{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:32:46Z","timestamp":1769041966528,"version":"3.49.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T00:00:00Z","timestamp":1756339200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T00:00:00Z","timestamp":1756339200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Lanzhou Science and Technology Bureau Project","award":["020-2-11-9"],"award-info":[{"award-number":["020-2-11-9"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Insights Imaging"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Objective<\/jats:title>\n            <jats:p>To develop a CT-based deep learning model for predicting the macrotrabecular-massive (MTM) subtype of hepatocellular carcinoma (HCC) and to compare its diagnostic performance with machine learning models.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Materials and methods<\/jats:title>\n            <jats:p>We retrospectively collected contrast-enhanced CT data from patients diagnosed with HCC via histopathological examination between January 2019 and August 2023. These patients were recruited from two medical centers. All analyses were performed using two-dimensional regions of interest. We developed a novel deep learning network based on ResNet-50, named ResNet-ViT Contrastive Learning (RVCL). The RVCL model was compared against baseline deep learning models and machine learning models. Additionally, we developed a multimodal prediction model by integrating deep learning models with clinical parameters. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC).<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>A total of 368 patients (mean age, 56\u2009\u00b1\u200910; 285 [77%] male) from two institutions were retrospectively enrolled. Our RVCL model demonstrated superior diagnostic performance in predicting MTM (AUC\u2009=\u20090.93) on the external test set compared to the five baseline deep learning models (AUCs range 0.46\u20130.72, all <jats:italic>p<\/jats:italic>\u2009&lt;\u20090.05) and the three machine learning models (AUCs range 0.49-0.60, all <jats:italic>p<\/jats:italic>\u2009&lt;\u20090.05). However, integrating the clinical biomarker Alpha-Fetoprotein (AFP) into the RVCL model did not significant improvement in diagnostic performance (internal test data set: AUC 0.99 vs 0.95 [<jats:italic>p<\/jats:italic>\u2009=\u20090.08]; external test data set: AUC 0.98 vs 0.93 [<jats:italic>p<\/jats:italic>\u2009=\u20090.05]).<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusion<\/jats:title>\n            <jats:p>The deep learning model based on contrast-enhanced CT can accurately predict the MTM subtype in HCC patients, offering a smart tool for clinical decision-making.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Critical relevance statement<\/jats:title>\n            <jats:p>The RVCL model introduces a transformative approach to the non-invasive diagnosis MTM subtype of HCC by harmonizing convolutional neural networks and vision transformers within a unified architecture.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Key Points<\/jats:title>\n            <jats:p>\n              <jats:list list-type=\"bullet\">\n                <jats:list-item>\n                  <jats:p>The RVCL model can accurately predict the MTM subtype.<\/jats:p>\n                <\/jats:list-item>\n                <jats:list-item>\n                  <jats:p>Deep learning outperforms machine learning for predicting MTM subtype.<\/jats:p>\n                <\/jats:list-item>\n                <jats:list-item>\n                  <jats:p>RVCL boosts accuracy and guides personalized therapy.<\/jats:p>\n                <\/jats:list-item>\n              <\/jats:list>\n            <\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Graphical Abstract<\/jats:title>\n          <\/jats:sec>","DOI":"10.1186\/s13244-025-02063-w","type":"journal-article","created":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T13:42:02Z","timestamp":1756388522000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Macrotrabecular-massive subtype in hepatocellular carcinoma based on contrast-enhanced CT: deep learning outperforms machine learning"],"prefix":"10.1186","volume":"16","author":[{"given":"Lulu","family":"Jia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanchen","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianxin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinkui","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7632-1922","authenticated-orcid":false,"given":"Junqiang","family":"Lei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,28]]},"reference":[{"key":"2063_CR1","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1016\/j.jhep.2017.05.014","volume":"67","author":"J Calderaro","year":"2017","unstructured":"Calderaro J, Couchy G, Imbeaud S et al (2017) Histological subtypes of hepatocellular carcinoma are related to gene mutations and molecular tumour classification. J Hepatol 67:727\u2013738","journal-title":"J Hepatol"},{"key":"2063_CR2","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1111\/his.13975","volume":"76","author":"ID Nagtegaal","year":"2020","unstructured":"Nagtegaal ID, Odze RD, Klimstra D et al (2020) The 2019 WHO classification of tumours of the digestive system. Histopathology 76:182\u2013188","journal-title":"Histopathology"},{"key":"2063_CR3","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1002\/hep.29762","volume":"68","author":"M Ziol","year":"2018","unstructured":"Ziol M, Pot\u00e9 N, Amaddeo G et al (2018) Macrotrabecular-massive hepatocellular carcinoma: a distinctive histological subtype with clinical relevance. Hepatology 68:103\u2013112","journal-title":"Hepatology"},{"key":"2063_CR4","doi-asserted-by":"publisher","first-page":"542","DOI":"10.1002\/1097-0142(19830201)51:3<542::AID-CNCR2820510330>3.0.CO;2-2","volume":"51","author":"K Kishi","year":"1983","unstructured":"Kishi K, Shikata T, Hirohashi S, Hasegawa H, Yamazaki S, Makuuchi M (1983) Hepatocellular carcinoma. A clinical and pathologic analysis of 57 hepatectomy cases. Cancer 51:542\u2013548","journal-title":"Cancer"},{"key":"2063_CR5","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1007\/BF00716991","volume":"413","author":"F Kondo","year":"1988","unstructured":"Kondo F, Wada K, Kondo Y (1988) Morphometric analysis of hepatocellular carcinoma. Virchows Arch A Pathol Anat Histopathol 413:425\u2013430","journal-title":"Virchows Arch A Pathol Anat Histopathol"},{"key":"2063_CR6","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1111\/liv.12889","volume":"36","author":"PS Tan","year":"2016","unstructured":"Tan PS, Nakagawa S, Goossens N et al (2016) Clinicopathological indices to predict hepatocellular carcinoma molecular classification. Liver Int 36:108\u2013118","journal-title":"Liver Int"},{"key":"2063_CR7","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.230255","volume":"308","author":"M Li","year":"2023","unstructured":"Li M, Fan Y, You H et al (2023) Dual-energy CT deep learning radiomics to predict macrotrabecular-massive hepatocellular carcinoma. Radiology 308:e230255","journal-title":"Radiology"},{"key":"2063_CR8","doi-asserted-by":"crossref","unstructured":"Schmittnaegel M, Rigamonti N, Kadioglu E et al (2017) Dual angiopoietin-2 and VEGFA inhibition elicits antitumor immunity that is enhanced by PD-1 checkpoint blockade. Sci Transl Med 9:eaak9670","DOI":"10.1126\/scitranslmed.aak9670"},{"key":"2063_CR9","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/s00262-020-02691-9","volume":"70","author":"LL Liu","year":"2021","unstructured":"Liu LL, Zhang SW, Chao X et al (2021) Coexpression of CMTM6 and PD-L1 as a predictor of poor prognosis in macrotrabecular-massive hepatocellular carcinoma. Cancer Immunol Immunother 70:417\u2013429","journal-title":"Cancer Immunol Immunother"},{"key":"2063_CR10","doi-asserted-by":"publisher","first-page":"1139","DOI":"10.1002\/hep.32201","volume":"75","author":"Y Kurebayashi","year":"2022","unstructured":"Kurebayashi Y, Matsuda K, Ueno A et al (2022) Immunovascular classification of HCC reflects reciprocal interaction between immune and angiogenic tumor microenvironments. Hepatology 75:1139\u20131153","journal-title":"Hepatology"},{"key":"2063_CR11","doi-asserted-by":"publisher","first-page":"4024","DOI":"10.1007\/s00330-022-09322-0","volume":"33","author":"M Luo","year":"2023","unstructured":"Luo M, Liu X, Yong J et al (2023) Preoperative prediction of macrotrabecular-massive hepatocellular carcinoma based on B-Mode US and CEUS. Eur Radiol 33:4024\u20134033","journal-title":"Eur Radiol"},{"key":"2063_CR12","doi-asserted-by":"publisher","first-page":"7696","DOI":"10.1007\/s00330-021-07898-7","volume":"31","author":"J Chen","year":"2021","unstructured":"Chen J, Xia C, Duan T et al (2021) Macrotrabecular-massive hepatocellular carcinoma: imaging identification and prediction based on gadoxetic acid-enhanced magnetic resonance imaging. Eur Radiol 31:7696\u20137704","journal-title":"Eur Radiol"},{"key":"2063_CR13","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1148\/radiol.2020192230","volume":"295","author":"S Mul\u00e9","year":"2020","unstructured":"Mul\u00e9 S, Galletto Pregliasco A, Tenenhaus A et al (2020) Multiphase liver MRI for identifying the macrotrabecular-massive subtype of hepatocellular carcinoma. Radiology 295:562\u2013571","journal-title":"Radiology"},{"key":"2063_CR14","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.jhep.2020.08.013","volume":"74","author":"H Rhee","year":"2021","unstructured":"Rhee H, Cho ES, Nahm JH et al (2021) Gadoxetic acid-enhanced MRI of macrotrabecular-massive hepatocellular carcinoma and its prognostic implications. J Hepatol 74:109\u2013121","journal-title":"J Hepatol"},{"key":"2063_CR15","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.221291","volume":"307","author":"Z Feng","year":"2023","unstructured":"Feng Z, Li H, Liu Q et al (2023) CT radiomics to predict macrotrabecular-massive subtype and immune status in hepatocellular carcinoma. Radiology 307:e221291","journal-title":"Radiology"},{"key":"2063_CR16","doi-asserted-by":"publisher","first-page":"661","DOI":"10.2147\/JHC.S364703","volume":"9","author":"A Sessa","year":"2022","unstructured":"Sessa A, Mul\u00e9 S, Brustia R et al (2022) Macrotrabecular-massive hepatocellular carcinoma: light and shadow in current knowledge. J Hepatocell Carcinoma 9:661\u2013670","journal-title":"J Hepatocell Carcinoma"},{"key":"2063_CR17","doi-asserted-by":"publisher","first-page":"3139","DOI":"10.1007\/s00261-021-02989-x","volume":"46","author":"Y Zhu","year":"2021","unstructured":"Zhu Y, Weng S, Li Y et al (2021) A radiomics nomogram based on contrast-enhanced MRI for preoperative prediction of macrotrabecular-massive hepatocellular carcinoma. Abdom Radiol (NY) 46:3139\u20133148","journal-title":"Abdom Radiol (NY)"},{"key":"2063_CR18","doi-asserted-by":"publisher","first-page":"2001","DOI":"10.3748\/wjg.v29.i13.2001","volume":"29","author":"Y Zhang","year":"2023","unstructured":"Zhang Y, He D, Liu J, Wei YG, Shi LL (2023) Preoperative prediction of macrotrabecular-massive hepatocellular carcinoma through dynamic contrast-enhanced magnetic resonance imaging-based radiomics. World J Gastroenterol 29:2001\u20132014","journal-title":"World J Gastroenterol"},{"key":"2063_CR19","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1007\/s00261-022-03722-y","volume":"48","author":"S Hu","year":"2023","unstructured":"Hu S, Kang Y, Xie Y et al (2023) 18F-FDG PET\/CT-based radiomics nomogram for preoperative prediction of macrotrabecular-massive hepatocellular carcinoma: a two-center study. Abdom Radiol (NY) 48:532\u2013542","journal-title":"Abdom Radiol (NY)"},{"key":"2063_CR20","doi-asserted-by":"publisher","first-page":"715","DOI":"10.2147\/JHC.S508091","volume":"12","author":"Y Li","year":"2025","unstructured":"Li Y, Duan S, Ren S et al (2025) Preoperative prediction of macrotrabecular-massive hepatocellular carcinoma using machine learning-based ultrasomics. J Hepatocell Carcinoma 12:715\u2013727","journal-title":"J Hepatocell Carcinoma"},{"key":"2063_CR21","doi-asserted-by":"publisher","first-page":"1749","DOI":"10.1001\/jamaoncol.2019.2996","volume":"5","author":"C Fitzmaurice","year":"2019","unstructured":"Fitzmaurice C, Abate D, Abbasi N et al (2019) Global, regional, and national cancer incidence, mortality, years of life lost, years lived with disability, and disability-adjusted life-years for 29 cancer groups, 1990 to 2017: a systematic analysis for the global burden of disease study. JAMA Oncol 5:1749\u20131768","journal-title":"JAMA Oncol"},{"key":"2063_CR22","doi-asserted-by":"publisher","first-page":"2373","DOI":"10.2147\/JHC.S480358","volume":"11","author":"J Pan","year":"2024","unstructured":"Pan J, Zhang C, Huang H et al (2024) Deciphering the prognostic and therapeutic value of a gene model associated with two aggressive hepatocellular carcinoma phenotypes using machine learning. J Hepatocell Carcinoma 11:2373\u20132390","journal-title":"J Hepatocell Carcinoma"},{"key":"2063_CR23","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1007\/s00261-023-04121-7","volume":"49","author":"F Chai","year":"2024","unstructured":"Chai F, Ma Y, Feng C et al (2024) Prediction of macrotrabecular-massive hepatocellular carcinoma by using MR-based models and their prognostic implications. Abdom Radiol (NY) 49:447\u2013457","journal-title":"Abdom Radiol (NY)"},{"key":"2063_CR24","doi-asserted-by":"publisher","first-page":"9017","DOI":"10.1002\/mp.17401","volume":"51","author":"Z Zhang","year":"2024","unstructured":"Zhang Z, Zhang W, He C et al (2024) Identification of macrotrabecular-massive hepatocellular carcinoma through multiphasic CT-based representation learning method. Med Phys 51:9017\u20139030","journal-title":"Med Phys"},{"key":"2063_CR25","doi-asserted-by":"publisher","first-page":"1508","DOI":"10.1007\/s11547-023-01719-1","volume":"128","author":"X He","year":"2023","unstructured":"He X, Li K, Wei R et al (2023) A multitask deep learning radiomics model for predicting the macrotrabecular-massive subtype and prognosis of hepatocellular carcinoma after hepatic arterial infusion chemotherapy. Radiol Med 128:1508\u20131520","journal-title":"Radiol Med"},{"key":"2063_CR26","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1148\/radiol.2019191022","volume":"294","author":"SM Humphries","year":"2020","unstructured":"Humphries SM, Notary AM, Centeno JP et al (2020) Deep learning enables automatic classification of emphysema pattern at CT. Radiology 294:434\u2013444","journal-title":"Radiology"},{"key":"2063_CR27","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1148\/radiol.2021211483","volume":"302","author":"D Mu","year":"2022","unstructured":"Mu D, Bai J, Chen W et al (2022) Calcium scoring at coronary CT angiography using deep learning. Radiology 302:309\u2013316","journal-title":"Radiology"},{"key":"2063_CR28","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.220425","volume":"307","author":"PM Johnson","year":"2023","unstructured":"Johnson PM, Lin DJ, Zbontar J et al (2023) Deep learning reconstruction enables prospectively accelerated clinical knee MRI. Radiology 307:e220425","journal-title":"Radiology"},{"key":"2063_CR29","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230229","volume":"6","author":"N Pecco","year":"2024","unstructured":"Pecco N, Della Rosa PA, Canini M et al (2024) Optimizing performance of transformer-based models for fetal brain MR image segmentation. Radiol Artif Intell 6:e230229","journal-title":"Radiol Artif Intell"},{"key":"2063_CR30","doi-asserted-by":"publisher","DOI":"10.1148\/ryct.230177","volume":"6","author":"MA Morales","year":"2024","unstructured":"Morales MA, Ghanbari F, Nakamori S et al (2024) Deformation-encoding deep learning transformer for high-frame-rate cardiac cine MRI. Radiol Cardiothorac Imaging 6:e230177","journal-title":"Radiol Cardiothorac Imaging"},{"key":"2063_CR31","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.230806","volume":"309","author":"F Khader","year":"2023","unstructured":"Khader F, M\u00fcller-Franzes G, Wang T et al (2023) Multimodal deep learning for integrating chest radiographs and clinical parameters: a case for transformers. Radiology 309:e230806","journal-title":"Radiology"},{"key":"2063_CR32","doi-asserted-by":"publisher","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. https:\/\/doi.org\/10.1145\/3065386","DOI":"10.1145\/3065386"},{"key":"2063_CR33","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. Preprint at https:\/\/arxiv.org\/abs\/1409.1556"},{"key":"2063_CR34","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. 2016 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, Las Vegas, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2063_CR35","unstructured":"Dosovitskiy A (2020) An image is worth 16\u2009\u00d7\u200916 words: transformers for image recognition at scale. Preprint at https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"2063_CR36","unstructured":"Tan M, Le Q (2019) Efficientnet: rethinking model scaling for convolutional neural networksInternational conference on machine learning. Preprint at https:\/\/arxiv.org\/abs\/1905.11946"}],"container-title":["Insights into Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13244-025-02063-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13244-025-02063-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13244-025-02063-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T05:03:49Z","timestamp":1757480629000},"score":1,"resource":{"primary":{"URL":"https:\/\/insightsimaging.springeropen.com\/articles\/10.1186\/s13244-025-02063-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,28]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["2063"],"URL":"https:\/\/doi.org\/10.1186\/s13244-025-02063-w","relation":{},"ISSN":["1869-4101"],"issn-type":[{"value":"1869-4101","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,28]]},"assertion":[{"value":"11 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Manuscripts reporting studies involving human participants, human data, or human tissue must: the study received approval from the Institutional Review Board of all participating centers (LDYYLL-2024-398;2022-432).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Due to its retrospective nature, the requirement for informed consent was waived.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests in this section.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"186"}}