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

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

doi:10.1186/s13000-021-01102-6

Abstract

BackgroundThe 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).MethodsIn 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.ResultsThe 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).ConclusionsThe 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.

Highlights

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
Our 210 primary sclerosing cholangitis (PSC) patients with K7-immuno-stained histological liver samples served as a cohort exemplifying chronic cholestatic liver disease
In partial validation of the K7-Artificial Intelligence (AI) model, we found that K7%area correlated both with fibrosis stage demonstrating disease stage, and with the biochemical markers of chronic cholestasis, such as plasma ALP levels

Summary

Introduction

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. The cohort of liver biopsies which served as a model of chronic cholestatic liver disease comprised of patients diagnosed with primary sclerosing cholangitis (PSC). A core needle biopsy specimen from the liver is the gold standard for the diagnosis of liver diseases and is considered important in the assessment of inflammatory activity and stage of fibrosis [1]. 7(K7) is a common immunohistochemical (IHC) marker for chronic cholestasis in liver biopsies - especially in liver diseases with biliary tract inflammation [2]. In chronic cholestasis, periportal hepatocytes and intermediate hepatobiliary cells (progenitor cells) stain positive for K7 [3, 4].

Objectives

Methods

Results

Conclusion