{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T10:07:11Z","timestamp":1779530831461,"version":"3.53.1"},"reference-count":41,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"49","license":[{"start":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T00:00:00Z","timestamp":1764892800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,5]]},"abstract":"<jats:p>This study developed an magnetic resonance imaging (MRI)-based multiclass model for the preoperative differentiation of primary liver cancer (PLC) subtypes by integrating radiomic and clinicoradiological features. We retrospectively enrolled 251 patients with pathologically confirmed PLC, including 92 with hepatocellular carcinoma, 77 with intrahepatic cholangiocarcinoma, and 82 with combined hepatocellular-cholangiocarcinoma. A clinicoradiological model was constructed using statistically significant clinical and MRI-based radiological characteristics. To develop the radiomics model, radiomic features were extracted from multiparametric MRI sequences, including diffusion-weighted imaging, dynamic contrast-enhanced T1WI in the arterial (T1WI-A), portal venous (T1WI-V), and delayed (T1WI-D) phases. A combined model was then developed by integrating these features. Feature selection employed a 2-stage strategy: initial filtering coupled with model construction using 6 machine learning (ML) algorithms, followed by recursive feature elimination (RFE) on the top-performing model to build the final RFE-integrated model. Performance was assessed by the area under the receiver operating characteristic curve (AUC), sensitivity, accuracy, precision, and specificity. Additionally, SHapley Additive exPlanations values were applied to interpret the model\u2019s prediction logic. The RFE-integrated model based on a support vector machine demonstrated the highest overall and per-class classification performance, achieving micro- and macro-average AUCs of 0.934 (95% CI: 0.908\u20130.955) and 0.925 (95% CI: 0.896\u20130.949), along with a sensitivity of 0.805 (95% CI: 0.761\u20130.850) and a specificity of 0.901 (95% CI: 0.878\u20130.925). The model also showed high discriminatory power for individual subtypes with AUCs of 0.931 for hepatocellular carcinoma, 0.975 for intrahepatic cholangiocarcinoma, and 0.868 for combined hepatocellular-cholangiocarcinoma. In conclusion, these findings demonstrate that the support vector machine-based RFE-integrated model provides a highly accurate, noninvasive tool for preoperative PLC subtyping, addressing a critical diagnostic challenge, facilitating subtype-specific management, and potentially improving patient outcomes.<\/jats:p>","DOI":"10.1097\/md.0000000000046056","type":"journal-article","created":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T22:01:02Z","timestamp":1764972062000},"page":"e46056","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":0,"title":["Preoperative differentiation of primary liver cancer subtypes: An MRI-based multiclass classification model integrating radiomic and clinicoradiological characteristics"],"prefix":"10.1097","volume":"104","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5746-2052","authenticated-orcid":false,"given":"Wenhao","family":"Wang","sequence":"first","affiliation":[{"name":"Henan University of Chinese Medicine, Zhengzhou, Henan, China"},{"name":"Henan Province Hospital of Traditional Chinese Medicine (The Second Affiliated Hospital of Henan University of Chinese Medicine) , Zhengzhou, Henan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinai","family":"Liu","sequence":"additional","affiliation":[{"name":"Henan Province Hospital of Traditional Chinese Medicine (The Second Affiliated Hospital of Henan University of Chinese Medicine) , Zhengzhou, Henan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhongshan Hospital Fudan University, Shanghai, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yubo","family":"Li","sequence":"additional","affiliation":[{"name":"Henan Province Hospital of Traditional Chinese Medicine (The Second Affiliated Hospital of Henan University of Chinese Medicine) , Zhengzhou, Henan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"R1-20260523","first-page":"229","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries.","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J Clin"},{"key":"R2-20260523","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1097\/HEP.0000000000001269","article-title":"Critical update: AASLD Practice Guidance on prevention, diagnosis, and treatment of hepatocellular carcinoma.","volume":"82","author":"Taddei","year":"2025","journal-title":"Hepatology"},{"key":"R3-20260523","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/j.jhep.2023.03.010","article-title":"Liver EAftSot. EASL-ILCA Clinical Practice Guidelines on the management of intrahepatic cholangiocarcinoma.","volume":"79","year":"2023","journal-title":"J Hepatol"},{"key":"R4-20260523","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1186\/s12943-024-02101-z","article-title":"Biomarkers for diagnosis and therapeutic options in hepatocellular carcinoma.","volume":"23","author":"Chan","year":"2024","journal-title":"Mol Cancer"},{"key":"R5-20260523","doi-asserted-by":"crossref","first-page":"4261","DOI":"10.3748\/wjg.v26.i29.4261","article-title":"Gadoxetic acid magnetic-enhanced resonance imaging in the diagnosis of cholangiocarcinoma.","volume":"26","author":"Inchingolo","year":"2020","journal-title":"World J Gastroenterol"},{"key":"R6-20260523","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1159\/000530495","article-title":"Guidelines for the diagnosis and treatment of primary liver cancer (2022 edition).","volume":"12","author":"Zhou","year":"2023","journal-title":"Liver Cancer"},{"key":"R7-20260523","doi-asserted-by":"crossref","first-page":"2386","DOI":"10.1111\/liv.14261","article-title":"Combining imaging and tumour biopsy improves the diagnosis of combined hepatocellular-cholangiocarcinoma.","volume":"39","author":"Gigante","year":"2019","journal-title":"Liver Int"},{"key":"R8-20260523","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.jhep.2018.03.019","article-title":"EASL clinical practice guidelines: management of hepatocellular carcinoma.","volume":"69","author":"Galle","year":"2018","journal-title":"J Hepatol"},{"key":"R9-20260523","doi-asserted-by":"crossref","first-page":"1212","DOI":"10.1016\/j.jhep.2021.01.035","article-title":"Combined hepatocellular-cholangiocarcinoma: an update.","volume":"74","author":"Beaufr\u00e8re","year":"2021","journal-title":"J Hepatol"},{"key":"R10-20260523","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1038\/s41568-018-0016-5","article-title":"Artificial intelligence in radiology.","volume":"18","author":"Hosny","year":"2018","journal-title":"Nat Rev Cancer"},{"key":"R11-20260523","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/j.ejca.2021.06.053","article-title":"Feasibility of magnetic resonance imaging-based radiomics features for preoperative prediction of extrahepatic cholangiocarcinoma stage.","volume":"155","author":"Huang","year":"2021","journal-title":"Eur J Cancer"},{"key":"R12-20260523","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1016\/j.ejca.2011.11.036","article-title":"Radiomics: extracting more information from medical images using advanced feature analysis.","volume":"48","author":"Lambin","year":"2012","journal-title":"Eur J Cancer"},{"key":"R13-20260523","doi-asserted-by":"crossref","first-page":"5004","DOI":"10.1007\/s00330-022-08548-2","article-title":"DCE-MRI based radiomics nomogram for preoperatively differentiating combined hepatocellular-cholangiocarcinoma from mass-forming intrahepatic cholangiocarcinoma.","volume":"32","author":"Zhou","year":"2022","journal-title":"Eur Radiol"},{"key":"R14-20260523","doi-asserted-by":"crossref","first-page":"5373","DOI":"10.3390\/cancers15225373","article-title":"Differentiation of hepatocellular carcinoma from intrahepatic cholangiocarcinoma through MRI radiomics.","volume":"15","author":"Liu","year":"2023","journal-title":"Cancers (Basel)"},{"key":"R15-20260523","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1038\/s41598-020-79829-3","article-title":"Precise enhancement quantification in post-operative MRI as an indicator of residual tumor impact is associated with survival in patients with glioblastoma.","volume":"11","author":"Garcia-Ruiz","year":"2021","journal-title":"Sci Rep"},{"key":"R16-20260523","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.acra.2021.04.019","article-title":"Radiomics analysis of Gd-EOB-DTPA\u2013enhanced hepatic MRI for assessment of functional liver reserve.","volume":"29","author":"Shi","year":"2022","journal-title":"Acad Radiol"},{"key":"R17-20260523","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1093\/ckj\/sfaa188","article-title":"External validation of prognostic models: what, why, how, when and where?","volume":"14","author":"Ramspek","year":"2021","journal-title":"Clin Kidney J"},{"key":"R18-20260523","doi-asserted-by":"crossref","first-page":"b375","DOI":"10.1136\/bmj.b375","article-title":"Prognosis and prognostic research: what, why, and how?","volume":"338","author":"Moons","year":"2009","journal-title":"BMJ"},{"key":"R19-20260523","doi-asserted-by":"crossref","first-page":"1925","DOI":"10.1093\/eurheartj\/ehu207","article-title":"Towards better clinical prediction models: seven steps for development and an ABCD for validation.","volume":"35","author":"Steyerberg","year":"2014","journal-title":"Eur Heart J"},{"key":"R20-20260523","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1007\/s00330-020-07119-7","article-title":"Can machine learning radiomics provide pre-operative differentiation of combined hepatocellular cholangiocarcinoma from hepatocellular carcinoma and cholangiocarcinoma to inform optimal treatment planning?","volume":"31","author":"Liu","year":"2021","journal-title":"Eur Radiol"},{"key":"R21-20260523","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1186\/s13244-024-01783-9","article-title":"Optimizing radiomics for prostate cancer diagnosis: feature selection strategies, machine learning classifiers, and MRI sequences.","volume":"15","author":"Mylona","year":"2024","journal-title":"Insights Imaging"},{"key":"R22-20260523","doi-asserted-by":"crossref","first-page":"322","DOI":"10.2214\/AJR.12.9478","article-title":"Biologic factors affecting HCC conspicuity in hepatobiliary phase imaging with liver-specific contrast agents.","volume":"201","author":"Kim","year":"2013","journal-title":"AJR Am J Roentgenol"},{"key":"R23-20260523","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1159\/000530700","article-title":"Combined hepatocellular-cholangiocarcinoma: biology, diagnosis, and management.","volume":"13","author":"Ye","year":"2024","journal-title":"Liver Cancer"},{"key":"R24-20260523","doi-asserted-by":"crossref","first-page":"S108","DOI":"10.1053\/j.gastro.2004.09.023","article-title":"Alpha-fetoprotein and ultrasonography screening for hepatocellular carcinoma.","volume":"127","author":"Daniele","year":"2004","journal-title":"Gastroenterology"},{"key":"R25-20260523","doi-asserted-by":"crossref","first-page":"399","DOI":"10.2147\/JHC.S394840","article-title":"Prognosis of primary liver cancer based on LI-RADS classification with extracellular agent-enhanced MRI.","volume":"10","author":"Li","year":"2023","journal-title":"J Hepatocell Carcinoma"},{"key":"R26-20260523","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1111\/his.13975","article-title":"The 2019 WHO classification of tumours of the digestive system.","volume":"76","author":"Nagtegaal","year":"2020","journal-title":"Histopathology"},{"key":"R27-20260523","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1007\/s11547-023-01597-7","article-title":"Development and validation of combined Ki67 status prediction model for intrahepatic cholangiocarcinoma based on clinicoradiological features and MRI radiomics.","volume":"128","author":"Qian","year":"2023","journal-title":"Radiol Med"},{"key":"R28-20260523","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1109\/TMI.2010.2046908","article-title":"N4ITK: improved N3 bias correction.","volume":"29","author":"Tustison","year":"2010","journal-title":"IEEE Trans Med Imaging"},{"key":"R29-20260523","doi-asserted-by":"crossref","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational radiomics system to decode the radiographic phenotype.","volume":"77","author":"van Griethuysen","year":"2017","journal-title":"Cancer Res"},{"key":"R30-20260523","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1148\/radiol.2020191145","article-title":"The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping.","volume":"295","author":"Zwanenburg","year":"2020","journal-title":"Radiology"},{"key":"R31-20260523","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1186\/s12967-025-06402-9","article-title":"Construction of enhanced MRI-based radiomics models using machine learning algorithms for non-invasive prediction of IL7R expression in high-grade gliomas and its prognostic value in clinical practice.","volume":"23","author":"Zhou","year":"2025","journal-title":"J Transl Med"},{"key":"R32-20260523","doi-asserted-by":"crossref","first-page":"133918","DOI":"10.1016\/j.ijbiomac.2024.133918","article-title":"Identifying potential targets for preventing cancer progression through the PLA2G1B recombinant protein using bioinformatics and machine learning methods.","volume":"276","author":"Guan","year":"2024","journal-title":"Int J Biol Macromol"},{"key":"R33-20260523","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.ejca.2022.04.027","article-title":"Disease-free survival as a surrogate endpoint for overall survival in adults with resectable esophageal or gastroesophageal junction cancer: a correlation meta-analysis.","volume":"170","author":"Ajani","year":"2022","journal-title":"Eur J Cancer"},{"key":"R34-20260523","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1038\/s42003-023-04734-0","article-title":"Multi-tissue DNA methylation aging clocks for sea lions, walruses and seals.","volume":"6","author":"Robeck","year":"2023","journal-title":"Commun Biol"},{"key":"R35-20260523","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1016\/j.carbon.2022.12.065","article-title":"Integrating structure annotation and machine learning approaches to develop graphene toxicity models.","volume":"204","author":"Wang","year":"2023","journal-title":"Carbon N Y"},{"key":"R36-20260523","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1186\/s13059-019-1716-1","article-title":"A practical guide to methods controlling false discoveries in computational biology.","volume":"20","author":"Korthauer","year":"2019","journal-title":"Genome Biol"},{"key":"R37-20260523","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1038\/s41551-018-0304-0","article-title":"Explainable machine-learning predictions for the prevention of hypoxaemia during surgery.","volume":"2","author":"Lundberg","year":"2018","journal-title":"Nat Biomed Eng"},{"key":"R38-20260523","doi-asserted-by":"crossref","first-page":"105058","DOI":"10.1016\/j.compbiomed.2021.105058","article-title":"MRI-based radiomics distinguish different pathological types of hepatocellular carcinoma.","volume":"141","author":"Wang","year":"2022","journal-title":"Comput Biol Med"},{"key":"R39-20260523","doi-asserted-by":"crossref","first-page":"912","DOI":"10.1007\/s00261-019-01906-7","article-title":"Volumetric quantitative histogram analysis using diffusion-weighted magnetic resonance imaging to differentiate HCC from other primary liver cancers.","volume":"44","author":"Lewis","year":"2019","journal-title":"Abdom Radiol (NY)"},{"key":"R40-20260523","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.1109\/TPAMI.2005.159","article-title":"Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy.","volume":"27","author":"Peng","year":"2005","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"R41-20260523","doi-asserted-by":"crossref","first-page":"31695","DOI":"10.1007\/s11042-024-20388-4","article-title":"Insights into radiomics: impact of feature selection and classification.","volume":"84","author":"Perniciano","year":"2024","journal-title":"Multimedia Tools Appl"}],"container-title":["Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000046056","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T10:01:37Z","timestamp":1779530497000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000046056"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,5]]},"references-count":41,"journal-issue":{"issue":"49","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1097\/md.0000000000046056","relation":{},"ISSN":["0025-7974","1536-5964"],"issn-type":[{"value":"0025-7974","type":"print"},{"value":"1536-5964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,5]]},"assertion":[{"value":"2025-07-31","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-15","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}