{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T06:19:47Z","timestamp":1787552387626,"version":"build-2736575974"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"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>Hepatoblastoma (HB) and focal nodular hyperplasia (FNH) require markedly different management strategies in children, but differentiation can be challenging when multiphasic computed tomography (CT) findings are atypical or overlapping. This study aimed to develop and temporally validate a pretreatment multiphasic CT-based fusion model combining deep learning (DL) predictions with quantitative enhancement features for pediatric HB\u2013FNH differentiation and to evaluate the potential value of model assistance for junior-radiologist interpretation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study included 612 children who underwent pretreatment multiphasic CT between January 2011 and September 2025, including 523 with HB and 89 with FNH. A chronological split on July 1, 2023 assigned 491 patients to model development and 121 patients to temporal testing. Three phase-specific DL models based on 2.5D ResNet-18 were trained using precontrast, arterial-phase, and portal venous-phase images, and their predicted probabilities were averaged to generate DL-3Phase. Quantitative enhancement features from standardized manual region-of-interest attenuation measurements were used to train a regularized logistic regression model, termed the quantitative enhancement feature (QEF) model. DL+QEF was prespecified as the unweighted average of the DL-3Phase and QEF model probabilities. Performance was assessed using the area under the receiver operating characteristic curve (AUC), diagnostic accuracy metrics, calibration, decision curve analysis, and comparison with radiologist interpretation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      In the temporal test cohort, DL+QEF achieved an AUC of 0.980, an accuracy of 94.2%, an HB sensitivity of 94.9%, and an FNH specificity of 92.9%. DL+QEF showed better discrimination than DL-3Phase and the best-performing single-phase DL model, and combined the high HB sensitivity of DL-3Phase with the high FNH specificity of the QEF model. In the pathology-confirmed test subset, the AUC was 0.972 and accuracy was 92.9%. Junior-radiologist accuracy was 88.4% during unaided reading and 95.0% during model-assisted reading (exact McNemar\n                      <jats:italic>p =<\/jats:italic>\n                      0.0078). In reader-defined atypical cases, DL+QEF had higher accuracy than the junior radiologist (90.2% vs. 68.3%).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The pretreatment multiphasic CT-based DL+QEF model showed favorable diagnostic performance for pediatric HB\u2013FNH differentiation and may serve as an adjunct to CT interpretation, with potential utility in reader-defined atypical or diagnostically uncertain cases.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1923907","type":"journal-article","created":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T05:32:27Z","timestamp":1787549547000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A pretreatment multiphasic CT-based decision-support model for differentiating pediatric hepatoblastoma from focal nodular hyperplasia"],"prefix":"10.3389","volume":"16","author":[{"given":"Lizhu","family":"Cai","sequence":"first","affiliation":[{"name":"Department of Radiology, MOE Key Laboratory of Major Diseases in Children, Beijing Children\u2019s Hospital, Capital Medical University, National Center for Children\u2019s Health","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Peng","sequence":"additional","affiliation":[{"name":"Department of Radiology, MOE Key Laboratory of Major Diseases in Children, Beijing Children\u2019s Hospital, Capital Medical University, National Center for Children\u2019s Health","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"B1","article-title":"PDQ Cancer Information Summaries [Internet]","year":"2025"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/s1470-2045(16)30598-8","article-title":"Risk-stratified staging in paediatric hepatoblastoma: a unified analysis from the Children's Hepatic tumors International Collaboration","volume":"18","author":"Meyers","year":"2017","journal-title":"Lancet Oncol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.14309\/ajg.0000000000002857","article-title":"ACG clinical guideline: focal liver lesions","volume":"119","author":"Frenette","year":"2024","journal-title":"Am J Gastroenterol"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.5114\/ceh.2025.155044","article-title":"Current approach to diagnosis and treatment of focal nodular hyperplasia in children with a management algorithm","volume":"11","author":"Chudoba","year":"2025","journal-title":"Clin Exp Hepatol"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhep.2016.04.001","article-title":"EASL Clinical Practice Guidelines on the management of benign liver tumours","volume":"65","year":"2016","journal-title":"J Hepatol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/215064","article-title":"Benign hepatocellular tumors in children: focal nodular hyperplasia and hepatocellular adenoma","volume":"2013","author":"Franchi-Abella","year":"2013","journal-title":"Int J Hepatol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.4102\/sajr.v28i1.2726","article-title":"Benign paediatric liver tumours: The radiological maze demystified","volume":"28","author":"Sherwani","year":"2024","journal-title":"SA J Radiol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1136\/wjps-2024-000980","article-title":"Congenital focal nodular hyperplasia-like lesion mimicking hepatoblastoma: anecdotal but plausible","volume":"8","author":"Gatto","year":"2025","journal-title":"World J Pediatr Surg"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/s0022-3468(78)80010-4","article-title":"Evaluation of alpha-fetoprotein in early infancy","volume":"13","author":"Tsuchida","year":"1978","journal-title":"J Pediatr Surg"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1515\/cclm-2018-0803","article-title":"Serum \u03b1-fetoprotein in pediatric oncology: not a children's tale","volume":"57","author":"Ferraro","year":"2019","journal-title":"Clin Chem Lab Med"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2024.1307619","article-title":"Alpha-fetoprotein level in fetuses, infants, and children with ovarian masses: a literature review","volume":"15","author":"Maton\u00f3g","year":"2024","journal-title":"Front Endocrinol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/s0022-3468(99)90307-x","article-title":"A case of well-differentiated, fetal-type hepatoblastoma with very low serum alpha-fetoprotein","volume":"34","author":"Tsuchida","year":"1999","journal-title":"J Pediatr Surg"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1111\/j.1440-1827.2011.02691.x","article-title":"High serum level of alpha-fetoprotein in focal nodular hyperplasia of the liver","volume":"61","author":"Mneimneh","year":"2011","journal-title":"Pathol Int"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinimag.2020.08.026","article-title":"Focal nodular hyperplasia masquerading as Malignancy in an infant with elevated alpha-fetoprotein: A case report with literature review","volume":"69","author":"Aboughalia","year":"2021","journal-title":"Clin Imaging"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.175.3.1750687","article-title":"CT and MR imaging findings in focal nodular hyperplasia of the liver: radiologic-pathologic correlation","volume":"175","author":"Mortel\u00e9","year":"2000","journal-title":"AJR Am J Roentgenol."},{"key":"B16","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1148\/rg.241035050","article-title":"Focal nodular hyperplasia: findings at state-of-the-art MR imaging, US, CT, and pathologic analysis","volume":"24","author":"Hussain","year":"2004","journal-title":"Radiographics: A Rev Publ Radiological Soc North America Inc"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpedsurg.2009.12.027","article-title":"Focal nodular hyperplasia in children: clinical features and current management practice","volume":"45","author":"Lautz","year":"2010","journal-title":"J Pediatr Surg"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.13.11856","article-title":"Clinical and imaging features of focal nodular hyperplasia in children","volume":"202","author":"Cha","year":"2014","journal-title":"AJR Am J Roentgenology"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1148\/rg.303095173","article-title":"From the archives of the AFIP: Pediatric liver masses: radiologic-pathologic correlation part 1. Benign tumors","volume":"30","author":"Chung","year":"2010","journal-title":"Radiographics: A Rev Publ Radiological Soc North America Inc"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3748\/wjg.v21.i28.8541","article-title":"Benign liver tumors in pediatric patients - Review with emphasis on imaging features","volume":"21","author":"Chiorean","year":"2015","journal-title":"World J Gastroenterol"},{"key":"B21","doi-asserted-by":"publisher","first-page":"3568","DOI":"10.3390\/diagnostics13233568","article-title":"Review on pediatric Malignant focal liver lesions with imaging evaluation: part I","volume":"13","author":"Dong","year":"2023","journal-title":"Diagnostics (Basel Switzerland)"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1002\/pbc.29965","article-title":"Imaging of pediatric liver tumors: A COG Diagnostic Imaging Committee\/SPR Oncology Committee White Paper","author":"Schooler","year":"2023","journal-title":"Pediatr Blood Cancer"},{"key":"B23","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1148\/rg.312105201","article-title":"From the archives of the AFIP: Pediatric liver masses: radiologic-pathologic correlation. Part 2. Malignant tumors","volume":"31","author":"Chung","year":"2011","journal-title":"Radiographics: A Rev Publ Radiological Soc North America Inc"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1148\/rg.240246","article-title":"Benign and Malignant pediatric liver masses: radiologic-pathologic update from the pediatric LI-RADS working group","volume":"45","author":"Rees","year":"2025","journal-title":"Radiographics: A Rev Publ Radiological Soc North America Inc"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.5152\/dir.2019.19398","article-title":"Hepatocyte-specific contrast-enhanced MRI findings of focal nodular hyperplasia-like nodules in the liver following chemotherapy in pediatric cancer patients","volume":"26","author":"\u00d6zcan","year":"2020","journal-title":"Diagn Interventional Radiol (Ankara Turkey)"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/s1076-6332(00)80632-7","article-title":"Application of CT in the investigation of angiogenesis in oncology","volume":"7","author":"Miles","year":"2000","journal-title":"Acad Radiol"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"B28","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1038\/s41586-019-1799-6","article-title":"International evaluation of an AI system for breast cancer screening","volume":"577","author":"McKinney","year":"2020","journal-title":"Nature"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20211136","article-title":"Clinical application of deep learning and radiomics in hepatic disease imaging: a systematic scoping review","volume":"95","author":"Wang","year":"2022","journal-title":"Br J Radiol"},{"key":"B30","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.diii.2022.10.001","article-title":"Artificial intelligence: A review of current applications in hepatocellular carcinoma imaging","volume":"104","author":"Pellat","year":"2023","journal-title":"Diagn Interventional Imaging"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1131","DOI":"10.1038\/s41467-024-45325-9","article-title":"A multicenter clinical AI system study for detection and diagnosis of focal liver lesions","volume":"15","author":"Ying","year":"2024","journal-title":"Nat Commun"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.dld.2025.06.017","article-title":"Identification of high-risk hepatoblastoma in the CHIC risk stratification system based on enhanced CT radiomics features","volume":"57","author":"Yang","year":"2025","journal-title":"Digestive Liver Disease: Off J Ital Soc Gastroenterol Ital Assoc For Study Liver"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1007\/s00431-023-05113-x","article-title":"MRI-based deep learning model for differentiation of hepatic hemangioma and hepatoblastoma in early infancy","volume":"182","author":"Yang","year":"2023","journal-title":"Eur J Pediatr"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2018.05.053","article-title":"Repeatability and reproducibility of radiomic features: A systematic review","volume":"102","author":"Traverso","year":"2018","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1080\/0284186x.2018.1445283","article-title":"Influence of inter-observer delineation variability on radiomics stability in different tumor sites","volume":"57","author":"Pavic","year":"2018","journal-title":"Acta Oncol (Stockholm Sweden)"},{"key":"B36","doi-asserted-by":"publisher","first-page":"103228","DOI":"10.1016\/j.eclinm.2025.103228","article-title":"Artificial intelligence for diagnostics in radiology practice: a rapid systematic scoping review","volume":"83","author":"Lawrence","year":"2025","journal-title":"EClinicalMedicine"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1093\/bjrai\/ubaf016","article-title":"Diagnostic accuracy of artificial intelligence-assisted radiology assessment of cancer: a systematic review","volume":"2","author":"Zhao","year":"2025","journal-title":"BJR Artif Intell"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.240531","article-title":"An explainable deep learning model for focal liver lesion diagnosis using multiparametric MRI","volume":"7","author":"Shen","year":"2025","journal-title":"Radiol Artif Intell"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0256152","article-title":"Radiomics machine learning study with a small sample size: Single random training-test set split may lead to unreliable results","volume":"16","author":"An","year":"2021","journal-title":"PloS One"},{"key":"B40","doi-asserted-by":"publisher","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":"B41","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.jclinepi.2016.03.022","article-title":"Partial verification bias and incorporation bias affected accuracy estimates of diagnostic studies for biomarkers that were part of an existing composite gold standard","volume":"78","author":"Karch","year":"2016","journal-title":"J Clin Epidemiol"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/5801662","article-title":"Diagnostic accuracy studies in radiology: how to recognize and address potential sources of bias","volume":"2021","author":"Pavlou","year":"2021","journal-title":"Radiol Res Pract"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1923907\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T05:32:28Z","timestamp":1787549548000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1923907\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"references-count":42,"alternative-id":["10.3389\/fonc.2026.1923907"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1923907","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,24]]},"article-number":"1923907"}}