\u00a0al.Swin transformer: hierarchical vision transformer using shifted windows. In:2021 IEEE\/CVF International Conference on Computer Vision (ICCV).2021:9992\u201010002. doi:10.1109\/iccv48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105534"},{"key":"e_1_2_8_41_1","first-page":"4203","article-title":"Focal modulation networks","volume":"35","author":"Yang J","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_8_42_1","doi-asserted-by":"crossref","unstructured":"XiaZ PanX SongS LiLE HuangG.Vision transformer with deformable attention. In:2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2022:4784\u20104793. doi:10.1109\/cvpr52688.2022.00475","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"e_1_2_8_43_1","first-page":"3965","article-title":"CoatNet: marrying convolution and attention for all data sizes","volume":"34","author":"Dai Z","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106791"},{"key":"e_1_2_8_45_1","doi-asserted-by":"crossref","unstructured":"HuJ ShenL SunG.Squeeze\u2010and\u2010excitation networks. In:2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2018. doi:10.1109\/cvpr.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_2_8_46_1","doi-asserted-by":"crossref","unstructured":"WangQ WuB ZhuP et\u00a0al.ECA\u2010Net: efficient channel attention for deep convolutional neural networks. In:2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2020:11531\u201011539. doi:10.1109\/cvpr42600.2020.01155","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"e_1_2_8_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"issue":"11","key":"e_1_2_8_48_1","first-page":"2579","article-title":"Visualizing data using t\u2010SNE","volume":"9","author":"Van der Maaten L","year":"2008","journal-title":"J Mach Learn Res"},{"key":"e_1_2_8_49_1","doi-asserted-by":"crossref","unstructured":"SelvarajuRR CogswellM DasA et\u00a0al.Grad\u2010CAM: visual explanations from deep networks via gradient\u2010based localization. In:2017 IEEE International Conference on Computer Vision (ICCV).2017:618\u2010626. doi:10.1109\/iccv.2017.74","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_2_8_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2022.119505"},{"key":"e_1_2_8_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103503"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70230","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.70230","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T01:56:44Z","timestamp":1773885404000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.70230"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1002\/mp.70230"],"URL":"https:\/\/doi.org\/10.1002\/mp.70230","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-02-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70230"}}