Abstract
Subtyping of hepatocellular adenoma (HCA) is an important task in practice as different subtypes may have different clinical outcomes and management algorithms. Definitive subtyping is currently dependent on immunohistochemical and molecular testing. The association between some morphologic/clinical features and HCA subtypes has been reported; however, the predictive performance of these features has been controversial. In this study, we attempted machine learning based methods to select an efficient and parsimonious set of morphologic/clinical features for differentiating a HCA subtype from the others, and then assessed the performance of the selected features in identifying the correct subtypes. We first examined 50 liver HCA resection specimens collected at the University of Washington and Kobe University/Kings College London, including HNF1α-mutated HCA (H-HCA) (n = 16), inflammatory HCA (I-HCA) (n = 20), beta-catenin activated HCA (β-HCA) (n = 8), and unclassified HCA (U-HCA) (n = 6). Twenty-six morphologic/clinical features were assessed. We used LASSO (least absolute shrinkage and selection operator) to select key features that could differentiate a subtype from the others. We further performed SVM (support vector machine) analysis to assess the performance (sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy) of the selected features in HCA subtyping in an independent cohort of liver resection samples (n = 20) collected at the University of Wisconsin-Madison. With some overlap, different combinations of morphologic/clinical features were selected for each subtype. Based on SVM analysis, the selected features classified HCA into correct subtypes with an overall accuracy of at least 80%. Our findings are useful for initial diagnosis and subtyping of HCA, especially in clinical settings without access to immunohistochemical and molecular assays.
Similar content being viewed by others
References
Nault JC, Couchy G, Balabaud C, Morcrette G, Caruso S, Blanc JF, et al. (2017) Molecular classification of hepatocellular adenoma associates with risk factors, bleeding, and malignant transformation. Gastroenterology 152:880–894 e886.
Nault JC, Paradis V, Cherqui D, Vilgrain V, Zucman-Rossi J (2017) Molecular classification of hepatocellular adenoma in clinical practice. J Hepatol 67:1074–1083
Nault JC, Zucman Rossi J (2013) Molecular classification of hepatocellular adenomas. Int J Hepatol. 2013:315947
Zucman-Rossi J, Jeannot E, Nhieu JT, Scoazec JY, Guettier C, Rebouissou S et al (2006) Genotype-phenotype correlation in hepatocellular adenoma: new classification and relationship with HCC. Hepatology 43:515–524
Bioulac-Sage P, Rebouissou S, Thomas C, Blanc JF, Saric J, Sa Cunha A et al (2007) Hepatocellular adenoma subtype classification using molecular markers and immunohistochemistry. Hepatology 46:740–748
Bioulac-Sage P, Laumonier H, Couchy G, Le Bail B, Sa Cunha A, Rullier A et al (2009) Hepatocellular adenoma management and phenotypic classification: the Bordeaux experience. Hepatology 50:481–489
Vedie AL, Sutter O, Ziol M, Nault JC (2018) Molecular classification of hepatocellular adenomas: impact on clinical practice. Hepat Oncol 5:HEP04
Bluteau O, Jeannot E, Bioulac-Sage P, Marques JM, Blanc JF, Bui H et al (2002) Bi-allelic inactivation of TCF1 in hepatic adenomas. Nat Genet 32:312–315
Pelletier L, Rebouissou S, Paris A, Rathahao-Paris E, Perdu E, Bioulac-Sage P et al (2010) Loss of hepatocyte nuclear factor 1alpha function in human hepatocellular adenomas leads to aberrant activation of signaling pathways involved in tumorigenesis. Hepatology 51:557–566
Rebouissou S, Imbeaud S, Balabaud C, Boulanger V, Bertrand-Michel J, Terce F et al (2007) HNF1alpha inactivation promotes lipogenesis in human hepatocellular adenoma independently of SREBP-1 and carbohydrate-response element-binding protein (ChREBP) activation. J Biol Chem 282:14437–14446
Bioulac-Sage P, Blanc JF, Rebouissou S, Balabaud C, Zucman-Rossi J (2007) Genotype phenotype classification of hepatocellular adenoma. World J Gastroenterol 13:2649–2654
Pilati C, Amessou M, Bihl MP, Balabaud C, Nhieu JT, Paradis V et al (2011) Somatic mutations activating STAT3 in human inflammatory hepatocellular adenomas. J Exp Med 208:1359–1366
Pilati C, Letouze E, Nault JC, Imbeaud S, Boulai A, Calderaro J et al (2014) Genomic profiling of hepatocellular adenomas reveals recurrent FRK-activating mutations and the mechanisms of malignant transformation. Cancer Cell 25:428–441
Nault JC, Fabre M, Couchy G, Pilati C, Jeannot E, Tran Van Nhieu J, et al. GNAS-activating mutations define a rare subgroup of inflammatory liver tumors characterized by STAT3 activation. J Hepatol. 2012;56:184–191.
Chen YW, Jeng YM, Yeh SH, Chen PJ (2002) P53 gene and Wnt signaling in benign neoplasms: beta-catenin mutations in hepatic adenoma but not in focal nodular hyperplasia. Hepatology 36(4 Pt 1):927–935
Thompson MD, Monga SP (2007) WNT/beta-catenin signaling in liver health and disease. Hepatology 45:1298–1305
Hale G, Liu X, Hu J, Xu Z, Che L, Solomon D et al (2016) Correlation of exon 3 beta-catenin mutations with glutamine synthetase staining patterns in hepatocellular adenoma and hepatocellular carcinoma. Mod Pathol 29:1370–1380
Rebouissou S, Franconi A, Calderaro J, Letouze E, Imbeaud S, Pilati C et al (2016) Genotype-phenotype correlation of CTNNB1 mutations reveals different ss-catenin activity associated with liver tumor progression. Hepatology 64:2047–2061
Sempoux C, Gouw ASH, Dunet V, Paradis V, Balabaud C, Bioulac-Sage P (2021) Predictive patterns of glutamine synthetase immunohistochemical staining in CTNNB1-mutated hepatocellular adenomas. Am J Surg Pathol 45:477–487
Evason KJ, Grenert JP, Ferrell LD, Kakar S (2013) Atypical hepatocellular adenoma-like neoplasms with beta-catenin activation show cytogenetic alterations similar to well-differentiated hepatocellular carcinomas. Hum Pathol 44:750–758
Torbenson M, Zen Y, Yeh MM (2018) Tumors of the liver, AFIP Atlas of tumor pathology series 4: American Registry of Pathology
Nault JC, Couchy G, Caruso S, Meunier L, Caruana L, Letouze E et al (2018) Argininosuccinate synthase 1 and periportal gene expression in sonic hedgehog hepatocellular adenomas. Hepatology 68:964–976
Joseph NM, Ferrell LD, Jain D, Torbenson MS, Wu TT, Yeh MM et al (2014) Diagnostic utility and limitations of glutamine synthetase and serum amyloid-associated protein immunohistochemistry in the distinction of focal nodular hyperplasia and inflammatory hepatocellular adenoma. Mod Pathol 27:62–72
Margolskee E, Bao F, de Gonzalez AK, Moreira RK, Lagana S, Sireci AN et al (2016) Hepatocellular adenoma classification: a comparative evaluation of immunohistochemistry and targeted mutational analysis. Diagn Pathol 11:27
Bioulac-Sage P, Taouji S, Le Bail B, Possenti L, Balabaud C (2013) Value and limits of routine histology alone or combined with glutamine synthetase immunostaining in the diagnosis of hepatocellular adenoma subtypes on surgical specimens. Int J Hepatol. 2013:417323
Alberti N, Castain C, Crombe A, Frulio N (2015) Steatotic hepatocellular adenomas with different phenotypic subtypes: a case report. Clin Res Hepatol Gastroenterol 39:e17-22
Larson BK, Guindi M (2017) A Limited Immunohistochemical Panel Can Subtype Hepatocellular Adenomas for Routine Practice. Am J Clin Pathol 147:557–570
Kakar S, Evason KJ, Ferrell LD (2014) Well-differentiated hepatocellular neoplasm of uncertain malignant potential: proposal for a new diagnostic category–reply. Hum Pathol 45:660–661
Bedossa P, Burt AD, Brunt EM, Callea F, Clouston AD, Dienes HP et al (2014) Well-differentiated hepatocellular neoplasm of uncertain malignant potential: proposal for a new diagnostic category. Hum Pathol 45:658–660
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297
Kuhn M (2008) Building predictive models in R using the caret package 28(5):26.
Fonseca S, Hoton D, Dardenne S, Annet L, Hubert C, Godecharles S et al (2013) Histological and immunohistochemical revision of hepatocellular adenomas: a learning experience. Int J Hepatol. 2013:398308
van Aalten SM, Verheij J, Terkivatan T, Dwarkasing RS, de Man RA, Ijzermans JN (2011) Validation of a liver adenoma classification system in a tertiary referral centre: implications for clinical practice. J Hepatol 55:120–125
Bellamy CO, Maxwell RS, Prost S, Azodo IA, Powell JJ, Manning JR (2013) The value of immunophenotyping hepatocellular adenomas: consecutive resections at one UK centre. Histopathology 62:431–445
Shafizadeh N, Genrich G, Ferrell L, Kakar S (2014) Hepatocellular adenomas in a large community population, 2000 to 2010: reclassification per current World Health Organization classification and results of long-term follow-up. Hum Pathol 45:976–983
Pan J, Chen L, Fan J, Zhou J, Qin L, Tan Y et al (2014) Retrospective study of hepatocellular adenomas based on the phenotypic classification system: a report from China. Histol Histopathol 29:243–249
Paradis V, Benzekri A, Dargere D, Bieche I, Laurendeau I, Vilgrain V et al (2004) Telangiectatic focal nodular hyperplasia: a variant of hepatocellular adenoma. Gastroenterology 126:1323–1329
Paradis V, Champault A, Ronot M, Deschamps L, Valla DC, Vidaud D et al (2007) Telangiectatic adenoma: an entity associated with increased body mass index and inflammation. Hepatology 46:140–146
van Aalten SM, de Man RA, JN IJ, Terkivatan T (2012) Systematic review of haemorrhage and rupture of hepatocellular adenomas. Br J Surg 99:911-916.
Author information
Authors and Affiliations
Contributions
Matthew M. Yeh, Yoh Zen, Yao-Zhong Liu, and Yongjun Liu conceived and designed the study. Yongjun Liu, Yoh Zen, Chie Inomoto, and Matthew M. Yeh collected the clinical data and reviewed the slides. Yao-Zhong Liu, Lifu Sun, and Yongjun Liu performed the statistical analyses. Yongjun Liu, Yao-Zhong Liu, Yoh Zen, and Matthew M. Yeh wrote the manuscript.
Corresponding author
Ethics declarations
Ethical approval
This study was approved by the institutional review boards of the University of Washington, Kobe University/King’s College Hospital, and University of Wisconsin-Madison.
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Liu, Y., Liu, YZ., Sun, L. et al. Subtyping of hepatocellular adenoma: a machine learning-based approach. Virchows Arch 481, 49–61 (2022). https://doi.org/10.1007/s00428-022-03311-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00428-022-03311-w