Efficiency of Machine Learning Algorithms for the Determination of Macrovesicular Steatosis in Frozen Sections Stained with Sudan to Evaluate the Quality of the Graft in Liver Transplantation

Abstract

Liver transplantation is the only curative treatment option in patients diagnosed with end-stage liver disease. The low availability of organs demands an accurate selection procedure based on histological analysis, in order to evaluate the allograft. This assessment, traditionally carried out by a pathologist, is not exempt from subjectivity. In this sense, new tools based on machine learning and artificial vision are continuously being developed for the analysis of medical images of different typologies. Accordingly, in this work, we develop a computer vision-based application for the fast and automatic objective quantification of macrovesicular steatosis in histopathological liver section slides stained with Sudan stain. For this purpose, digital microscopy images were used to obtain thousands of feature vectors based on the RGB and CIE L*a*b* pixel values. These vectors, under a supervised process, were labelled as fat vacuole or non-fat vacuole, and a set of classifiers based on different algorithms were trained, accordingly. The results obtained showed an overall high accuracy for all classifiers (>0.99) with a sensitivity between 0.844 and 1, together with a specificity >0.99. In relation to their speed when classifying images, KNN and Naïve Bayes were substantially faster than other classification algorithms. Sudan stain is a convenient technique for evaluating ME in pre-transplant liver biopsies, providing reliable contrast and facilitating fast and accurate quantification through the machine learning algorithms tested.

Artificial intelligence in liver diseases: Improving diagnostics, prognostics and response prediction

“…All of these diseases share the clinical need for clear-cut diagnostic and prognostic systems. Several studies have focused on models quantifying steatosis, inflammation, hepatocellular ballooning and other morphological patterns in NAFLD patients, as well as the staging of liver fibrosis [20][21][22]. In 2014, Vanderbeck et al published one of the first studies using handcrafted features in a support vector machine algorithm to identify and quantify macrosteatosis, central veins, bile ducts and other structures on scanned H&E slides from NAFLD and healthy liver biopsies with an overall accuracy of 89% [23].…”

Diagnostic Assessment of Deep Learning Algorithms for Frozen Tissue Section Analysis in Women with Breast Cancer

“…However, the application of computer-aided diagnosis in frozen section pathology is still in its infancy. There have been several studies on the quantification of steatosis using deep learning for frozen liver biopsy sections [28,29] but few studies on computer-aided diagnosis in frozen section pathology of cancer surgery. Our group previously held HeLP Challenge 2018 to develop a deep learning algorithm for the diagnosis of SLN sections in breast cancer surgery as summarized in the introduction section.…”

Artificial Intelligence: Present and Future Potential for Solid Organ Transplantation

“…Perez-Sanz et al developed a quick and easy workflow to quantify steatosis content in Sudan-stained frozen sections of procurement biopsies through machine learning. Their algorithm, available as an open-source interactive web platform ( 50 ), proved highly accurate in comparison with the assessment of an expert pathologist. This tool could be extremely valuable for the decision-making in remote procurement locations, where an expert pathologist is not readily available.…”