Top

Diagnostic Pathology

Published in:

Open Access 01-12-2021 | Primary Sclerosing Cholangitis | Research

Chronic cholestasis detection by a novel tool: automated analysis of cytokeratin 7-stained liver specimens

Authors: Nelli Sjöblom, Sonja Boyd, Anniina Manninen, Anna Knuuttila, Sami Blom, Martti Färkkilä, Johanna Arola

Published in: Diagnostic Pathology | Issue 1/2021

Abstract

Background

The objective was to build a novel method for automated image analysis to locate and quantify the number of cytokeratin 7 (K7)-positive hepatocytes reflecting cholestasis by applying deep learning neural networks (AI model) in a cohort of 210 liver specimens. We aimed to study the correlation between the AI model’s results and disease progression. The cohort of liver biopsies which served as a model of chronic cholestatic liver disease comprised of patients diagnosed with primary sclerosing cholangitis (PSC).

Methods

In a cohort of patients with PSC identified from the PSC registry of the University Hospital of Helsinki, their K7-stained liver biopsy specimens were scored by a pathologist (human K7 score) and then digitally analyzed for K7-positive hepatocytes (K7%area). The digital analysis was by a K7-AI model created in an Aiforia Technologies cloud platform. For validation, values were human K7 score, stage of disease (Metavir and Nakunuma fibrosis score), and plasma liver enzymes indicating clinical cholestasis, all subjected to correlation analysis.

Results

The K7-AI model results (K7%area) correlated with the human K7 score (0.896; p < 2.2e^− 16). In addition, K7%area correlated with stage of PSC (Metavir 0.446; p < 1.849e^− 10 and Nakanuma 0.424; p < 4.23e^− 10) and with plasma alkaline phosphatase (P-ALP) levels (0.369, p < 5.749e^− 5).

Conclusions

The accuracy of the AI-based analysis was comparable to that of the human K7 score. Automated quantitative image analysis correlated with stage of PSC and with P-ALP. Based on the results of the K7-AI model, we recommend K7 staining in the assessment of cholestasis by means of automated methods that provide fast (9.75 s/specimen) quantitative analysis.

Available only for authorised users

Goodman ZD. Grading and staging systems for inflammation and fibrosis in chronic liver diseases. J Hepatol. 2007;47(4):598–607. https://doi.org/10.1016/j.jhep.2007.07.006.CrossRefPubMed

Starling C, Bhathal PS, Quaglia A. Do orcein-positive copper-binding protein deposits and cytokeratin 7 co-localise in periportal hepatocytes in chronic cholestasis? J Clin Pathol. 2018;71(6):563–4. https://doi.org/10.1136/jclinpath-2018-205139.CrossRefPubMed

Quaglia A, Bhathal PS. Copper, copper-binding protein and cytokeratin 7 in biliary disorders. Histopathology. 2017;71(6):1006–8. https://doi.org/10.1111/his.13314.CrossRefPubMed

Van Eyken P, Sciot R, Desmet VJ. A cytokeratin immunohistochemical study of cholestatic liver disease: evidence that hepatocytes can express ‘bile duct-type’ cytokeratins. Histopathology. 1989;15(2):125–35. https://doi.org/10.1111/j.1365-2559.1989.tb03060.x.CrossRefPubMed

Bateman AC, Hubscher SG. Cytokeratin expression as an aid to diagnosis in medical liver biopsies. Histopathology. 2010;56(4):415–25. https://doi.org/10.1111/j.1365-2559.2009.03391.x.CrossRefPubMed

Barakauskiene A, Speiciene D, Liakina V, Semuchiniene T, Valantinas J. Expression of cytokeratin 7 as a histological marker of cholestasis and stages of primary biliary cirrhosis. Medicina (Kaunas, Lithuania). 2011;47(1):31–8.

Seki H, Ikeda F, Nanba S, Moritou Y, Takeuchi Y, Yasunaka T, et al. Aberrant expression of keratin 7 in hepatocytes as a predictive marker of rapid progression to hepatic failure in asymptomatic primary biliary cirrhosis. Acta Medica Okayama. 2015;69(3):137–44. https://doi.org/10.18926/AMO/53520.CrossRefPubMed

Yabushita K, Yamamoto K, Ibuki N, Okano N, Matsumura S, Okamoto R, et al. Aberrant expression of cytokeratin 7 as a histological marker of progression in primary biliary cirrhosis. Liver. 2001;21(1):50–5. https://doi.org/10.1034/j.1600-0676.2001.210108.x.CrossRefPubMed

Wendum D, Layese R, Ganne-Carrie N, Bourcier V, Merabtene F, Cagnot C, et al. Influence of progenitor-derived regeneration markers on hepatitis C virus-related cirrhosis outcome (ANRS CO12 CirVir cohort). Hepatology (Baltimore, Md.). 2018;68(4):1534–48. https://doi.org/10.1002/hep.29927.CrossRef

10.

Pavlides M, Birks J, Fryer E, Delaney D, Sarania N, Banerjee R, et al. Interobserver variability in histologic evaluation of liver fibrosis using categorical and quantitative scores. Am J Clin Pathol. 2017;147(4):364–9. https://doi.org/10.1093/ajcp/aqx011.CrossRefPubMedPubMedCentral

11.

Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition; 1998. https://doi.org/10.1109/5.726791.CrossRef

12.

Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2015. p. 1–9.

13.

Penttinen AM, Parkkinen I, Blom S, Kopra J, Andressoo JO, Pitkanen K, et al. Implementation of deep neural networks to count dopamine neurons in substantia nigra. Eur J Neurosci. 2018;48(6):2354–61. https://doi.org/10.1111/ejn.14129.CrossRefPubMedPubMedCentral

14.

Mäkelä K, Mäyränpää MI, Sihvo HK, Bergman P, Sutinen E, Ollila H, Kaarteenaho R, Myllärniemi M. Artificial intelligence identifies inflammation and confirms fibroblast foci as prognostic tissue biomarkers in idiopathic pulmonary fibrosis. Hum Pathol. 2021;107:58–68. https://doi.org/10.1016/j.humpath.2020.10.008.

15.

LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436–44. https://doi.org/10.1038/nature14539.CrossRef

16.

Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Adv Neural Inf Proces Syst. 2012;25:1097–105.

17.

O’Mahony N, Campbell S, Carvalho A, Harapanahalli S, Hernandez GV, Krpalkova, et al. Deep learning vs. traditional computer vision. In Science and Information Conference. Springer; 2019. p. 128–44.

18.

Dyson JK, Beuers U, Jones DEJ, Lohse AW, Hudson M. Primary sclerosing cholangitis. Lancet (London, England). 2018;391(10139):2547–59. https://doi.org/10.1016/S0140-6736(18)30300-3.CrossRef

19.

Nakanuma Y, Zen Y, Harada K, Sasaki M, Nonomura A, Uehara T, et al. Application of a new histological staging and grading system for primary biliary cirrhosis to liver biopsy specimens: Interobserver agreement. Pathol Int. 2010;60(3):167–74. https://doi.org/10.1111/j.1440-1827.2009.02500.x.CrossRefPubMed

20.

de Vries EM, de Krijger M, Farkkila M, Arola J, Schirmacher P, Gotthardt D, et al. Validation of the prognostic value of histologic scoring systems in primary sclerosing cholangitis: an international cohort study. Hepatology (Baltimore, Md.). 2017;65(3):907–19. https://doi.org/10.1002/hep.28963.CrossRef

21.

European Association for the Study of the Liver. EASL clinical practice guidelines: Management of cholestatic liver diseases. J Hepatol. 2009;51(2):237–67. https://doi.org/10.1016/j.jhep.2009.04.009.CrossRef

22.

Chapman R, Fevery J, Kalloo A, Nagorney DM, Boberg KM, Shneider B, et al. Diagnosis and management of primary sclerosing cholangitis. Hepatology (Baltimore, Md.). 2010;51(2):660–78. https://doi.org/10.1002/hep.23294.CrossRef

23.

Ponsioen CY, Chapman RW, Chazouilleres O, Hirschfield GM, Karlsen TH, Lohse AW, et al. Surrogate endpoints for clinical trials in primary sclerosing cholangitis: Review and results from an international PSC study group consensus process. Hepatology (Baltimore, Md.). 2016;63(4):1357–67. https://doi.org/10.1002/hep.28256.CrossRef

24.

Kakuda Y, Harada K, Sawada-Kitamura S, Ikeda H, Sato Y, Sasaki M, et al. Evaluation of a new histologic staging and grading system for primary biliary cirrhosis in comparison with classical systems. Human Pathol. 2013;44(6):1107–17. https://doi.org/10.1016/j.humpath.2012.09.017.CrossRef

25.

Rousselet MC, Michalak S, Dupre F, Croue A, Bedossa P, Saint-Andre JP, et al. Sources of variability in histological scoring of chronic viral hepatitis. Hepatology (Baltimore, Md.). 2005;41(2):257–64. https://doi.org/10.1002/hep.20535.CrossRef

26.

Teutsch HF. The modular microarchitecture of human liver. Hepatology (Baltimore, Md.). 2005;42(2):317–25. https://doi.org/10.1002/hep.20764.CrossRef

27.

Yagi Y, Gilbertson JR. The importance of optical optimization in whole slide imaging (WSI) and digital pathology imaging. Diagn Pathol. 2008;3(S1). https://doi.org/10.1186/1746-1596-3-S1-S1.

28.

Goet JC, Floreani A, Verhelst X, Cazzagon N, Perini L, Lammers WJ, et al. Validation, clinical utility and limitations of the Amsterdam-oxford model for primary sclerosing cholangitis. J Hepatol. 2019;71(5):992–9. https://doi.org/10.1016/j.jhep.2019.06.012.CrossRefPubMed

29.

Parwani AV. Next generation diagnostic pathology: use of digital pathology and artificial intelligence tools to augment a pathological diagnosis. Diagn Pathol. 2019;14(1):138. https://doi.org/10.1186/s13000-019-0921-2.CrossRefPubMedPubMedCentral

Title: Chronic cholestasis detection by a novel tool: automated analysis of cytokeratin 7-stained liver specimens
Authors: Nelli Sjöblom
Sonja Boyd
Anniina Manninen
Anna Knuuttila
Sami Blom
Martti Färkkilä
Johanna Arola
Publication date: 01-12-2021
Publisher: BioMed Central
Keywords: Primary Sclerosing Cholangitis
Artificial Intelligence
Published in: Diagnostic Pathology / Issue 1/2021
Electronic ISSN: 1746-1596
DOI: https://doi.org/10.1186/s13000-021-01102-6

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Chronic cholestasis detection by a novel tool: automated analysis of cytokeratin 7-stained liver specimens

Abstract

Background

Methods

Results

Conclusions

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Background

Methods

Results

Conclusions

Please log in to get access to this content

Other articles of this Issue 1/2021

Interobserver variability between experienced and inexperienced observers in the histopathological analysis of Wilms tumors: a pilot study for future algorithmic approach

Long noncoding RNA TUG1 regulates the progression of colorectal cancer through miR-542-3p/TRIB2 axis and Wnt/β-catenin pathway

Detection of BCOR gene rearrangement in Ewing-like sarcoma: an important diagnostic tool

Endobronchial sialolipoma. Case report

Pulmonary tumor with Notochordal differentiation: a case report and morphologic, Immunohistochemical and molecular study of benign Notochordal cell tumor originating in the lung

Giant vascular eccrine spiradenoma: the first case in the scrotum and review of the literature author