{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T10:21:22Z","timestamp":1771928482384,"version":"3.50.1"},"reference-count":22,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"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>Objective<\/jats:title>\n                    <jats:p>This study aimed to develop interpretable machine learning (ML) models using apparent diffusion coefficient (ADC) radiomics to differentiate hepatocellular carcinoma (HCC) from intrahepatic cholangiocarcinoma (ICC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Radiomic features were extracted from ADC maps of 83 pathologically confirmed HCC and 46 pathologically confirmed ICC patients who underwent MRI examinations. The least absolute shrinkage and selection operator (LASSO) method selected essential features for five ML models: logistic regression (LR), random forest (RF), gaussian naive bayes (GNB), support vector machine (SVM), and k-nearest neighbors (kNN). external validation was performed using 20 HCC and 20 ICC cases from the cancer imaging archive (TCIA) public database. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, accuracy, F1 score, calibration plots, and decision curve analysis (DCA). The best-performing model was interpreted using shapley additive explanations (SHAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>LASSO selected eight features. The models achieved training AUROCs of 0.84-0.95 and internal validation AUROCs of 0.78-0.91. The LR model demonstrated superior performance (training AUROC: 0.95; internal validation AUROC: 0.91; external validation AUROC: 0.85). Moreover, calibration plots and DCA confirmed that this model exhibited the best calibration and clinical utility. SHAP identified wavelet-LLL-firstorder-RootMeanSquared as the most impactful feature.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The ADC-based LR model robustly differentiates HCC from ICC, with validated generalizability using public data, offering a promising non-invasive clinical tool.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1681920","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T05:22:08Z","timestamp":1770096128000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpretable ADC-based radiomics models for differentiating hepatocellular carcinoma and intrahepatic cholangiocarcinoma"],"prefix":"10.3389","volume":"16","author":[{"given":"Yun","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Radiology, Shenzhen Longhua Maternity and Child Healthcare Hospital","place":["Shenzhen, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Yin","sequence":"additional","affiliation":[{"name":"Department of Radiology, Yueyang Central Hospital","place":["Yueyang, Hunan, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baowen","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First Affiliated Hospital of Shantou University Medical College","place":["Shantou, Guangdong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwu","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First Affiliated Hospital of Shantou University Medical College","place":["Shantou, Guangdong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongjie","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Shenzhen Longhua Maternity and Child Healthcare Hospital","place":["Shenzhen, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,3]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.canlet.2024.216799","article-title":"Characterization of the distinct immune microenvironments between hepatocellular carcinoma and intrahepatic cholangiocarcinoma","volume":"588","author":"Jiang","year":"2024","journal-title":"Cancer Lett"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.mcpro.2023.100604","article-title":"Proteome landscapes of human hepatocellular carcinoma and intrahepatic cholangiocarcinoma","volume":"22","author":"Yi","year":"2023","journal-title":"Mol Cell Proteomics"},{"key":"B3","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1016\/bs.acr.2022.03.002","article-title":"Immunotherapies for hepatocellular carcinoma and intrahepatic cholangiocarcinoma: Current and developing strategies","volume":"156","author":"Argemi","year":"2022","journal-title":"Adv Cancer Res"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1002\/lt.25786","article-title":"Resection of mixed hepatocellular cholangiocarcinoma, hepatocellular carcinoma, and intrahepatic cholangiocarcinoma","volume":"26","author":"Holzner","year":"2020","journal-title":"Liver Transpl"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.semradonc.2018.06.010","article-title":"Hepatocellular carcinoma and intrahepatic cholangiocarcinoma: imaging for diagnosis, tumor response to treatment and liver response to radiation","volume":"28","author":"Lo","year":"2018","journal-title":"Semin Radiat Oncol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/5334095","article-title":"Classification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma based on radiomic analysis","volume":"2022","author":"Xu","year":"2022","journal-title":"Comput Math Methods Med"},{"key":"B7","doi-asserted-by":"publisher","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":"B8","doi-asserted-by":"publisher","DOI":"10.1007\/s00261-023-03870-9","article-title":"Machine learning based on gadoxetic acid-enhanced MRI for differentiating atypical intrahepatic mass-forming cholangiocarcinoma from poorly differentiated hepatocellular carcinoma","volume":"48","author":"Chen","year":"2023","journal-title":"Abdom Radiol (NY)"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3248489","article-title":"Computerized diagnosis of liver tumors from CT scans using a deep neural network approach","volume":"27","author":"Midya","year":"2023","journal-title":"IEEE J BioMed Health Inform"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2017170706","article-title":"Deep learning with convolutional neural network for differentiation of liver masses at dynamic contrast-enhanced CT: A preliminary study","volume":"286","author":"Yasaka","year":"2018","journal-title":"Radiology"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-019-06205-9","article-title":"Deep learning for liver tumor diagnosis part I: development of a convolutional neural network classifier for multi-phasic MRI","volume":"29","author":"Hamm","year":"2019","journal-title":"Eur Radiol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.2463\/mrms.mp.2021-0077","article-title":"Effect of an Ultrahigh b Value of 3000 s\/mm 2 and the Minimal Echo-time on Image Quality and the T2 Shine-through Effect in Diffusion-weighted Imaging of the Liver at 3T: Phantom and Clinical Pilot Studies","volume":"22","author":"Fukushima","year":"2023","journal-title":"Magn Reson Med Sci"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1111\/hepr.14015","article-title":"Apparent diffusion coefficient in intrahepatic cholangiocarcinoma diffusion-weighted magnetic resonance imaging noninvasively predicts Ki-67 expression","volume":"54","author":"Hokkoku","year":"2024","journal-title":"Hepatol Res"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1097\/RLI.0000000000000766","article-title":"The rate of apparent diffusion coefficient change with diffusion time on breast diffusion-weighted imaging depends on breast tumor types and molecular prognostic biomarker expression","volume":"56","author":"Iima","year":"2021","journal-title":"Invest Radiol"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.25044","article-title":"Apparent diffusion coefficient-dependent voxelwise computed diffusion-weighted imaging: An approach for improving SNR and reducing T2 shine-through effects","volume":"43","author":"Gatidis","year":"2016","journal-title":"J Magn Reson Imaging"},{"key":"B16","doi-asserted-by":"publisher","first-page":"170124","DOI":"10.1038\/sdata.2017.124","article-title":"The public cancer radiology imaging collections of The Cancer Imaging Archive","volume":"4","author":"Prior","year":"2017","journal-title":"Sci Data"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.21037\/tcr-2025-2024","article-title":"Radiomics-based machine learning for glioma grade classification: a multicenter study with SHapley Additive exPlanations interpretability analysis","volume":"14","author":"Shi","year":"2025","journal-title":"Transl Cancer Res"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1002\/sim.7679","article-title":"Performance of intraclass correlation coefficient (ICC) as a reliability index under various distributions in scale reliability studies","volume":"37","author":"Mehta","year":"2018","journal-title":"Stat Med"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1002\/sim.6152","article-title":"Calibration plots for risk prediction models in the presence of competing risks","volume":"33","author":"Gerds","year":"2014","journal-title":"Stat Med"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.spinee.2021.02.024","article-title":"Decision curve analysis to evaluate the clinical benefit of prediction models","volume":"21","author":"Vickers","year":"2021","journal-title":"Spine J"},{"key":"B21","doi-asserted-by":"publisher","first-page":"7924","DOI":"10.1038\/s41598-022-11997-w","article-title":"Automated machine learning for differentiation of hepatocellular carcinoma from intrahepatic cholangiocarcinoma on multiphasic MRI","volume":"12","author":"Hu","year":"2022","journal-title":"Sci Rep"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2023.01.009","article-title":"Dependence of apparent diffusion coefficient on slice position in magnetic resonance diffusion imaging","volume":"99","author":"Takatsu","year":"2023","journal-title":"Magn Reson Imaging"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1681920\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T09:30:08Z","timestamp":1771925408000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1681920\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,3]]},"references-count":22,"alternative-id":["10.3389\/fonc.2026.1681920"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1681920","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,3]]},"article-number":"1681920"}}