{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,26]],"date-time":"2026-07-26T18:11:51Z","timestamp":1785089511895,"version":"3.55.0"},"reference-count":37,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T00:00:00Z","timestamp":1751846400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004391","name":"China Medical University Hospital (CMUH)","doi-asserted-by":"publisher","award":["DMR-114-169"],"award-info":[{"award-number":["DMR-114-169"]}],"id":[{"id":"10.13039\/501100004391","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>Background: Acute Aortic Syndrome (AAS), encompassing aortic dissection (AD), intramural hematoma (IMH), and penetrating atherosclerotic ulcer (PAU), presents diagnostic challenges due to its varied manifestations and the critical need for rapid assessment. Methods: We developed a multi-stage deep learning model trained on chest computed tomography angiography (CTA) scans. The model utilizes a U-Net architecture for aortic segmentation, followed by a cascaded classification approach for detecting AD and IMH, and a multiscale CNN for identifying PAU. External validation was conducted on 260 anonymized CTA scans from 14 U.S. clinical sites, encompassing data from four different CT manufacturers. Performance metrics, including sensitivity, specificity, and area under the receiver operating characteristic curve (AUC), were calculated with 95% confidence intervals (CIs) using Wilson\u2019s method. Model performance was compared against predefined benchmarks. Results: The model achieved a sensitivity of 0.94 (95% CI: 0.88\u20130.97), specificity of 0.93 (95% CI: 0.89\u20130.97), and an AUC of 0.96 (95% CI: 0.94\u20130.98) for overall AAS detection, with p-values &lt; 0.001 when compared to the 0.80 benchmark. Subgroup analyses demonstrated consistent performance across different patient demographics, CT manufacturers, slice thicknesses, and anatomical locations. Conclusions: This deep learning model effectively detects the full spectrum of AAS across diverse populations and imaging platforms, suggesting its potential utility in clinical settings to enable faster triage and expedite patient management.<\/jats:p>","DOI":"10.3390\/jcm14134797","type":"journal-article","created":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T10:03:27Z","timestamp":1751882607000},"page":"4797","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Multi-Stage Cascaded Deep Learning-Based Model for Acute Aortic Syndrome Detection: A Multisite Validation Study"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1704-2755","authenticated-orcid":false,"given":"Joseph","family":"Chang","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, No. 1, Sec. 1, Jen-Ai Road, Taipei 100, Taiwan"},{"name":"EverFortune.AI Co., Ltd., Taichung 403, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kuan-Jung","family":"Lee","sequence":"additional","affiliation":[{"name":"EverFortune.AI Co., Ltd., Taichung 403, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ti-Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"EverFortune.AI Co., Ltd., Taichung 403, Taiwan"},{"name":"Department of Medicine, China Medical University, Taichung 404, Taiwan"},{"name":"Department of Radiation Oncology, China Medical University Hospital, Taichung 404, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0023-5817","authenticated-orcid":false,"given":"Chung-Ming","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, No. 1, Sec. 1, Jen-Ai Road, Taipei 100, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e004689","DOI":"10.1161\/CIRCOUTCOMES.118.004689","article-title":"Population-Based Assessment of the Incidence of Aortic Dissection, Intramural Hematoma, and Penetrating Ulcer, and Its Associated Mortality From 1995 to 2015","volume":"11","author":"DeMartino","year":"2018","journal-title":"Circ. Cardiovasc. Qual. Outcomes"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1586\/14779072.3.3.423","article-title":"Acute Aortic Syndromes: Aortic Dissections, Penetrating Aortic Ulcers and Intramural Aortic Hematomas","volume":"3","author":"Dieter","year":"2005","journal-title":"Expert Rev. Cardiovasc. Ther."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"628","DOI":"10.1161\/01.CIR.0000087009.16755.E4","article-title":"Aortic dissection: New frontiers in diagnosis and management: Part I: From etiology to diagnostic strategies","volume":"108","author":"Nienaber","year":"2003","journal-title":"Circulation"},{"key":"ref_4","first-page":"191","article-title":"Imaging of acute aortic syndrome","volume":"15","author":"Evangelista","year":"2018","journal-title":"Nat. Rev. Cardiol."},{"key":"ref_5","unstructured":"McLatchie, R., Reed, M.J., Freeman, N., Parker, R.A., Wilson, S., Goodacre, S., Cowan, A., Boyle, J., Clarke, B., and Clarke, E. Diagnosis of Acute Aortic Syndrome in the Emergency Department (DAShED) study: An observational cohort study. Emerg. Med. J., 2023."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.carj.2018.10.011","article-title":"Acute Aortic Syndrome: Yield of CT Angiography in Acute Chest Pain","volume":"70","author":"Meng","year":"2019","journal-title":"Can. Assoc. Radiol. J."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1111\/1742-6723.13974","article-title":"Trends in CT Aortography and Acute Aortic Syndrome in New Zealand","volume":"34","author":"Waqanivavalagi","year":"2022","journal-title":"Emerg. Med. Australas."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1148\/rg.210098","article-title":"CT of the Difficult Acute Aortic Syndrome","volume":"42","author":"Steinbrecher","year":"2021","journal-title":"Radiographics"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"20201294","DOI":"10.1259\/bjr.20201294","article-title":"Emergency CT Misdiagnosis in Acute Aortic Syndrome","volume":"94","author":"Dreisbach","year":"2021","journal-title":"Br. J. Radiol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1038\/nrcardio.2013.92","article-title":"Imaging Modalities for Early Diagnosis of Acute Aortic Syndrome","volume":"10","author":"Evangelista","year":"2013","journal-title":"Nat. Rev. Cardiol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"e27","DOI":"10.1016\/j.crad.2021.09.009","article-title":"ECG-Gated CT for Aortic Syndrome: Subspecialty Recommendations Impact","volume":"77","author":"Hamilton","year":"2021","journal-title":"Clin. Radiol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"108713","DOI":"10.1016\/j.ejrad.2019.108713","article-title":"Fully Automatic Segmentation of Type B Aortic Dissection","volume":"121","author":"Cao","year":"2019","journal-title":"Eur. J. Radiol."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Yi, Y., Mao, L., Wang, C., Guo, Y., Luo, X., Jia, D., Lei, Y., Pan, J., Li, J., and Li, S. (2022). Early Warning of Aortic Dissection on Non-Contrast CT. Front. Cardiovasc. Med., 8.","DOI":"10.3389\/fcvm.2021.762958"},{"key":"ref_14","first-page":"2914","article-title":"Cascaded Deep Learning for Detecting Aortic Dissection","volume":"43","author":"Xiong","year":"2021","journal-title":"IEEE EMBC"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Laletin, V., Ayobi, A., Chang, P.D., Chow, D.S., Soun, J.E., Junn, J.C., Scudeler, M., Quenet, S., Tassy, M., and Avare, C. (2024). Diagnostic Performance of a Deep Learning-Powered Application for Aortic Dissection Triage Prioritization and Classification. Diagnostics, 14.","DOI":"10.20944\/preprints202407.0962.v1"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Liu, H.-H., Chang, C.-B., Chen, Y.-S., Kuo, C.-F., Lin, C.-Y., Ma, C.-Y., and Wang, L.-J. (2025). Automated Detection and Differentiation of Stanford Type A and Type B Aortic Dissections in CTA Scans Using Deep Learning. Diagnostics, 15.","DOI":"10.3390\/diagnostics15010012"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2277","DOI":"10.1007\/s00330-021-08370-2","article-title":"Automated Stanford classification of aortic dissection using a 2-step hierarchical neural network at computed tomography angiography","volume":"32","author":"Huang","year":"2022","journal-title":"Eur. Radiol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2729","DOI":"10.1007\/s10278-024-01164-0","article-title":"Streamlining Acute Abdominal Aortic Dissection Management-An AI-based CT Imaging Workflow","volume":"37","author":"Raj","year":"2024","journal-title":"J. Imaging Inform Med."},{"key":"ref_19","unstructured":"Chen, J., Qian, L., Wang, P., Sun, C., Qin, T., Kalyanasundaram, A., Zafar, M., Elefteriades, J.A., Sun, W., and Liang, L. (2024). A 3D Image Segmentation Study on Aorta Anatomy. bioRxiv."},{"key":"ref_20","first-page":"147","article-title":"Segmentation of Thoracic Aorta Using Attention-Gated U-Net","volume":"11597","author":"Zhong","year":"2021","journal-title":"SPIE Med. Imaging"},{"key":"ref_21","unstructured":"Ravichandran, S.R., Nataraj, B., Huang, S., Qin, Z., Lu, Z., Katsuki, A., Huang, W., and Zeng, Z. (2019, January 19\u201322). 3D Inception U-Net for Aorta Segmentation. Proceedings of the 2019 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Chicago, IL, USA."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1089\/cmb.2022.0248","article-title":"Automatic Organ-at-Risk Segmentation with Ensembled U-Net","volume":"30","author":"Ashok","year":"2023","journal-title":"J. Comput. Biol."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhang, H., and Cai, Z. (2024). ConvNextUNet: A small-region attentioned model for cardiac MRI segmentation. Comput. Biol. Med., 177.","DOI":"10.1016\/j.compbiomed.2024.108592"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"8356294","DOI":"10.1155\/2016\/8356294","article-title":"Multiscale CNNs for Brain Tumor Diagnosis","volume":"2016","author":"Zhao","year":"2016","journal-title":"Comput. Math. Methods Med."},{"key":"ref_25","first-page":"139","article-title":"Multiscale Detection of Cancerous Tissue in High Resolution Slide Scans","volume":"12510","author":"Zhang","year":"2020","journal-title":"Adv. Vis. Comput."},{"key":"ref_26","first-page":"267","article-title":"Deep Multiscale Feature Learning in X-Ray Localization","volume":"11073","author":"Sedai","year":"2018","journal-title":"MICCAI"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Ristow, A.V., Massi\u00e8re, B., and Beer, F. (2011). Intramural Hematoma and Penetrating Ulcers. Springer Ref., 555\u2013566.","DOI":"10.1007\/978-88-470-1857-0_45"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Maas, A., van Bakel, P.A.J., Ahmed, Y., Patel, H., and Burris, N. (2022). Natural History of Aortic Intimal Flaps. Front. Cardiovasc. Med., 9.","DOI":"10.3389\/fcvm.2022.959517"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"456","DOI":"10.21037\/acs.2019.07.05","article-title":"Intramural Hematoma and Penetrating Ulcer of Descending Aorta","volume":"8","author":"Evangelista","year":"2019","journal-title":"Ann. Cardiothorac. Surg."},{"key":"ref_30","unstructured":"(2023). Code of Federal Regulation (Standard No. 45 CFR \u00a7 164.514 (e))."},{"key":"ref_31","unstructured":"(2023). Code of Federal Regulation (Standard No. 45 CFR \u00a7 46.101)."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1007\/s10278-019-00281-5","article-title":"Classification of Aortic Dissection and Rupture on CT Using CNN","volume":"32","author":"Harris","year":"2019","journal-title":"J. Digit. Imaging"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1151","DOI":"10.1007\/s00330-020-07213-w","article-title":"Deep Learning for Aortic Dissection on Non-Contrast CT","volume":"31","author":"Hata","year":"2020","journal-title":"Eur. Radiol."},{"key":"ref_34","unstructured":"Aidoc Medical (2025, April 21). Aidoc BriefCase: Aortic Dissection Module. FDA 510(k) Summary. K222329, Available online: https:\/\/www.accessdata.fda.gov\/cdrh_docs\/pdf22\/K222329.pdf."},{"key":"ref_35","unstructured":"(2025, April 21). AvicennaAI CINA Chest: FDA 510(k) Summary, Available online: https:\/\/www.accessdata.fda.gov\/cdrh_docs\/pdf21\/K210237.pdf."},{"key":"ref_36","unstructured":"Viz.ai, Inc (2025, April 21). Viz Aortic: Triage and Notification Software for Aortic Dissection. FDA Summary, Available online: https:\/\/www.fda.gov\/media\/157653\/download."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1097\/HCO.0000000000000782","article-title":"Penetrating atherosclerotic ulcer","volume":"35","author":"Evangelista","year":"2020","journal-title":"Curr. Opin. Cardiol"}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/14\/13\/4797\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:05:57Z","timestamp":1760033157000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/14\/13\/4797"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,7]]},"references-count":37,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["jcm14134797"],"URL":"https:\/\/doi.org\/10.3390\/jcm14134797","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,7]]}}}