{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T01:51:54Z","timestamp":1789869114601,"version":"4.0.1"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T00:00:00Z","timestamp":1772582400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T00:00:00Z","timestamp":1772582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"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>Objectives<\/jats:title>\n                    <jats:p>We compared three customized nnU-Net models (A: baseline two-dimensional (2D); B: 2D\u2009+\u2009region-growing; C: three-dimensional (3D)\u2009+\u2009region-growing) for automated detection and blood clot volume (BCV) quantification of acute pulmonary embolism (PE) on computed tomography pulmonary angiography (CTPA), and to explore the association between BCV and clinical outcome.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>\n                      We retrospectively screened 9,715 CTPA examinations (2015\u20122024) to develop a dataset of 874 PE-positive and 339 PE-negative cases. A stratified subset (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009437) with manually refined ground-truth segmentations was used for model training and internal validation. Region-growing in Models B and C included a 5-voxel negative buffer. Internal testing was performed on 776 cases (Humanitas dataset). External testing was performed on the public RSPECT-RSNA dataset. Performance metrics included accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) at zero-clot and for optimized BCV threshold. Correlations between BCV, survival, and major adverse cardiovascular events (MACE) were analyzed.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Model C achieved the highest AUROC on external testing (0.868), outperforming Model A (0.843) and Model B (0.846). On internal testing at ROC-optimized threshold, Model C showed the highest accuracy (85.5%) and AUROC (0.909) compared to Model A (73.4%, 0.784) and Model B (76.0%, 0.816). Model C achieved 83.6% sensitivity and 79.5% accuracy at the zero-clot threshold on external data. BCV was not significantly associated with MACE or survival (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.600).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>A locally trained 3D nnU-Net with region-growing demonstrated superior performance and generalizability on external data for automated PE detection on CTPA. However, BCV was not predictive of short-term clinical outcomes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Relevance statement<\/jats:title>\n                    <jats:p>A locally developed nnU-Net models integrating volumetric 3D segmentation with region-growing offer robust, clinically acceptable performance for the detection of acute pulmonary embolism without the need for ROC-based thresholds.<\/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>Our 3D nnU-Net model automates clot detection on CT scans in seconds and shows numerically higher performance than the 2D models.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Built on local data, this framework enables institution-specific model training and validation to complement European conformity\u2012CE-marked tools and assess performance locally.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>High-sensitivity volumetric quantification reduces missed emboli, paving the way for personalized risk stratification and improved patient outcomes.<\/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\/s41747-026-00693-3","type":"journal-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T09:53:00Z","timestamp":1772617980000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["3D region-growing nnU-Net improves pulmonary embolism detection on CTPA: a dual-cohort validation study"],"prefix":"10.1186","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1889-8798","authenticated-orcid":false,"given":"Ezio","family":"Lanza","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angela","family":"Ammirabile","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Vanzulli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Costanza","family":"Lisi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arosh Shavinda","family":"Perera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ada Maria Antonella","family":"Lucia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandra","family":"Mininni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Riccardo","family":"Levi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Francone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Laghi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,4]]},"reference":[{"key":"693_CR1","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1093\/eurheartj\/ehz405","volume":"41","author":"SV Konstantinides","year":"2020","unstructured":"Konstantinides SV, Meyer G, Becattini C et al (2020) 2019 ESC guidelines for the diagnosis and management of acute pulmonary embolism developed in collaboration with the European Respiratory Society (ERS). Eur Heart J 41:543\u2013603. https:\/\/doi.org\/10.1093\/eurheartj\/ehz405","journal-title":"Eur Heart J"},{"key":"693_CR2","doi-asserted-by":"publisher","first-page":"2317","DOI":"10.1056\/NEJMoa052367","volume":"354","author":"PD Stein","year":"2006","unstructured":"Stein PD, Fowler SE, Goodman LR et al (2006) Multidetector computed tomography for acute pulmonary embolism. N Engl J Med 354:2317\u20132327. https:\/\/doi.org\/10.1056\/NEJMoa052367","journal-title":"N Engl J Med"},{"key":"693_CR3","doi-asserted-by":"publisher","first-page":"4296","DOI":"10.1182\/bloodadvances.2019001052","volume":"4","author":"P Patel","year":"2020","unstructured":"Patel P, Patel P, Bhatt M et al (2020) Systematic review and meta-analysis of test accuracy for the diagnosis of suspected pulmonary embolism. Blood Adv 4:4296\u20134311. https:\/\/doi.org\/10.1182\/bloodadvances.2019001052","journal-title":"Blood Adv"},{"key":"693_CR4","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1148\/radiology.210.3.r99mr41689","volume":"210","author":"PD Stein","year":"1999","unstructured":"Stein PD, Henry JW, Gottschalk A (1999) Reassessment of pulmonary angiography for the diagnosis of pulmonary embolism: relation of interpreter agreement to the order of the involved pulmonary arterial branch. Radiology 210:689\u2013691. https:\/\/doi.org\/10.1148\/radiology.210.3.r99mr41689","journal-title":"Radiology"},{"key":"693_CR5","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1016\/j.ajem.2008.08.019","volume":"27","author":"G Costantino","year":"2009","unstructured":"Costantino G, Norsa AH, Amadori R et al (2009) Interobserver agreement in the interpretation of computed tomography in acute pulmonary embolism. Am J Emerg Med 27:1109\u20131111. https:\/\/doi.org\/10.1016\/j.ajem.2008.08.019","journal-title":"Am J Emerg Med"},{"key":"693_CR6","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.1007\/s10278-019-00228-w","volume":"32","author":"C Zhou","year":"2019","unstructured":"Zhou C, Chan H-P, Chughtai A et al (2019) Variabilities in reference standard by radiologists and performance assessment in detection of pulmonary embolism in CT pulmonary angiography. J Digit Imaging 32:1089\u20131096. https:\/\/doi.org\/10.1007\/s10278-019-00228-w","journal-title":"J Digit Imaging"},{"key":"693_CR7","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-95249-3","volume":"11","author":"S Soffer","year":"2021","unstructured":"Soffer S, Klang E, Shimon O et al (2021) Deep learning for pulmonary embolism detection on computed tomography pulmonary angiogram: a systematic review and meta-analysis. Sci Rep 11:15814. https:\/\/doi.org\/10.1038\/s41598-021-95249-3","journal-title":"Sci Rep"},{"key":"693_CR8","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.clinimag.2022.05.003","volume":"88","author":"L Azour","year":"2022","unstructured":"Azour L, Ko JP, Toussie D et al (2022) Current imaging of PE and emerging techniques: is there a role for artificial intelligence? Clin Imaging 88:24\u201332. https:\/\/doi.org\/10.1016\/j.clinimag.2022.05.003","journal-title":"Clin Imaging"},{"key":"693_CR9","doi-asserted-by":"publisher","first-page":"110402","DOI":"10.1016\/j.compbiomed.2025.110402","volume":"193","author":"E Lanza","year":"2025","unstructured":"Lanza E, Ammirabile A, Francone M (2025) Meta-analysis of AI-based pulmonary embolism detection: how reliable are deep learning models? Comput Biol Med 193:110402. https:\/\/doi.org\/10.1016\/j.compbiomed.2025.110402","journal-title":"Comput Biol Med"},{"key":"693_CR10","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee F, Jaeger PF, Kohl SAA et al (2021) nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18:203\u2013211. https:\/\/doi.org\/10.1038\/s41592-020-01008-z","journal-title":"Nat Methods"},{"key":"693_CR11","doi-asserted-by":"publisher","first-page":"e38118","DOI":"10.1016\/j.heliyon.2024.e38118","volume":"10","author":"AT Kahraman","year":"2024","unstructured":"Kahraman AT, Fr\u00f6ding T, Toumpanakis D et al (2024) Enhanced classification performance using deep learning based segmentation for pulmonary embolism detection in CT angiography. Heliyon 10:e38118. https:\/\/doi.org\/10.1016\/j.heliyon.2024.e38118","journal-title":"Heliyon"},{"key":"693_CR12","doi-asserted-by":"publisher","first-page":"111592","DOI":"10.1016\/j.ejrad.2024.111592","volume":"177","author":"E Lanza","year":"2024","unstructured":"Lanza E, Ammirabile A, Francone M (2024) nnU-Net-based deep-learning for pulmonary embolism: detection, clot volume quantification, and severity correlation in the RSPECT dataset. Eur J Radiol 177:111592. https:\/\/doi.org\/10.1016\/j.ejrad.2024.111592","journal-title":"Eur J Radiol"},{"key":"693_CR13","doi-asserted-by":"publisher","first-page":"66","DOI":"10.21037\/qims-21-140","volume":"12","author":"H Zhang","year":"2022","unstructured":"Zhang H, Cheng Y, Chen Z et al (2022) Clot burden of acute pulmonary thromboembolism: comparison of two deep learning algorithms, Qanadli score, and Mastora score. Quant Imaging Med Surg 12:66\u201379. https:\/\/doi.org\/10.21037\/qims-21-140","journal-title":"Quant Imaging Med Surg"},{"key":"693_CR14","doi-asserted-by":"publisher","first-page":"86","DOI":"10.21037\/qims-23-322","volume":"14","author":"L Xi","year":"2024","unstructured":"Xi L, Xu F, Kang H et al (2024) Clot ratio, new clot burden score with deep learning, correlates with the risk stratification of patients with acute pulmonary embolism. Quant Imaging Med Surg 14:86\u201397. https:\/\/doi.org\/10.21037\/qims-23-322","journal-title":"Quant Imaging Med Surg"},{"key":"693_CR15","doi-asserted-by":"publisher","first-page":"1950","DOI":"10.21037\/qims-24-1412","volume":"15","author":"Y Qiao","year":"2025","unstructured":"Qiao Y, Gao Y, Chen Y et al (2025) Quantitative assessment and risk stratification of random acute pulmonary embolism cases using a deep learning model based on computed tomography pulmonary angiography images. Quant Imaging Med Surg 15:1950\u20131962. https:\/\/doi.org\/10.21037\/qims-24-1412","journal-title":"Quant Imaging Med Surg"},{"key":"693_CR16","doi-asserted-by":"publisher","first-page":"838","DOI":"10.21037\/atm-21-975","volume":"9","author":"X Li","year":"2021","unstructured":"Li X, Wang X, Yang X et al (2021) Preliminary study on artificial intelligence diagnosis of pulmonary embolism based on computer in-depth study. Ann Transl Med 9:838. https:\/\/doi.org\/10.21037\/atm-21-975","journal-title":"Ann Transl Med"},{"key":"693_CR17","doi-asserted-by":"publisher","first-page":"2293","DOI":"10.1007\/s10554-024-03222-8","volume":"40","author":"F Hagen","year":"2024","unstructured":"Hagen F, Vorberg L, Thamm F et al (2024) Improved detection of small pulmonary embolism on unenhanced computed tomography using an artificial intelligence-based algorithm\u2014a single centre retrospective study. Int J Cardiovasc Imaging 40:2293\u20132304. https:\/\/doi.org\/10.1007\/s10554-024-03222-8","journal-title":"Int J Cardiovasc Imaging"},{"key":"693_CR18","doi-asserted-by":"publisher","first-page":"105382","DOI":"10.1109\/ACCESS.2021.3099479","volume":"9","author":"H Yuan","year":"2021","unstructured":"Yuan H, Shao Y, Liu Z, Wang H (2021) An improved faster R-CNN for pulmonary embolism detection from CTPA images. IEEE Access 9:105382\u2013105392","journal-title":"IEEE Access"},{"key":"693_CR19","doi-asserted-by":"publisher","first-page":"e200254","DOI":"10.1148\/ryai.2021200254","volume":"3","author":"E Colak","year":"2021","unstructured":"Colak E, Kitamura FC, Hobbs SB et al (2021) The RSNA pulmonary embolism CT dataset. Radiol Artif Intell 3:e200254. https:\/\/doi.org\/10.1148\/ryai.2021200254","journal-title":"Radiol Artif Intell"},{"key":"693_CR20","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":"693_CR21","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 et al (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":"693_CR22","doi-asserted-by":"publisher","first-page":"3567","DOI":"10.1007\/s00330-020-06699-8","volume":"30","author":"W Liu","year":"2020","unstructured":"Liu W, Liu M, Guo X et al (2020) Evaluation of acute pulmonary embolism and clot burden on CTPA with deep learning. Eur Radiol 30:3567\u20133575. https:\/\/doi.org\/10.1007\/s00330-020-06699-8","journal-title":"Eur Radiol"},{"key":"693_CR23","doi-asserted-by":"publisher","first-page":"131","DOI":"10.5578\/tt.20239916","volume":"71","author":"N Ayd\u0131n","year":"2023","unstructured":"Ayd\u0131n N, Cihan \u00c7, \u00c7elik \u00d6 et al (2023) [Segmentation of acute pulmonary embolism in computed tomography pulmonary angiography using the deep learning method]. Tuberk Toraks 71:131\u2013137. https:\/\/doi.org\/10.5578\/tt.20239916","journal-title":"Tuberk Toraks"},{"key":"693_CR24","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-0266-y","volume":"3","author":"S-C Huang","year":"2020","unstructured":"Huang S-C, Kothari T, Banerjee I et al (2020) PENet-a scalable deep-learning model for automated diagnosis of pulmonary embolism using volumetric CT imaging. NPJ Digit Med 3:61. https:\/\/doi.org\/10.1038\/s41746-020-0266-y","journal-title":"NPJ Digit Med"},{"key":"693_CR25","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 et al (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":"693_CR26","doi-asserted-by":"publisher","first-page":"110245","DOI":"10.1016\/j.clinimag.2024.110245","volume":"113","author":"A Ayobi","year":"2024","unstructured":"Ayobi A, Chang PD, Chow DS et al (2024) Performance and clinical utility of an artificial intelligence-enabled tool for pulmonary embolism detection. Clin Imaging 113:110245. https:\/\/doi.org\/10.1016\/j.clinimag.2024.110245","journal-title":"Clin Imaging"},{"key":"693_CR27","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1186\/s13244-023-01454-1","volume":"14","author":"E Langius-Wiffen","year":"2023","unstructured":"Langius-Wiffen E, de Jong PA, Hoesein FAM et al (2023) Retrospective batch analysis to evaluate the diagnostic accuracy of a clinically deployed AI algorithm for the detection of acute pulmonary embolism on CTPA. Insights Imaging 14:102. https:\/\/doi.org\/10.1186\/s13244-023-01454-1","journal-title":"Insights Imaging"},{"key":"693_CR28","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1177\/10815589241258968","volume":"72","author":"A Talon","year":"2024","unstructured":"Talon A, Puri C, Mccreary DL et al (2024) Single-center outcomes of artificial intelligence in management of pulmonary embolism and pulmonary embolism response team activation. J Invest Med 72:652\u2013660. https:\/\/doi.org\/10.1177\/10815589241258968","journal-title":"J Invest Med"},{"key":"693_CR29","doi-asserted-by":"publisher","unstructured":"DePry EX, Parmar V, Rajendran S et al (2025) Performance of FDA-approved AI algorithms in detecting acute pulmonary embolism on computed tomographic pulmonary angiography (CTPA): a meta-analysis of real-world retrospective studies. Cureus. https:\/\/doi.org\/10.7759\/cureus.94391","DOI":"10.7759\/cureus.94391"},{"key":"693_CR30","unstructured":"Medical Device Regulation. (2017) MDR\u2014Article 5\u2014Placing on the market and putting into service. Available via https:\/\/www.medical-device-regulation.eu\/mdr-article-5-placing-on-the-market-and-putting-into-service\/. Accessed 3 Nov 2025"},{"key":"693_CR31","unstructured":"European Parliament and the Council of the European Union (2017) Regulation (EU) 2017\/745 of the European Parliament and of the Council of 5 April 2017 on medical devices, amending Directive 2001\/83\/EC, Regulation (EC) No 178\/2002 and Regulation (EC) No 1223\/2009 and repealing Council Directives 90\/385\/EEC and 93\/42\/EEC. Available via https:\/\/eur-lex.europa.eu\/legal-content\/EN\/TXT\/HTML\/?uri=CELEX:32017R0745. Accessed 3 Nov 2025"}],"container-title":["European Radiology Experimental"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-026-00693-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s41747-026-00693-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-026-00693-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T09:53:02Z","timestamp":1772617982000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s41747-026-00693-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,4]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["693"],"URL":"https:\/\/doi.org\/10.1186\/s41747-026-00693-3","relation":{},"ISSN":["2509-9280"],"issn-type":[{"value":"2509-9280","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,4]]},"assertion":[{"value":"31 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 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":"This retrospective study was conducted using fully anonymized imaging data retrieved from the institutional PACS. No identifiable information was collected, and no data were transferred outside the institution. According to the internal guidelines of Humanitas IRCCS Research Hospital Institutional Review Board (IRB), studies involving the use of pre-existing, fully anonymized data for non-interventional research purposes do not require formal IRB protocol submission and are considered implicitly approved. Therefore, ethical approval and informed consent were not required for this study, in accordance with institutional policy and the Declaration of Helsinki.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"According to the internal guidelines of Humanitas IRCCS Research Hospital Institutional Review Board (IRB), studies involving the use of pre-existing, fully anonymized data for non-interventional research purposes do not require formal IRB protocol submission and are considered implicitly approved. Therefore, ethical approval and informed consent were not required for this study, in accordance with institutional policy and the Declaration of Helsinki.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"EL, AA, and AV are members of the Scientific Editorial Board of\n                      European Radiology Experimental\n                      , and as such, they did not participate in the selection or review processes for this article. The remaining authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"23"}}