{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T08:23:41Z","timestamp":1792484621124,"version":"4.5.0"},"reference-count":41,"publisher":"Public Library of Science (PLoS)","issue":"11","license":[{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Foundation of General Hospital of Western Theater Command","award":["2024-YGJS-A05"],"award-info":[{"award-number":["2024-YGJS-A05"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop and validate an integrated 2.5D deep learning (DL) and Radiomics model using gadoxetic acid-enhanced MRI hepatobiliary phase (HBP) images combined with clinical features for preoperative prediction of microvascular invasion (MVI) and high Ki-67 expression (&gt;20%) dual positivity in hepatocellular carcinoma (HCC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study included 235 pathologically confirmed HCC patients categorized as MVI\/Ki-67 double-positive (n\u2009=\u2009129) or non-double-positive (n\u2009=\u2009106). Clinical data (tumor diameter, AFP, GGT, differentiation grade, etc.) and HBP MRI images were collected. Tumor ROIs were segmented on HBP images. A 2.5D DL approach utilized axial, sagittal, and coronal planes of the largest tumor cross-section. LASSO regression selected key features from clinical, radiomic, and DL feature sets. Multivariate logistic regression identified independent predictors, and a nomogram was built. Model performance was evaluated via ROC curves, calibration plots, DCA, confusion matrices, and waterfall plots. Assessment of early recurrence within 2 years after HCC surgery was performed using alpha-fetoprotein (AFP) levels and imaging examinations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Significant intergroup differences existed in tumor diameter, AFP, GGT, and differentiation grade (\n                      <jats:italic>\n                        <jats:italic>P<\/jats:italic>\n                        \u2009\n                      <\/jats:italic>\n                      &lt;\u20090.05). LASSO selected 38 key features (7 clinical, 23 DL, 8 radiomic). Multivariate analysis confirmed the derived clinical feature score, DL_Radscore, and radiomics Radscore as independent predictors of dual positivity. The integrated nomogram model (combining 2.5D DL, radiomics, and clinical features) achieved optimal prediction performance: AUROC, sensitivity, specificity, precision, accuracy, and F1-score values of 0.939, 0.793, 0.940, 0.942, 0.859, and 0.861, respectively.Calibration curves demonstrated good agreement, and DCA indicated clinical utility. Furthermore, postoperative follow-up confirmed that the MVI\/Ki-67 dual-positive group exhibited a significantly higher early recurrence rate compared to the non-dual-positive group (\n                      <jats:italic>\n                        <jats:italic>P<\/jats:italic>\n                      <\/jats:italic>\n                      \u2009&lt;\u20090.05).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The integrated MRI 2.5D DL model synergizing radiomics and clinical features surpasses single-modality models for preoperative prediction of MVI\/Ki-67 dual positivity in HCC. This tool shows strong potential for enhancing HCC risk stratification and guiding personalized treatment planning.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0336579","type":"journal-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:27:31Z","timestamp":1763144851000},"page":"e0336579","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["MRI-based 2.5D deep learning and radiomics effectively predicted microvascular invasion and Ki-67 expression in hepatocellular carcinoma"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6207-4536","authenticated-orcid":true,"given":"Hongmei","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Depeng","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojun","family":"Mo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ju","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9288-2399","authenticated-orcid":true,"given":"Feizhou","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"issue":"12","key":"pone.0336579.ref001","doi-asserted-by":"crossref","first-page":"1013","DOI":"10.1001\/jama.2024.14101","article-title":"Prevention, Diagnosis, and Treatment of Hepatocellular Carcinoma","volume":"332","author":"S Park","year":"2024","journal-title":"JAMA"},{"issue":"2","key":"pone.0336579.ref002","doi-asserted-by":"crossref","first-page":"339","DOI":"10.3350\/cmh.2023.0077","article-title":"The clinical management of hepatocellular carcinoma in China: Progress and challenges","volume":"29","author":"S Shan","year":"2023","journal-title":"Clin Mol Hepatol"},{"issue":"6","key":"pone.0336579.ref003","doi-asserted-by":"crossref","first-page":"3342","DOI":"10.1016\/j.acra.2025.02.006","article-title":"Predicting Microvascular Invasion and Early Recurrence in Hepatocellular Carcinoma Using DeepLab V3+ Segmentation of Multiregional MR Habitat Images","volume":"32","author":"Z Huang","year":"2025","journal-title":"Acad Radiol"},{"key":"pone.0336579.ref004","doi-asserted-by":"crossref","first-page":"6651397","DOI":"10.1155\/2021\/6651397","article-title":"Correlationship between Ki67, VEGF, and p53 and Hepatocellular Carcinoma Recurrence in Liver Transplant Patients","volume":"2021","author":"X Zhang","year":"2021","journal-title":"Biomed Res Int"},{"issue":"1","key":"pone.0336579.ref005","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1186\/s12957-022-02632-z","article-title":"Individual and joint influence of cytokeratin 19 and microvascular invasion on the prognosis of patients with hepatocellular carcinoma after hepatectomy","volume":"20","author":"S-D Qin","year":"2022","journal-title":"World J Surg Oncol"},{"issue":"11","key":"pone.0336579.ref006","doi-asserted-by":"crossref","first-page":"6774","DOI":"10.1245\/s10434-022-12000-6","article-title":"Application of a Convolutional Neural Network for Multitask Learning to Simultaneously Predict Microvascular Invasion and Vessels that Encapsulate Tumor Clusters in Hepatocellular Carcinoma","volume":"29","author":"T Chu","year":"2022","journal-title":"Ann Surg Oncol"},{"issue":"1","key":"pone.0336579.ref007","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1186\/s12885-023-10503-3","article-title":"Mesenchymal circulating tumor cells and Ki67: their mutual correlation and prognostic implications in hepatocellular carcinoma","volume":"23","author":"X Yang","year":"2023","journal-title":"BMC Cancer"},{"issue":"2","key":"pone.0336579.ref008","doi-asserted-by":"crossref","first-page":"277","DOI":"10.3350\/cmh.2022.0212","article-title":"Utility of combining PIVKA-II and AFP in the surveillance and monitoring of hepatocellular carcinoma in the Asia-Pacific region","volume":"29","author":"DY Kim","year":"2023","journal-title":"Clin Mol Hepatol"},{"issue":"6","key":"pone.0336579.ref009","doi-asserted-by":"crossref","first-page":"1469","DOI":"10.1016\/j.jhep.2023.08.020","article-title":"AFP-L3 and DCP strongly predict early hepatocellular carcinoma recurrence after liver transplantation","volume":"79","author":"JS Norman","year":"2023","journal-title":"J Hepatol"},{"issue":"2","key":"pone.0336579.ref010","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.222891","article-title":"Using Machine Learning to Predict Response to Image-guided Therapies for Hepatocellular Carcinoma","volume":"309","author":"C Hsieh","year":"2023","journal-title":"Radiology"},{"issue":"3","key":"pone.0336579.ref011","doi-asserted-by":"crossref","first-page":"767","DOI":"10.1002\/jmri.28982","article-title":"MRI\u2010Based Radiomics and Deep Learning in Biological Characteristics and Prognosis of Hepatocellular Carcinoma: Opportunities and Challenges","volume":"59","author":"T Xia","year":"2023","journal-title":"Magnetic Resonance Imaging"},{"issue":"2","key":"pone.0336579.ref012","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1001\/jamasurg.2022.6697","article-title":"Machine Learning Predictive Model to Guide Treatment Allocation for Recurrent Hepatocellular Carcinoma After Surgery","volume":"158","author":"S Famularo","year":"2023","journal-title":"JAMA Surg"},{"issue":"6","key":"pone.0336579.ref013","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1016\/j.jhep.2022.01.014","article-title":"Artificial intelligence for the prevention and clinical management of hepatocellular carcinoma","volume":"76","author":"J Calderaro","year":"2022","journal-title":"J Hepatol"},{"issue":"1","key":"pone.0336579.ref014","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1186\/s12885-025-13781-1","article-title":"Deep learning based on intratumoral heterogeneity predicts histopathologic grade of hepatocellular carcinoma","volume":"25","author":"S Song","year":"2025","journal-title":"BMC Cancer"},{"issue":"12","key":"pone.0336579.ref015","doi-asserted-by":"crossref","first-page":"9152","DOI":"10.1007\/s00330-023-09928-y","article-title":"Consensus report from the 10th Global Forum for Liver Magnetic Resonance Imaging: developments in HCC management","volume":"33","author":"B Taouli","year":"2023","journal-title":"Eur Radiol"},{"issue":"1","key":"pone.0336579.ref016","article-title":"Gd-EOB-DTPA-enhanced MRI radiomics and deep learning models to predict microvascular invasion in hepatocellular carcinoma: a multicenter study","volume":"25","author":"Z Zhu","year":"2025","journal-title":"BMC Med Imaging"},{"issue":"3","key":"pone.0336579.ref017","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1016\/j.acra.2023.07.019","article-title":"Radiomic Analysis Based on Gd-EOB-DTPA Enhanced MRI for the Preoperative Prediction of Ki-67 Expression in Hepatocellular Carcinoma","volume":"31","author":"Y Yan","year":"2024","journal-title":"Acad Radiol"},{"issue":"1","key":"pone.0336579.ref018","doi-asserted-by":"crossref","DOI":"10.1186\/s12880-024-01204-9","article-title":"A gadoxetic acid-enhanced MRI-based model using LI-RADS v2018 features for preoperatively predicting Ki-67 expression in hepatocellular carcinoma","volume":"24","author":"Y Liang","year":"2024","journal-title":"BMC Med Imaging"},{"issue":"2","key":"pone.0336579.ref019","first-page":"350","article-title":"Evaluation of Preoperative Microvascular Invasion in Hepatocellular Carcinoma Through Multidimensional Parameter Combination Modeling Based on Gd-EOB-DTPA MRI","volume":"11","author":"H-D Zhang","year":"2023","journal-title":"J Clin Transl Hepatol"},{"key":"pone.0336579.ref020","doi-asserted-by":"crossref","first-page":"111146","DOI":"10.1016\/j.ejrad.2023.111146","article-title":"Microvascular invasion-negative hepatocellular carcinoma: Prognostic value of qualitative and quantitative Gd-EOB-DTPA MRI analysis","volume":"168","author":"L Wang","year":"2023","journal-title":"Eur J Radiol"},{"issue":"11","key":"pone.0336579.ref021","doi-asserted-by":"crossref","first-page":"4445","DOI":"10.1016\/j.acra.2024.04.028","article-title":"Deep Learning Model for Predicting Proliferative Hepatocellular Carcinoma Using Dynamic Contrast-Enhanced MRI: Implications for Early Recurrence Prediction Following Radical Resection","volume":"31","author":"H Qu","year":"2024","journal-title":"Acad Radiol"},{"issue":"2","key":"pone.0336579.ref022","article-title":"Deep Learning Radiopathomics Models Based on Contrast-enhanced MRI and Pathologic Imaging for Predicting Vessels Encapsulating Tumor Clusters and Prognosis in Hepatocellular Carcinoma","volume":"7","author":"Y Yu","year":"2025","journal-title":"Radiol Imaging Cancer"},{"issue":"1","key":"pone.0336579.ref023","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1002\/jmri.28745","article-title":"Deep Learning Radiomics Model of Dynamic Contrast\u2010Enhanced MRI for Evaluating Vessels Encapsulating Tumor Clusters and Prognosis in Hepatocellular Carcinoma","volume":"59","author":"X Dong","year":"2023","journal-title":"Magnetic Resonance Imaging"},{"issue":"12","key":"pone.0336579.ref024","doi-asserted-by":"crossref","first-page":"3435","DOI":"10.31557\/APJCP.2018.19.12.3435","article-title":"Platelet-to-Lymphocyte Ratio and Large Tumor Size Predict Microvascular Invasion after Resection for Hepatocellular Carcinoma","volume":"19","author":"N Rungsakulkij","year":"2018","journal-title":"Asian Pac J Cancer Prev"},{"issue":"10","key":"pone.0336579.ref025","doi-asserted-by":"crossref","first-page":"4021","DOI":"10.1016\/j.acra.2024.02.035","article-title":"A Dynamic Online Nomogram Based on Gd-EOB-DTPA-Enhanced MRI and Inflammatory Biomarkers for Preoperative Prediction of Pathological Grade and Stratification in Solitary Hepatocellular Carcinoma: A Multicenter Study","volume":"31","author":"F Wang","year":"2024","journal-title":"Acad Radiol"},{"issue":"11","key":"pone.0336579.ref026","doi-asserted-by":"crossref","first-page":"8615","DOI":"10.1007\/s00330-021-07941-7","article-title":"Nomogram development and validation to predict hepatocellular carcinoma tumor behavior by preoperative gadoxetic acid-enhanced MRI","volume":"31","author":"M Tang","year":"2021","journal-title":"Eur Radiol"},{"issue":"6","key":"pone.0336579.ref027","doi-asserted-by":"crossref","first-page":"4186","DOI":"10.1007\/s00330-021-08502-8","article-title":"Prediction of microvascular invasion in HCC by a scoring model combining Gd-EOB-DTPA MRI and biochemical indicators","volume":"32","author":"K Zhang","year":"2022","journal-title":"Eur Radiol"},{"key":"pone.0336579.ref028","doi-asserted-by":"crossref","first-page":"1134646","DOI":"10.3389\/fonc.2023.1134646","article-title":"Gadoxetic acid-enhanced MRI combined with T1 mapping and clinical factors to predict Ki-67 expression of hepatocellular carcinoma","volume":"13","author":"G Qiu","year":"2023","journal-title":"Front Oncol"},{"issue":"5","key":"pone.0336579.ref029","doi-asserted-by":"crossref","first-page":"4286","DOI":"10.3390\/ijms24054286","article-title":"Updating the Clinical Application of Blood Biomarkers and Their Algorithms in the Diagnosis and Surveillance of Hepatocellular Carcinoma: A Critical Review","volume":"24","author":"E Shahini","year":"2023","journal-title":"Int J Mol Sci"},{"key":"pone.0336579.ref030","article-title":"Establishment and validation of nomogram model for the diagnosis of AFP-negative hepatocellular carcinoma","volume":"13","author":"L Liu","year":"2023","journal-title":"Front Oncol"},{"key":"pone.0336579.ref031","doi-asserted-by":"crossref","first-page":"111348","DOI":"10.1016\/j.ejrad.2024.111348","article-title":"Prediction of microvascular invasion and pathological differentiation of hepatocellular carcinoma based on a deep learning model","volume":"172","author":"X He","year":"2024","journal-title":"Eur J Radiol"},{"issue":"5","key":"pone.0336579.ref032","doi-asserted-by":"crossref","first-page":"1139","DOI":"10.1002\/hep.32201","article-title":"Immunovascular classification of HCC reflects reciprocal interaction between immune and angiogenic tumor microenvironments","volume":"75","author":"Y Kurebayashi","year":"2022","journal-title":"Hepatology"},{"issue":"7","key":"pone.0336579.ref033","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1007\/s00535-009-0056-4","article-title":"Expression of OATP1B3 determines uptake of Gd-EOB-DTPA in hepatocellular carcinoma","volume":"44","author":"M Narita","year":"2009","journal-title":"J Gastroenterol"},{"key":"pone.0336579.ref034","doi-asserted-by":"crossref","first-page":"954445","DOI":"10.3389\/fonc.2022.954445","article-title":"Nomogram development and validation to predict Ki-67 expression of hepatocellular carcinoma derived from Gd-EOB-DTPA-enhanced MRI combined with T1 mapping","volume":"12","author":"Z Liu","year":"2022","journal-title":"Front Oncol"},{"issue":"1","key":"pone.0336579.ref035","doi-asserted-by":"crossref","first-page":"109364","DOI":"10.1016\/j.ejso.2024.109364","article-title":"Development and validation of a cross-modality tensor fusion model using multi-modality MRI radiomics features and clinical radiological characteristics for the prediction of microvascular invasion in hepatocellular carcinoma","volume":"51","author":"A Meng","year":"2025","journal-title":"Eur J Surg Oncol"},{"issue":"8","key":"pone.0336579.ref036","doi-asserted-by":"crossref","first-page":"948","DOI":"10.3390\/bioengineering10080948","article-title":"Clinical Interpretability of Deep Learning for Predicting Microvascular Invasion in Hepatocellular Carcinoma by Using Attention Mechanism","volume":"10","author":"H You","year":"2023","journal-title":"Bioengineering (Basel)"},{"issue":"6","key":"pone.0336579.ref037","doi-asserted-by":"crossref","first-page":"2071","DOI":"10.1007\/s00261-022-03496-3","article-title":"Radiomics models for preoperative prediction of microvascular invasion in hepatocellular carcinoma: a systematic review and meta-analysis","volume":"47","author":"X Zhong","year":"2022","journal-title":"Abdom Radiol (NY)"},{"issue":"6","key":"pone.0336579.ref038","doi-asserted-by":"crossref","first-page":"1351","DOI":"10.1111\/liv.15870","article-title":"Multitask deep learning for prediction of microvascular invasion and recurrence-free survival in hepatocellular carcinoma based on MRI images","volume":"44","author":"F Wang","year":"2024","journal-title":"Liver Int"},{"issue":"3","key":"pone.0336579.ref039","doi-asserted-by":"crossref","DOI":"10.1111\/liv.16205","article-title":"MRI-Based Topology Deep Learning Model for Noninvasive Prediction of Microvascular Invasion and Assisting Prognostic Stratification in HCC","volume":"45","author":"T Zheng","year":"2025","journal-title":"Liver Int"},{"issue":"1","key":"pone.0336579.ref040","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1186\/s12880-021-00633-0","article-title":"Radiomic analysis of Gd-EOB-DTPA-enhanced MRI predicts Ki-67 expression in hepatocellular carcinoma","volume":"21","author":"Y Fan","year":"2021","journal-title":"BMC Med Imaging"},{"issue":"6","key":"pone.0336579.ref041","doi-asserted-by":"crossref","first-page":"1755","DOI":"10.1002\/jmri.26974","article-title":"Diagnostic Value of Gd-EOB-DTPA-Enhanced MRI for the Expression of Ki67 and Microvascular Density in Hepatocellular Carcinoma","volume":"51","author":"Y Chen","year":"2020","journal-title":"J Magn Reson Imaging"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0336579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:27:39Z","timestamp":1763144859000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0336579"}},"subtitle":[],"editor":[{"given":"Nima","family":"Broomand Lomer,","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":41,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11,14]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0336579","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,14]]}}}