{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:01:14Z","timestamp":1792785674285,"version":"4.5.0"},"reference-count":30,"publisher":"IOP Publishing","issue":"18","license":[{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"},{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"}],"funder":[{"name":"the Bagui Youth Top Talent Training Program, Qihang Scholar Program","award":["KX201403709"],"award-info":[{"award-number":["KX201403709"]}]},{"name":"Jiangmen Basic and Applied Basic Research Project","award":["2520002000123"],"award-info":[{"award-number":["2520002000123"]}]},{"name":"GUAT Special Research Project on the Strategic Development of Distinctive Interdisciplinary Fields","award":["TS2024231"],"award-info":[{"award-number":["TS2024231"]}]},{"name":"Special Clinical Research Fund Project of Guangdong Medical Association","award":["2025YX-C1005"],"award-info":[{"award-number":["2025YX-C1005"]}]},{"name":"the National Natural Science Foundation of China","award":["62176104"],"award-info":[{"award-number":["62176104"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Jiangmen Science and Technology Plan Program","award":["2024YL01033"],"award-info":[{"award-number":["2024YL01033"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2026,9,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective.<\/jats:italic>\n                    To develop and validate a cross-modal interactive fusion (CMIF) framework that addresses the limitations of single-modality imaging by integrating complementary CT and MRI features for noninvasive preoperative prediction of high-grade hepatocellular carcinoma (HCC).\n                    <jats:italic>Approach.<\/jats:italic>\n                    To address the clinical need for noninvasive preoperative identification of high-grade HCC, we retrospectively analyzed paired CT and MRI data from 270 pathologically confirmed HCC patients across four centers. Leveraging the complementary anatomical and tumor-heterogeneity information provided by CT and MRI, we developed a CMIF framework. The framework used a frozen DINOv2 backbone for CT and MRI feature extraction, a lightweight multilayer perceptron for task-specific adaptation, and a cross-modal feature alignment and fusion (CMAF) module to model bidirectional CT\u2013MRI interactions and generate fused representations for histological grading. The model was evaluated in internal and external validation cohorts and compared with unimodal models and representative multimodal fusion methods.\n                    <jats:italic>Main results.<\/jats:italic>\n                    The proposed CMIF model achieved an area under the receiver operating characteristic curve (AUC) of 0.760 in the internal validation cohort and AUCs of 0.754 and 0.790 in two external validation cohorts. Compared with unimodal models and alternative fusion methods, CMIF showed more stable performance across validation cohorts. Ablation experiments further indicated that both DINOv2-based feature extraction and the cross-modal fusion module contributed to the improvement in predictive performance.\n                    <jats:italic>Significance.<\/jats:italic>\n                    The proposed framework provides a noninvasive and quantitative approach for preoperative HCC histological grading. By explicitly modeling complementary CT and MRI information, CMIF may assist radiologists in identification of high-grade tumors and provide valuable support for individualized preoperative treatment planning.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/aea5d1","type":"journal-article","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T22:54:04Z","timestamp":1789080844000},"page":"185008","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross-modal interactive fusion framework for preoperative histological grading of hepatocellular carcinoma"],"prefix":"10.1088","volume":"71","author":[{"given":"Siyun","family":"Wang","sequence":"first","affiliation":[{"name":"School of Automation, Guangxi University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"given":"Bao","family":"Feng","sequence":"additional","affiliation":[{"name":"Laboratory of Artificial Intelligence of Biomedicine, Guilin University of Aerospace Technology"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"methodology","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"given":"Zhaole","family":"Yu","sequence":"additional","affiliation":[{"name":"Laboratory of Artificial Intelligence of Biomedicine, Guilin University of Aerospace Technology"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1518-6074","authenticated-orcid":true,"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"Laboratory of Artificial Intelligence of Biomedicine, Guilin University of Aerospace Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuewei","family":"Kang","sequence":"additional","affiliation":[{"name":"Laboratory of Artificial Intelligence of Biomedicine, Guilin University of Aerospace Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yehang","family":"Chen","sequence":"additional","affiliation":[{"name":"Laboratory of Artificial Intelligence of Biomedicine, Guilin University of Aerospace Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunxuan","family":"Xie","sequence":"additional","affiliation":[{"name":"Jiangmen Central Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaqin","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Fifth Affiliated Hospital of Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Lin","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital of Shenzhen University, Health Science Center, ShenzhenSecond People\u2019s Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangrong","family":"Yu","sequence":"additional","affiliation":[{"name":"Zhuhai People\u2019s Hospital Medical Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhixin","family":"Luo","sequence":"additional","affiliation":[{"name":"Jiangmen Central Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Cui","sequence":"additional","affiliation":[{"name":"Jiangmen Central Hospital"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"data-curation","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"given":"Enming","family":"Cui","sequence":"additional","affiliation":[{"name":"Jiangmen Central Hospital"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"data-curation","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1600-8176","authenticated-orcid":true,"given":"Xisheng","family":"Dai","sequence":"additional","affiliation":[{"name":"School of Automation, Guangxi University of Science and Technology"},{"name":"Guangdong University of Finance"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"funding-acquisition","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]}],"member":"266","published-online":{"date-parts":[[2026,9,24]]},"reference":[{"key":"pmbaea5d1bib1","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/j.livres.2023.11.004","type":"journal-article","article-title":"Hepatocellular carcinoma recurrence: predictors and management","volume":"7","author":"Abdelhamed","year":"2023","journal-title":"Liver Res."},{"key":"pmbaea5d1bib2","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.livres.2024.05.004","type":"journal-article","article-title":"Hepatitis B virus as a risk factor for hepatocellular carcinoma: there is still much work to do","volume":"8","author":"Abdelhamed","year":"2024","journal-title":"Liver Res."},{"key":"pmbaea5d1bib3","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","type":"journal-article","article-title":"Multimodal machine learning: a survey and taxonomy","volume":"41","author":"Baltrusaitis","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"pmbaea5d1bib4","first-page":"9650","type":"conference-proceedings","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"key":"pmbaea5d1bib5","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1148\/radiol.2018181494","type":"journal-article","article-title":"Liver imaging reporting and data system (LI-RADS) version 2018: imaging of hepatocellular carcinoma in at-risk patients","volume":"289","author":"Chernyak","year":"2018","journal-title":"Radiology"},{"key":"pmbaea5d1bib6","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1016\/j.jhep.2024.08.028","type":"journal-article","article-title":"EASL clinical practice guidelines on the management of hepatocellular carcinoma","volume":"82","author":"European Association for the Study of the Liver","year":"2025","journal-title":"J. Hepatol."},{"key":"pmbaea5d1bib7","first-page":"7696","type":"conference-proceedings","article-title":"Dynamic multimodal information bottleneck for multimodality classification","author":"Fang","year":"2024"},{"key":"pmbaea5d1bib8","doi-asserted-by":"publisher","first-page":"2551","DOI":"10.1109\/TPAMI.2022.3171983","type":"journal-article","article-title":"Trusted multi-view classification with dynamic evidential fusion","volume":"45","author":"Han","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"pmbaea5d1bib9","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1038\/s41746-020-00341-z","type":"journal-article","article-title":"Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines","volume":"3","author":"Huang","year":"2020","journal-title":"npj Digit. Med."},{"key":"pmbaea5d1bib10","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2024.1295575","type":"journal-article","article-title":"CT-based radiomics for predicting pathological grade in hepatocellular carcinoma","volume":"14","author":"Huang","year":"2024","journal-title":"Front. Oncol."},{"key":"pmbaea5d1bib11","first-page":"4015","type":"conference-proceedings","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"pmbaea5d1bib12","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1186\/s13244-023-01415-8","type":"journal-article","article-title":"CheckList for evaluation of radiomics research (CLEAR): a step-by-step reporting guideline for authors and reviewers endorsed by ESR and EuSoMII","volume":"14","author":"Kocak","year":"2023","journal-title":"Insights Imaging"},{"key":"pmbaea5d1bib13","doi-asserted-by":"publisher","first-page":"1397","DOI":"10.1007\/s00261-024-04202-1","type":"journal-article","article-title":"Predicting microvascular invasion in hepatocellular carcinoma with a CT and MRI-based multimodal deep learning model","volume":"49","author":"Lei","year":"2024","journal-title":"Abdom. Radiol."},{"key":"pmbaea5d1bib14","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1186\/s13244-024-01623-w","type":"journal-article","article-title":"Multiparametric MRI-based intratumoral and peritumoral radiomics for predicting the pathological differentiation of hepatocellular carcinoma","volume":"15","author":"Liu","year":"2024","journal-title":"Insights Imaging"},{"key":"pmbaea5d1bib15","doi-asserted-by":"publisher","first-page":"4473","DOI":"10.3390\/cancers14184473","type":"journal-article","article-title":"Changes in the epidemiology of hepatocellular carcinoma in Asia","volume":"14","author":"Liu","year":"2022","journal-title":"Cancers"},{"key":"pmbaea5d1bib16","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1038\/s41572-020-00240-3","type":"journal-article","article-title":"Hepatocellular carcinoma","volume":"6","author":"Llovet","year":"2021","journal-title":"Nat. Rev. Dis. Primers"},{"key":"pmbaea5d1bib17","doi-asserted-by":"publisher","first-page":"2097","DOI":"10.1038\/s41467-025-57427-z","type":"journal-article","article-title":"General lightweight framework for vision foundation model supporting multi-task and multi-center medical image analysis","volume":"16","author":"Lu","year":"2025","journal-title":"Nat. Commun."},{"key":"pmbaea5d1bib18","doi-asserted-by":"publisher","first-page":"836","DOI":"10.1109\/TNNLS.2013.2281839","type":"journal-article","article-title":"Sparse Bayesian extreme learning machine for multi-classification","volume":"25","author":"Luo","year":"2014","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"pmbaea5d1bib19","doi-asserted-by":"publisher","first-page":"2268","DOI":"10.1109\/JBHI.2019.2956354","type":"journal-article","article-title":"Multi-level multi-modality fusion radiomics: application to PET and CT imaging for prognostication of head and neck cancer","volume":"24","author":"Lv","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"pmbaea5d1bib20","doi-asserted-by":"publisher","first-page":"13","DOI":"10.21037\/hbsn-19-870","type":"journal-article","article-title":"Gd-EOB-DTPA-enhanced MRI radiomic features for predicting histological grade of hepatocellular carcinoma","volume":"11","author":"Mao","year":"2022","journal-title":"Hepatobiliary Surg. Nutr."},{"key":"pmbaea5d1bib21","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","type":"journal-article","article-title":"Foundation models for generalist medical artificial intelligence","volume":"616","author":"Moor","year":"2023","journal-title":"Nature"},{"key":"pmbaea5d1bib22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.07193","type":"journal-article","article-title":"DINOv2: learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"pmbaea5d1bib23","doi-asserted-by":"publisher","first-page":"2136","DOI":"10.5555\/3540261.3540425","type":"book","article-title":"TransMIL: transformer-based correlated multiple instance learning for whole slide image classification","volume":"vol 34","author":"Shao","year":"2021"},{"key":"pmbaea5d1bib24","doi-asserted-by":"publisher","first-page":"1922","DOI":"10.1097\/HEP.0000000000000466","type":"journal-article","article-title":"AASLD practice guidance on prevention, diagnosis, and treatment of hepatocellular carcinoma","volume":"78","author":"Singal","year":"2023","journal-title":"Hepatology"},{"key":"pmbaea5d1bib25","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.240300","type":"journal-article","article-title":"Checklist for artificial intelligence in medical imaging (CLAIM): 2024 update","volume":"6","author":"Tejani","year":"2024","journal-title":"Radiol. Artif. Intell."},{"key":"pmbaea5d1bib26","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ad4f45","type":"journal-article","article-title":"Prediction model of early recurrence of multimodal hepatocellular carcinoma with tensor fusion","volume":"69","author":"Wang","year":"2024","journal-title":"Phys. Med. Biol."},{"key":"pmbaea5d1bib27","doi-asserted-by":"publisher","first-page":"2117","DOI":"10.1002\/jmri.29289","type":"journal-article","article-title":"Multiphase MRI-based radiomics for predicting histological grade of hepatocellular carcinoma","volume":"60","author":"Yan","year":"2024","journal-title":"J. Magn. Reson. Imaging"},{"key":"pmbaea5d1bib28","doi-asserted-by":"publisher","first-page":"2029","DOI":"10.1111\/liv.15251","type":"journal-article","article-title":"Changing epidemiology of hepatocellular carcinoma in Asia","volume":"42","author":"Zhang","year":"2022","journal-title":"Liver Int."},{"key":"pmbaea5d1bib29","doi-asserted-by":"publisher","first-page":"559","DOI":"10.5555\/3454287.3454338","type":"book","article-title":"CPM-Nets: cross partial multi-view networks","volume":"vol 32","author":"Zhang","year":"2019"},{"key":"pmbaea5d1bib30","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1109\/TMI.2024.3455931","type":"journal-article","article-title":"Cohort-individual cooperative learning for multimodal cancer survival analysis","volume":"44","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Med. Imaging"}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea5d1","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea5d1\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea5d1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea5d1\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea5d1\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea5d1\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea5d1\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea5d1\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T06:02:54Z","timestamp":1790229774000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea5d1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,24]]},"references-count":30,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9,24]]},"published-print":{"date-parts":[[2026,9,28]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/aea5d1","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,24]]},"assertion":[{"value":"Cross-modal interactive fusion framework for preoperative histological grading of hepatocellular carcinoma","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2026-03-14","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-09-10","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-09-24","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}