{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T11:50:28Z","timestamp":1773661828633,"version":"3.50.1"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100008376","name":"Helsingin ja Uudenmaan Sairaanhoitopiiri","doi-asserted-by":"publisher","award":["TYH2024228"],"award-info":[{"award-number":["TYH2024228"]}],"id":[{"id":"10.13039\/100008376","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008376","name":"Helsingin ja Uudenmaan Sairaanhoitopiiri","doi-asserted-by":"publisher","award":["M780025014"],"award-info":[{"award-number":["M780025014"]}],"id":[{"id":"10.13039\/100008376","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol Exp"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Chronic pulmonary embolism (CPE) and chronic thromboembolic pulmonary hypertension (CTEPH) are challenging to diagnose, with delayed detection increasing mortality. We evaluated the performance of a convolutional neural network (CNN) in identifying these conditions from computed tomography pulmonary angiography (CTPA)-derived maximum intensity projection (MIP) images using a novel approach including proximal pulmonary vessels and a layered segmentation of the lung volume to assess the diagnostic value of different vascular regions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>We included 41 CPE, 41 acute pulmonary embolism (APE) and 41 normal controls (non-PE). 25 of the CPE patients had CTEPH confirmed by right heart catheterization. CNN classifiers were trained to identify CPE or CTEPH against a combined APE and non-PE group. Eleven masking schemes were applied for both classification tasks, resulting in 22 experiments. Model performances were compared using areas under the receiver operating characteristic curves (AUROC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The model achieved good performance in distinguishing CPE from non-PE and APE cases (cross-validation AUROC 0.80) using full lung volume MIPs, while performance decreased with reduced data. For CTEPH classification against non-PE and APE, the model reached AUROC 0.88 with full data and 0.86 using only the most proximal half of the lung volume, suggesting key diagnostic features reside centrally. Using an open-source segmentation model, which excludes proximal vessels, resulted in lower AUROCs (0.74 for CPE, 0.83 for CTEPH).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The cross-validation indicated that CPE and CTEPH could be identified from CTPA-derived MIP images, with performance improving as more vessels were included. The proximal vessels were most relevant for CTEPH detection.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Relevance statement<\/jats:title>\n                    <jats:p>Our study shows that neural networks can identify chronic pulmonary embolism in CTPA and the role of different vascular regions in that task, with the potential to improve future imaging diagnostics in patients with chronic pulmonary embolism.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:list list-type=\"bullet\">\n                        <jats:list-item>\n                          <jats:p>A convolutional neural network detects chronic thromboembolic pulmonary hypertension and chronic embolism from CTPA MIP projections.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>CTPA data were divided into four concentric anatomic layers for regional analysis.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Central layers were most important for identifying CTEPH features.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Network performance improved when more vessel regions were used as input.<\/jats:p>\n                        <\/jats:list-item>\n                      <\/jats:list>\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Graphical Abstract<\/jats:title>\n                  <\/jats:sec>","DOI":"10.1186\/s41747-026-00699-x","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T10:52:07Z","timestamp":1773658327000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning-based identification of chronic pulmonary embolism on CTPA: a regional lung analysis using multiplanar MIP images"],"prefix":"10.1186","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3098-0084","authenticated-orcid":false,"given":"Tuomas","family":"Vainio","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Teemu","family":"M\u00e4kel\u00e4","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arttu","family":"Ruohola","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anssi","family":"Arkko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sauli","family":"Savolainen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marko","family":"Kangasniemi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"699_CR1","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1378\/chest.119.3.818","volume":"119","author":"J Lewczuk","year":"2001","unstructured":"Lewczuk J, Piszko P, Jagas J et al (2001) Prognostic factors in medically treated patients with chronic pulmonary embolism. Chest 119:818\u2013823. https:\/\/doi.org\/10.1378\/chest.119.3.818","journal-title":"Chest"},{"key":"699_CR2","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1378\/chest.81.2.151","volume":"81","author":"M Riedel","year":"1982","unstructured":"Riedel M, Stanek V, Widimsky J, Prerovsky I (1982) Long-term follow-up of patients with pulmonary thromboembolism. Late prognosis and evolution of hemodynamic and respiratory data. Chest 81:151\u2013158. https:\/\/doi.org\/10.1378\/chest.81.2.151","journal-title":"Chest"},{"key":"699_CR3","doi-asserted-by":"publisher","first-page":"1248","DOI":"10.1111\/j.1538-7836.2010.03844.x","volume":"8","author":"O Sanchez","year":"2010","unstructured":"Sanchez O, Helley D, Couchon S et al (2010) Perfusion defects after pulmonary embolism: risk factors and clinical significance. J Thromb Haemost 8:1248\u20131255. https:\/\/doi.org\/10.1111\/j.1538-7836.2010.03844.x","journal-title":"J Thromb Haemost"},{"key":"699_CR4","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1007\/s11739-011-0577-8","volume":"6","author":"B Cosmi","year":"2011","unstructured":"Cosmi B, Nijkeuter M, Valentino M, Huisman MV, Barozzi L, Palareti G (2011) Residual emboli on lung perfusion scan or multidetector computed tomography after a first episode of acute pulmonary embolism. Intern Emerg Med 6:521\u2013528. https:\/\/doi.org\/10.1007\/s11739-011-0577-8","journal-title":"Intern Emerg Med"},{"key":"699_CR5","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1183\/09031936.00201612","volume":"41","author":"J Pepke-Zaba","year":"2013","unstructured":"Pepke-Zaba J, Jansa P, Kim NH, Naeije R, Simonneau G (2013) Chronic thromboembolic pulmonary hypertension: role of medical therapy. Eur Respir J 41:985\u2013990. https:\/\/doi.org\/10.1183\/09031936.00201612","journal-title":"Eur Respir J"},{"key":"699_CR6","doi-asserted-by":"publisher","first-page":"155","DOI":"10.4103\/2045-8932.97594","volume":"2","author":"WR Auger","year":"2012","unstructured":"Auger WR, Kerr KM, Kim NH, Fedullo PF (2012) Evaluation of patients with chronic thromboembolic pulmonary hypertension for pulmonary endarterectomy. Pulm Circ 2:155\u2013162. https:\/\/doi.org\/10.4103\/2045-8932.97594","journal-title":"Pulm Circ"},{"key":"699_CR7","doi-asserted-by":"publisher","first-page":"680","DOI":"10.2967\/jnumed.106.039438","volume":"48","author":"N Tunariu","year":"2007","unstructured":"Tunariu N, Gibbs SJR, Win Z et al (2007) Ventilation-perfusion scintigraphy is more sensitive than multidetector CTPA in detecting chronic thromboembolic pulmonary disease as a treatable cause of pulmonary hypertension. J Nucl Med 48:680\u2013684. https:\/\/doi.org\/10.2967\/jnumed.106.039438","journal-title":"J Nucl Med"},{"key":"699_CR8","doi-asserted-by":"publisher","first-page":"1465","DOI":"10.1056\/NEJMra010902","volume":"345","author":"PF Fedullo","year":"2001","unstructured":"Fedullo PF, Auger WR, Kerr KM, Rubin LJ (2001) Chronic thromboembolic pulmonary hypertension. N Engl J Med 345:1465\u20131472. https:\/\/doi.org\/10.1056\/NEJMra010902","journal-title":"N Engl J Med"},{"key":"699_CR9","doi-asserted-by":"publisher","first-page":"1576","DOI":"10.1177\/0284185119836232","volume":"60","author":"AN Rogberg","year":"2019","unstructured":"Rogberg AN, Gopalan D, Westerlund E, Lindholm P (2019) Do radiologists detect chronic thromboembolic disease on computed tomography? Acta Radiol 60:1576\u20131583. https:\/\/doi.org\/10.1177\/0284185119836232","journal-title":"Acta Radiol"},{"key":"699_CR10","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1016\/j.crad.2017.02.011","volume":"72","author":"A Ruggiero","year":"2017","unstructured":"Ruggiero A, Screaton NJ (2017) Imaging of acute and chronic thromboembolic disease: state of the art. Clin Radiol 72:375\u2013388. https:\/\/doi.org\/10.1016\/j.crad.2017.02.011","journal-title":"Clin Radiol"},{"key":"699_CR11","doi-asserted-by":"publisher","first-page":"S222","DOI":"10.1513\/AnnalsATS.201509-623AS","volume":"13","author":"D Gopalan","year":"2016","unstructured":"Gopalan D, Blanchard D, Auger WR (2016) Diagnostic evaluation of chronic thromboembolic pulmonary hypertension. Ann Am Thorac Soc 13:S222\u2013S239. https:\/\/doi.org\/10.1513\/AnnalsATS.201509-623AS","journal-title":"Ann Am Thorac Soc"},{"key":"699_CR12","doi-asserted-by":"publisher","first-page":"1973","DOI":"10.1161\/CIRCULATIONAHA.110.015008","volume":"124","author":"J Pepke-Zaba","year":"2011","unstructured":"Pepke-Zaba J, Delcroix M, Lang I et al (2011) Chronic thromboembolic pulmonary hypertension (CTEPH): results from an international prospective registry. Circulation 124:1973\u20131981. https:\/\/doi.org\/10.1161\/CIRCULATIONAHA.110.015008","journal-title":"Circulation"},{"key":"699_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcchd.2024.100536","volume":"17","author":"H Ghani","year":"2024","unstructured":"Ghani H, Weir-McCall JR, Ruggiero A, Pepke-Zaba J (2024) Imaging in chronic thromboembolic pulmonary disease: current practice and advances. Int J Cardiol Congenit Heart Dis 17:100536. https:\/\/doi.org\/10.1016\/j.ijcchd.2024.100536","journal-title":"Int J Cardiol Congenit Heart Dis"},{"key":"699_CR14","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.blre.2010.06.001","volume":"24","author":"FA Klok","year":"2010","unstructured":"Klok FA, Mos IC, Huisman MV (2010) The post-PE syndrome: a new concept for chronic complications of pulmonary embolism. Blood Rev 24:167\u2013173. https:\/\/doi.org\/10.1016\/j.blre.2010.06.001","journal-title":"Blood Rev"},{"key":"699_CR15","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1186\/s41747-021-00235-z","volume":"5","author":"T Vainio","year":"2021","unstructured":"Vainio T, M\u00e4kel\u00e4 T, Savolainen S, Kangasniemi M (2021) Performance of a 3D convolutional neural network in the detection of hypoperfusion at CT pulmonary angiography in patients with chronic pulmonary embolism: a feasibility study. Eur Radiol Exp 5:45. https:\/\/doi.org\/10.1186\/s41747-021-00235-z","journal-title":"Eur Radiol Exp"},{"key":"699_CR16","doi-asserted-by":"publisher","first-page":"1471","DOI":"10.3390\/s23031471","volume":"23","author":"M Khan","year":"2023","unstructured":"Khan M, Shah PM, Khan IA et al (2023) IoMT-enabled computer-aided diagnosis of pulmonary embolism from computed tomography scans using deep learning. Sensors (Basel) 23:1471. https:\/\/doi.org\/10.3390\/s23031471","journal-title":"Sensors (Basel)"},{"key":"699_CR17","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-16976-9","volume":"12","author":"X Ma","year":"2022","unstructured":"Ma X, Ferguson EC, Jiang X, Savitz SI, Shams S (2022) A multitask deep learning approach for pulmonary embolism detection and identification. Sci Rep 12:13087. https:\/\/doi.org\/10.1038\/s41598-022-16976-9","journal-title":"Sci Rep"},{"key":"699_CR18","doi-asserted-by":"publisher","DOI":"10.3389\/fradi.2024.1335349","volume":"4","author":"L Abdulaal","year":"2024","unstructured":"Abdulaal L, Maiter A, Salehi M et al (2024) A systematic review of artificial intelligence tools for chronic pulmonary embolism on CT pulmonary angiography. Front Radiol 4:1335349. https:\/\/doi.org\/10.3389\/fradi.2024.1335349","journal-title":"Front Radiol"},{"key":"699_CR19","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/s41747-023-00346-9","volume":"7","author":"T Vainio","year":"2023","unstructured":"Vainio T, M\u00e4kel\u00e4 T, Arkko A, Savolainen S, Kangasniemi M (2023) Leveraging open dataset and transfer learning for accurate recognition of chronic pulmonary embolism from CT angiogram maximum intensity projection images. Eur Radiol Exp 7:33. https:\/\/doi.org\/10.1186\/s41747-023-00346-9","journal-title":"Eur Radiol Exp"},{"key":"699_CR20","doi-asserted-by":"publisher","first-page":"6983","DOI":"10.1007\/s00330-025-11698-8","volume":"35","author":"Y Lin","year":"2025","unstructured":"Lin Y, Li M, Xie S (2025) Diagnostic value of fully automated CT pulmonary angiography in patients with chronic thromboembolic pulmonary hypertension and chronic thromboembolic disease. Eur Radiol 35:6983\u20136995. https:\/\/doi.org\/10.1007\/s00330-025-11698-8","journal-title":"Eur Radiol"},{"key":"699_CR21","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1186\/s13244-025-02067-6","volume":"16","author":"L Xi","year":"2025","unstructured":"Xi L, Wang J, Liu A et al (2025) Development of a lung perfusion automated quantitative model based on dual-energy CT pulmonary angiography in patients with chronic pulmonary thromboembolism. Insights Imaging 16:182. https:\/\/doi.org\/10.1186\/s13244-025-02067-6","journal-title":"Insights Imaging"},{"key":"699_CR22","doi-asserted-by":"publisher","first-page":"253","DOI":"10.21037\/cdt.2018.01.09","volume":"8","author":"KH Nishiyama","year":"2018","unstructured":"Nishiyama KH, Saboo SS, Tanabe Y, Jasinowodolinski D, Landay MJ, Kay FU (2018) Chronic pulmonary embolism: diagnosis. Cardiovasc Diagn Ther 8:253\u2013271. https:\/\/doi.org\/10.21037\/cdt.2018.01.09","journal-title":"Cardiovasc Diagn Ther"},{"key":"699_CR23","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1086\/685081","volume":"6","author":"FN Rahaghi","year":"2016","unstructured":"Rahaghi FN, Ross JC, Agarwal M et al (2016) Pulmonary vascular morphology as an imaging biomarker in chronic thromboembolic pulmonary hypertension. Pulm Circ 6:70\u201381. https:\/\/doi.org\/10.1086\/685081","journal-title":"Pulm Circ"},{"key":"699_CR24","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/1465-9921-13-27","volume":"13","author":"R Quarck","year":"2012","unstructured":"Quarck R, Wynants M, Ronisz A et al (2012) Characterization of proximal pulmonary arterial cells from chronic thromboembolic pulmonary hypertension patients. Respir Res 13:27. https:\/\/doi.org\/10.1186\/1465-9921-13-27","journal-title":"Respir Res"},{"key":"699_CR25","doi-asserted-by":"publisher","first-page":"S421","DOI":"10.2214\/AJR.04.1955","volume":"186","author":"C Wittram","year":"2006","unstructured":"Wittram C, Kalra MK, Maher MM, Greenfield A, McLoud TC, Shepard JA (2006) Acute and chronic pulmonary emboli: angiography-CT correlation. AJR Am J Roentgenol 186:S421\u2013S429. https:\/\/doi.org\/10.2214\/AJR.04.1955","journal-title":"AJR Am J Roentgenol"},{"key":"699_CR26","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.jneumeth.2016.03.001","volume":"264","author":"X Li","year":"2016","unstructured":"Li X, Morgan PS, Ashburner J, Smith J, Rorden C (2016) The first step for neuroimaging data analysis: DICOM to NIfTI conversion. J Neurosci Methods 264:47\u201356. https:\/\/doi.org\/10.1016\/j.jneumeth.2016.03.001","journal-title":"J Neurosci Methods"},{"key":"699_CR27","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1186\/s41747-020-00173-2","volume":"4","author":"J Hofmanninger","year":"2020","unstructured":"Hofmanninger J, Prayer F, Pan J et al (2020) Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem. Eur Radiol Exp 4:50. https:\/\/doi.org\/10.1186\/s41747-020-00173-2","journal-title":"Eur Radiol Exp"},{"key":"699_CR28","doi-asserted-by":"publisher","unstructured":"Kikinis R, Pieper SD, Vosburgh K (2014) 3D Slicer: a platform for subject-specific image analysis, visualization, and clinical support. In: Jolesz FA (ed) Intraoperative imaging image-guided therapy. Springer, New York, NY, pp 277\u2013289. https:\/\/doi.org\/10.1016\/j.mri.2012.05.001","DOI":"10.1016\/j.mri.2012.05.001"}],"container-title":["European Radiology Experimental"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-026-00699-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s41747-026-00699-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-026-00699-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T10:52:08Z","timestamp":1773658328000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s41747-026-00699-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["699"],"URL":"https:\/\/doi.org\/10.1186\/s41747-026-00699-x","relation":{},"ISSN":["2509-9280"],"issn-type":[{"value":"2509-9280","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,16]]},"assertion":[{"value":"27 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The Helsinki University Hospital Ethics Committee approved this retrospective study (Department of Radiology, decisions HUS\/211\/2020, 23 March 2020, and HUS\/31\/2024, 29 February 2024). The study was deemed exempt from the requirement for signed informed consent under the Finnish Acts on Medical Research and the Secondary Use of Health and Social Data.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The study was deemed exempt from the requirement for signed informed consent under the Finnish Acts on Medical Research and the Secondary Use of Health and Social Data.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"32"}}