{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T16:56:38Z","timestamp":1776876998579,"version":"3.51.2"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T00:00:00Z","timestamp":1754265600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T00:00:00Z","timestamp":1754265600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100007052","name":"Universit\u00e0 degli Studi di Verona","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007052","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Digit Imaging. Inform. med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Pancreatic ductal adenocarcinoma (PDAC) exhibits high metastatic potential, with distinct prognoses based on metastatic sites. Radiomics enables quantitative imaging analysis for predictive modeling. To evaluate the feasibility of radiomic models in predicting PDAC metastatic patterns, specifically distinguishing between hepatic and pulmonary metastases. This retrospective study included 115 PDAC patients with either liver (\n                    <jats:italic>n<\/jats:italic>\n                    \u2009=\u200994) or lung (\n                    <jats:italic>n<\/jats:italic>\n                    \u2009=\u200921) metastases. Radiomic features were extracted from pancreatic arterial and venous phase CT scans of primary tumors using PyRadiomics. Two radiologists independently segmented tumors for inter-reader reliability assessment. Features with ICC\u2009&gt;\u20090.9 underwent LASSO regularization for feature selection. Class imbalance was addressed using SMOTE and class weighting. Model performance was evaluated using fivefold cross-validation and bootstrap resampling. The multivariate logistic regression model achieved an AUC-ROC of 0.831 (95% CI: 0.752\u20130.910). At the optimal threshold, sensitivity was 0.762 (95% CI: 0.659\u20130.865) and specificity was 0.787 (95% CI: 0.695\u20130.879). The negative predictive value for lung metastases was 0.810 (95% CI: 0.734\u20130.886). LargeDependenceEmphasis showed a trend toward significance (\n                    <jats:italic>p<\/jats:italic>\n                    \u2009=\u20090.0566) as a discriminative feature. Precision was 0.842, recall 0.762, and F1 score 0.800. Radiomic analysis of primary pancreatic tumors demonstrates potential for predicting hepatic versus pulmonary metastatic patterns. The high negative predictive value for lung metastases may support clinical decision-making. External validation is essential before clinical implementation. These findings from a single-center study require confirmation in larger, multicenter cohorts.\n                  <\/jats:p>","DOI":"10.1007\/s10278-025-01627-y","type":"journal-article","created":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T16:00:03Z","timestamp":1754323203000},"page":"1536-1546","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Can Machine Learning Predict Metastatic Sites in Pancreatic Ductal Adenocarcinoma? A Radiomic Analysis"],"prefix":"10.1007","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9846-8145","authenticated-orcid":false,"given":"F.","family":"Spoto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R.","family":"De Robertis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"N.","family":"Cardobi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A.","family":"Garofano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"L.","family":"Messineo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"E.","family":"Lucin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Milella","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"D\u2019Onofrio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,4]]},"reference":[{"key":"1627_CR1","doi-asserted-by":"publisher","unstructured":"Dyba T, et al. The European cancer burden in 2020: Incidence and mortality estimates for 40 countries and 25 major cancers. https:\/\/doi.org\/10.1016\/j.ejca.2021.07.039","DOI":"10.1016\/j.ejca.2021.07.039"},{"key":"1627_CR2","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21820","author":"RL Siegel","year":"2024","unstructured":"Siegel RL, et al. Cancer statistics, 2024. https:\/\/doi.org\/10.3322\/caac.21820","journal-title":"Cancer statistics"},{"key":"1627_CR3","doi-asserted-by":"publisher","unstructured":"Orth M, et al. Pancreatic ductal adenocarcinoma: biological hallmarks, current status, and future perspectives. https:\/\/doi.org\/10.1186\/s13014-019-1345-6","DOI":"10.1186\/s13014-019-1345-6"},{"key":"1627_CR4","doi-asserted-by":"publisher","unstructured":"Guti\u00e9rrez ML, et al. Genomic Heterogeneity of Pancreatic Ductal Adenocarcinoma and Its Clinical Impact. https:\/\/doi.org\/10.3390\/cancers13174451","DOI":"10.3390\/cancers13174451"},{"key":"1627_CR5","doi-asserted-by":"publisher","unstructured":"Konstantinidis IT, et al. Pancreatic ductal adenocarcinoma: is there a survival difference for R1 resections versus locally advanced unresectable tumors? https:\/\/doi.org\/10.1097\/SLA.0b013e318263da2f","DOI":"10.1097\/SLA.0b013e318263da2f"},{"key":"1627_CR6","doi-asserted-by":"publisher","unstructured":"Zheng B, et al. Primary Recurrence in the Lung is Related to Favorable Prognosis in Patients with Pancreatic Cancer. https:\/\/doi.org\/10.1007\/s00268-017-4068-6","DOI":"10.1007\/s00268-017-4068-6"},{"key":"1627_CR7","doi-asserted-by":"publisher","unstructured":"Katz MH, et al. Long-term survival after multidisciplinary management of resected pancreatic adenocarcinoma. https:\/\/doi.org\/10.1245\/s10434-008-0295-2","DOI":"10.1245\/s10434-008-0295-2"},{"key":"1627_CR8","doi-asserted-by":"publisher","unstructured":"Lovecek M, et al. Different clinical presentations of metachronous pulmonary metastases after resection of pancreatic ductal adenocarcinoma. https:\/\/doi.org\/10.3748\/wjg.v23.i35.6420","DOI":"10.3748\/wjg.v23.i35.6420"},{"key":"1627_CR9","doi-asserted-by":"publisher","unstructured":"Oweira H, et al. Prognostic value of site-specific metastases in pancreatic adenocarcinoma. https:\/\/doi.org\/10.3748\/wjg.v23.i10.1872","DOI":"10.3748\/wjg.v23.i10.1872"},{"key":"1627_CR10","doi-asserted-by":"publisher","unstructured":"Decoster C, et al. Heterogeneity of metastatic pancreatic adenocarcinoma: Lung metastasis show better prognosis than liver metastasis. https:\/\/doi.org\/10.18632\/oncotarget.98611254.","DOI":"10.18632\/oncotarget.98611254"},{"key":"1627_CR11","doi-asserted-by":"publisher","unstructured":"Ebrahimi A, et al. Do patients with metastatic pancreatic adenocarcinoma to the lung have improved survival? https:\/\/doi.org\/10.1002\/cam4.5751","DOI":"10.1002\/cam4.5751"},{"key":"1627_CR12","doi-asserted-by":"publisher","unstructured":"Damanakis AI, et al. Proposal for a definition of \"Oligometastatic disease in pancreatic cancer\". https:\/\/doi.org\/10.1186\/s12885-019-6448-9","DOI":"10.1186\/s12885-019-6448-9"},{"key":"1627_CR13","doi-asserted-by":"publisher","unstructured":"Renz BW, et al. Oligometastatic Disease in Pancreatic Cancer - How to Proceed? https:\/\/doi.org\/10.1159\/000455027","DOI":"10.1159\/000455027"},{"key":"1627_CR14","doi-asserted-by":"publisher","unstructured":"Guerra F, et al. Metastases or primary recurrence to the lung is related to improved survival of pancreatic cancer. https:\/\/doi.org\/10.1016\/j.ejso.2020.06.013","DOI":"10.1016\/j.ejso.2020.06.013"},{"key":"1627_CR15","doi-asserted-by":"publisher","unstructured":"Arnaoutakis GJ, et al. Pulmonary resection for isolated pancreatic adenocarcinoma metastasis. https:\/\/doi.org\/10.1007\/s11605-011-1607-6","DOI":"10.1007\/s11605-011-1607-6"},{"key":"1627_CR16","doi-asserted-by":"publisher","unstructured":"Furuse J, et al. Development of chemotherapy and significance of conversion surgery in unresectable pancreatic cancer. https:\/\/doi.org\/10.1002\/hbp.12633","DOI":"10.1002\/hbp.12633"},{"key":"1627_CR17","doi-asserted-by":"publisher","unstructured":"Thomas RM, et al. Selective reoperation for locally recurrent or metastatic pancreatic ductal adenocarcinoma. https:\/\/doi.org\/10.1007\/s11605-012-1969-4","DOI":"10.1007\/s11605-012-1969-4"},{"key":"1627_CR18","doi-asserted-by":"publisher","unstructured":"Yasuda S, et al. Essential updates 2021\/2022: Surgical outcomes of oligometastasis in pancreatic ductal adenocarcinoma. https:\/\/doi.org\/10.1002\/ags3.12655","DOI":"10.1002\/ags3.12655"},{"key":"1627_CR19","doi-asserted-by":"publisher","unstructured":"Homma Y, et al. Outcomes of lung metastasis from pancreatic cancer: a nationwide multicenter analysis. https:\/\/doi.org\/10.1002\/jhbp.1122","DOI":"10.1002\/jhbp.1122"},{"key":"1627_CR20","doi-asserted-by":"publisher","unstructured":"Yun WG, et al. Can surgical resection of metastatic lesions Be beneficial to PDAC patients with isolated lung metastasis? https:\/\/doi.org\/10.3390\/cancers14092067","DOI":"10.3390\/cancers14092067"},{"key":"1627_CR21","doi-asserted-by":"publisher","unstructured":"Anghel C, et al. Pancreatic Adenocarcinoma: Imaging Modalities and AI in Analyzing CT and MRI Images. https:\/\/doi.org\/10.3390\/diagnostics14040438","DOI":"10.3390\/diagnostics14040438"},{"key":"1627_CR22","doi-asserted-by":"publisher","unstructured":"Yip SS, et al. Applications and limitations of radiomics. https:\/\/doi.org\/10.1088\/0031-9155\/61\/13\/R150","DOI":"10.1088\/0031-9155\/61\/13\/R150"},{"key":"1627_CR23","doi-asserted-by":"publisher","unstructured":"Gillies RJ, et al. Radiomics: Images Are More than Pictures, They Are Data. https:\/\/doi.org\/10.1148\/radiol.2015151169","DOI":"10.1148\/radiol.2015151169"},{"key":"1627_CR24","doi-asserted-by":"publisher","unstructured":"Marti-Bonmati L, et al. Pancreatic cancer, radiomics and artificial intelligence. https:\/\/doi.org\/10.1259\/bjr.20220072","DOI":"10.1259\/bjr.20220072"},{"key":"1627_CR25","doi-asserted-by":"publisher","unstructured":"Van Griethuysen JJM, et al. Computational Radiomics System to Decode the Radiographic Phenotype. https:\/\/doi.org\/10.1158\/0008-5472.CAN-17-0339","DOI":"10.1158\/0008-5472.CAN-17-0339"},{"key":"1627_CR26","doi-asserted-by":"publisher","unstructured":"Zwanenburg A, et al. The Image Biomarker Standardization Initiative. https:\/\/doi.org\/10.1148\/radiol.2020191145","DOI":"10.1148\/radiol.2020191145"},{"key":"1627_CR27","doi-asserted-by":"publisher","unstructured":"Reichert M, et al. Regulation of Epithelial Plasticity Determines Metastatic Organotropism in Pancreatic Cancer. https:\/\/doi.org\/10.1016\/j.devcel.2018.04.025","DOI":"10.1016\/j.devcel.2018.04.025"},{"key":"1627_CR28","doi-asserted-by":"publisher","unstructured":"Papargyriou A, Reichert M. The Biology in the Pattern: Metastatic Organotropism and Clinical Outcome Depend on DNA Damage Response and Immune Interactions in Pancreatic Cancer.\u00a0https:\/\/doi.org\/10.1158\/0008-5472.","DOI":"10.1158\/0008-5472"},{"key":"1627_CR29","doi-asserted-by":"publisher","unstructured":"Comprehensive Molecular Characterization of Metastatic Pancreatic Cancer. https:\/\/doi.org\/10.1016\/j.ccell.2021.04.005","DOI":"10.1016\/j.ccell.2021.04.005"},{"key":"1627_CR30","doi-asserted-by":"publisher","unstructured":"Koay EJ, et al. A Visually Apparent CT Imaging Feature Identifies Biophysical Subtypes of PDAC. https:\/\/doi.org\/10.1158\/1078-0432.CCR-18-0522","DOI":"10.1158\/1078-0432.CCR-18-0522"},{"key":"1627_CR31","doi-asserted-by":"publisher","unstructured":"Kaissis G, et al. A machine learning model for prediction in pancreatic ductal adenocarcinoma. https:\/\/doi.org\/10.1007\/s00330-019-06176-x","DOI":"10.1007\/s00330-019-06176-x"},{"key":"1627_CR32","doi-asserted-by":"publisher","unstructured":"Yachida S, et al. Clinical significance of the genetic landscape of pancreatic cancer. https:\/\/doi.org\/10.1158\/1078-0432.CCR-12-1215","DOI":"10.1158\/1078-0432.CCR-12-1215"},{"key":"1627_CR33","doi-asserted-by":"publisher","unstructured":"Dreyer SB, et al. Pancreatic Cancer Genomes: Clinical Management and Therapeutic Development. https:\/\/doi.org\/10.1158\/1078-0432.CCR-16-2411","DOI":"10.1158\/1078-0432.CCR-16-2411"},{"key":"1627_CR34","doi-asserted-by":"publisher","unstructured":"Wu J, et al. Intratumoral heterogeneity of pancreatic ductal adenocarcinoma. https:\/\/doi.org\/10.1016\/j.canlet.2020.10.023","DOI":"10.1016\/j.canlet.2020.10.023"},{"key":"1627_CR35","doi-asserted-by":"publisher","unstructured":"Pihlak R, et al. Germline variants in pancreatic cancer and therapeutic implications. https:\/\/doi.org\/10.1016\/j.ctrv.2017.02.010","DOI":"10.1016\/j.ctrv.2017.02.010"},{"key":"1627_CR36","doi-asserted-by":"publisher","unstructured":"Park W, et al. Genomic Methods Identify Homologous Recombination Deficiency in Pancreas Cancer. https:\/\/doi.org\/10.1158\/1078-0432.CCR-19-3702","DOI":"10.1158\/1078-0432.CCR-19-3702"},{"key":"1627_CR37","doi-asserted-by":"publisher","unstructured":"Shen R, et al. Evaluating Pancreatic Cancer Subtypes Using Integrated Genomic Profiling. https:\/\/doi.org\/10.1158\/0008-5472.CAN-20-2133","DOI":"10.1158\/0008-5472.CAN-20-2133"}],"container-title":["Journal of Imaging Informatics in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-025-01627-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-025-01627-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-025-01627-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T16:22:13Z","timestamp":1776874933000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10278-025-01627-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,4]]},"references-count":37,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["1627"],"URL":"https:\/\/doi.org\/10.1007\/s10278-025-01627-y","relation":{},"ISSN":["2948-2933"],"issn-type":[{"value":"2948-2933","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,4]]},"assertion":[{"value":"27 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 July 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 July 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 August 2025","order":4,"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 on anonymized imaging data in accordance with institutional guidelines.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval"}},{"value":"Informed consent has been obtained from patients for the use of diagnostic images (CT) in accordance with the ethical principles established by the Declaration of Helsinki.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"Patients provided informed consent allowing the extraction and publication of anonymized data from their imaging studies for research purposes.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Publish"}},{"value":"The authors declare that they have no competing interests.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}]}}