{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T06:12:35Z","timestamp":1788415955757,"version":"build-2803163510"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T00:00:00Z","timestamp":1788393600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate preoperative risk assessment is crucial for patients undergoing hepatic resection for hepatocellular carcinoma (HCC). Conventional prediction methods are limited by the inability to capture complex relationships among multiple factors, and existing deep learning (DL) approaches focus on individual surgical outcomes. In this study, we developed and evaluated a DL model that integrates preoperative contrast-enhanced computed tomography (CT) imaging features and clinical variables to predict intraoperative blood loss and major postoperative complications.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We analyzed data of 622 patients who underwent initial hepatectomy for solitary HCC between 2006 and 2021. Patients were randomly assigned to training (n = 498), validation (n = 62), and test (n = 62) cohorts. Combining convolutional neural networks and multilayer perceptron architectures, the DL model evaluated both intraoperative blood loss and postoperative complication risks. Patients were classified into major and minor intraoperative blood loss groups. Postoperative complications were defined as events of Clavien\u2013Dindo grade IIIa or higher. Model performance was assessed via the area under the receiver operating characteristic curve (AUC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>For predicting major intraoperative blood loss, the model achieved AUCs of 0.81 and 0.80 in the validation and test cohorts, respectively. Furthermore, predicted blood loss significantly correlated with actual blood loss (Spearman\u2019s \u03c1 = 0.500, p &amp;lt; 0.001). For predicting postoperative complications, the model demonstrated AUCs of 0.65 in the validation cohort and 0.63 in the test cohort. Patients stratified as high risk exhibited significantly higher complication rates than those in the low-risk group across both cohorts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The integrated DL model enabled the simultaneous prediction of intraoperative blood loss and postoperative complications. This framework may contribute to comprehensive preoperative surgical risk assessment, although further validation is required to confirm its clinical utility.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1910921","type":"journal-article","created":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T05:14:58Z","timestamp":1788412498000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning model using contrast-enhanced CT imaging features and clinical variables to predict surgical risk after hepatic resection for hepatocellular carcinoma"],"prefix":"10.3389","volume":"16","author":[{"given":"Kimika","family":"Kato","sequence":"first","affiliation":[{"name":"Department of Hepatobiliary\u2013Pancreatic Surgery, Osaka Metropolitan University Graduate School of Medicine","place":["Osaka, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasuhito","family":"Mitsuyama","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Osaka Metropolitan University Graduate School of Medicine","place":["Osaka, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroji","family":"Shinkawa","sequence":"additional","affiliation":[{"name":"Department of Hepatobiliary\u2013Pancreatic Surgery, Osaka Metropolitan University Graduate School of Medicine","place":["Osaka, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takuma","family":"Okada","sequence":"additional","affiliation":[{"name":"Department of Hepatobiliary\u2013Pancreatic Surgery, Osaka Metropolitan University Graduate School of Medicine","place":["Osaka, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atsushi","family":"Sugimoto","sequence":"additional","affiliation":[{"name":"Department of Hepatobiliary\u2013Pancreatic Surgery, Osaka Metropolitan University Graduate School of Medicine","place":["Osaka, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryota","family":"Tanaka","sequence":"additional","affiliation":[{"name":"Department of Hepatobiliary\u2013Pancreatic Surgery, Osaka Metropolitan University Graduate School of Medicine","place":["Osaka, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sadaaki","family":"Nishimura","sequence":"additional","affiliation":[{"name":"Department of Hepatobiliary\u2013Pancreatic Surgery, Osaka Metropolitan University Graduate School of Medicine","place":["Osaka, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Tauchi","sequence":"additional","affiliation":[{"name":"Department of Hepatobiliary\u2013Pancreatic Surgery, Osaka Metropolitan University Graduate School of Medicine","place":["Osaka, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masahiko","family":"Kinoshita","sequence":"additional","affiliation":[{"name":"Department of Hepatobiliary\u2013Pancreatic Surgery, Osaka Metropolitan University Graduate School of Medicine","place":["Osaka, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Genki","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Department of Hepatobiliary\u2013Pancreatic Surgery, Osaka Metropolitan University Graduate School of Medicine","place":["Osaka, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kohei","family":"Nishio","sequence":"additional","affiliation":[{"name":"Department of Hepatobiliary\u2013Pancreatic Surgery, Osaka Metropolitan University Graduate School of Medicine","place":["Osaka, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takeaki","family":"Ishizawa","sequence":"additional","affiliation":[{"name":"Department of Hepatobiliary\u2013Pancreatic Surgery, Osaka Metropolitan University Graduate School of Medicine","place":["Osaka, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,3]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1097\/01.SLA.0000029003.66466.B3","article-title":"Improvement in perioperative outcome after hepatic resection: analysis of 1,803 consecutive cases over the past decade","volume":"236","author":"Jarnagin","year":"2002","journal-title":"Ann Surg"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.3390\/cancers16101938","article-title":"Significance of prediction models for post-hepatectomy liver failure based on Type IV collagen 7s domain in patients with hepatocellular carcinoma","volume":"16","author":"Okada","year":"2024","journal-title":"Cancers (Basel)"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.hpb.2025.01.010","article-title":"Impact of intraoperative blood loss on postoperative morbidity after liver resection for primary and secondary liver cancer","volume":"27","author":"Altaf","year":"2025","journal-title":"HPB (Oxford)"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.hpb.2025.08.006","article-title":"The surgical burden score: a novel continuous metric to predict postoperative complications after hepatectomy for hepatocellular carcinoma","volume":"27","author":"Akabane","year":"2025","journal-title":"HPB (Oxford)"},{"key":"B5","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.jhep.2011.12.001","article-title":"EASL Clinical Practice Guidelines: management of hepatocellular carcinoma","volume":"69","year":"2018","journal-title":"J Hepatol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1007\/s00268-020-05686-w","article-title":"Predictive value of the age-adjusted Charlson comorbidity index for outcomes after hepatic resection of hepatocellular carcinoma","volume":"44","author":"Shinkawa","year":"2020","journal-title":"World J Surg"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1093\/postmj\/qgad087","article-title":"Risk factors of major bleeding detected by machine learning method in patients undergoing liver resection with controlled low central venous pressure technique","volume":"99","author":"Liu","year":"2023","journal-title":"Postgrad Med J"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.suronc.2020.02.004","article-title":"Future liver remnant function as a predictor of postoperative morbidity following liver resection for hepatocellular carcinoma\u2014A risk factor analysis","volume":"33","author":"Bl\u00fcthner","year":"2020","journal-title":"Surg Oncol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0000000000005028","article-title":"Risk factors for early mortality after hepatectomy for hepatocellular carcinoma","volume":"95","author":"Lee","year":"2016","journal-title":"Med (Baltim)"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2021203614","article-title":"Preoperative CT for characterization of aggressive macrotrabecular-massive subtype and vessels that encapsulate tumor clusters pattern in hepatocellular carcinoma","volume":"300","author":"Feng","year":"2021","journal-title":"Radiology"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15072140","article-title":"Deep learning model based on contrast-enhanced computed tomography imaging to predict postoperative early recurrence after the curative resection of a solitary hepatocellular carcinoma","volume":"15","author":"Kinoshita","year":"2023","journal-title":"Cancers (Basel)"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1111\/hepr.70055","article-title":"Individualized prognostication based on deep-learning models using computed tomography as an imaging biomarker after hepatocellular carcinoma resection","volume":"56","author":"Shinkawa","year":"2026","journal-title":"Hepatol Res"},{"key":"B13","doi-asserted-by":"publisher","first-page":"90","DOI":"10.4251\/wjgo.v16.i1.90","article-title":"Development and validation of a machine learning-based early prediction model for massive intraoperative bleeding in patients with primary hepatic malignancies","volume":"16","author":"Li","year":"2024","journal-title":"World J Gastrointest Oncol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinane.2021.110444","article-title":"Predicting intraoperative bleeding in patients undergoing a hepatectomy using multiple machine learning and deep learning techniques","volume":"74","author":"Xue","year":"2021","journal-title":"J Clin Anesth"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2023.1154314","article-title":"A deep learning model for prediction of posthepatectomy liver failure after hemihepatectomy using preoperative contrast-enhanced computed tomography: a retrospective study","volume":"10","author":"Xu","year":"2023","journal-title":"Front Med (Lausanne)"},{"key":"B16","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.hpb.2024.12.015","article-title":"Machine learning-based prediction model for bile leak following hepatectomy for liver cancer","volume":"27","author":"Altaf","year":"2025","journal-title":"HPB (Oxford)"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejso.2024.109462","article-title":"Preoperative prediction of post hepatectomy liver failure after surgery for hepatocellular carcinoma on CT-scan by machine learning and radiomics analyses","volume":"51","author":"Famularo","year":"2025","journal-title":"Eur J Surg Oncol"},{"key":"B18","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW50498.2020.00359","article-title":"RandAugment: practical automated data augmentation with a reduced search space","author":"Cubuk","year":"2020"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1097\/01.sla.0000133083.54934.ae","article-title":"Classification of surgical complications: a new proposal with evaluation in a cohort of 6336 patients and results of a survey","volume":"240","author":"Dindo","year":"2004","journal-title":"Ann Surg"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.surg.2010.12.002","article-title":"Bile leakage after hepatobiliary and pancreatic surgery: a definition and grading of severity by the International Study Group of Liver Surgery","volume":"149","author":"Koch","year":"2011","journal-title":"Surgery"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.surg.2010.10.001","article-title":"Posthepatectomy liver failure: a definition and grading by the International Study Group of Liver Surgery (ISGLS)","volume":"149","author":"Rahbari","year":"2011","journal-title":"Surgery"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1086\/501620","article-title":"Guideline for prevention of surgical site infection, 1999. Hospital Infection Control Practices Advisory Committee","volume":"20","author":"Mangram","year":"1999","journal-title":"Infect Control Hosp Epidemiol"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.164.4.7726040","article-title":"Dual-phase helical CT of the liver: value of arterial phase scans in the detection of small (\u22641.5 cm) malignant hepatic neoplasms","volume":"164","author":"Hollett","year":"1995","journal-title":"AJR Am J Roentgenol"},{"key":"B24","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"B25","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.308","article-title":"Rethinking the Inception architecture for computer vision","author":"Szegedy","year":"2016"},{"key":"B26","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.243","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"B27","article-title":"PyTorch: an imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"B28","article-title":"Nervus: a comprehensive deep learning classification, regression, and prognostication tool for both medical image and clinical data analysis","volume-title":"arXiv preprint arXiv:2212.11113","author":"Matsumoto","year":"2022"},{"key":"B29","article-title":"A method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"B30","doi-asserted-by":"crossref","DOI":"10.1109\/WACV.2018.00097","article-title":"Grad-CAM++: generalized gradient-based visual explanations for deep convolutional networks","author":"Chattopadhay","year":"2018"},{"key":"B31","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1002\/bjs.11351","article-title":"Performance of a modified three-level classification in stratifying open liver resection procedures in terms of complexity and postoperative morbidity","volume":"107","author":"Kawaguchi","year":"2020","journal-title":"Br J Surg"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1097\/SLA.0000000000002176","article-title":"Difficulty of laparoscopic liver resection: proposal for a new classification","volume":"267","author":"Kawaguchi","year":"2018","journal-title":"Ann Surg"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1007\/s00268-010-0495-3","article-title":"Risk factors for massive bleeding during major hepatectomy","volume":"34","author":"Shirabe","year":"2010","journal-title":"World J Surg"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/j.gassur.2003.09.012","article-title":"Impact of steatosis on perioperative outcome following hepatic resection","volume":"7","author":"Kooby","year":"2003","journal-title":"J Gastrointest Surg"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1002\/jhbp.166","article-title":"A novel difficulty scoring system for laparoscopic liver resection","volume":"21","author":"Ban","year":"2014","journal-title":"J Hepatobiliary Pancreat Sci"},{"key":"B37","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1186\/s12876-026-04914-2","article-title":"Liver CT-based composite biomarkers can identify MASH and steatosis grade in people with obesity prior to bariatric surgery: a retrospective study","volume":"26","author":"Zhang","year":"2026","journal-title":"BMC Gastroenterol"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1245\/s10434-020-09143-9","article-title":"Computed tomography-derived liver surface nodularity and sarcopenia as prognostic factors in patients with resectable metabolic syndrome-related hepatocellular carcinoma","volume":"28","author":"Seror","year":"2021","journal-title":"Ann Surg Oncol"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1016\/j.jamcollsurg.2014.11.027","article-title":"Texture analysis of preoperative CT images for prediction of postoperative hepatic insufficiency: a preliminary study","volume":"220","author":"Simpson","year":"2015","journal-title":"J Am Coll Surg"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1910921\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T05:15:00Z","timestamp":1788412500000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1910921\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,3]]},"references-count":39,"alternative-id":["10.3389\/fonc.2026.1910921"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1910921","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,3]]},"article-number":"1910921"}}