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

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.

[1]  Matthew K. Matlock,et al.  Deep learning quantification of percent steatosis in donor liver biopsy frozen sections , 2020, EBioMedicine.

[2]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[3]  Emmanuelle Gouillart,et al.  scikit-image: image processing in Python , 2014, PeerJ.

[4]  Jun Kong,et al.  Liver Steatosis Segmentation With Deep Learning Methods , 2019, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[5]  I. Sauer,et al.  Prevalence of Steatosis Hepatis in the Eurotransplant Region: Impact on Graft Acceptance Rates , 2018, HPB surgery : a world journal of hepatic, pancreatic and biliary surgery.

[6]  Philipp Dutkowski,et al.  Liver transplantation using fatty livers: always feasible? , 2011, Journal of hepatology.

[7]  K. Washington,et al.  Assessment of Hepatic Steatosis by Expert Pathologists: The End of a Gold Standard , 2009, Annals of surgery.

[8]  Kuang-Yu Jen,et al.  Donor Liver Small Droplet Macrovesicular Steatosis Is Associated With Increased Risk for Recipient Allograft Rejection , 2017, The American journal of surgical pathology.

[9]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[10]  J. Lefkowitch Steatosis, Steatohepatitis and Related Conditions , 2021, Scheuer's Liver Biopsy Interpretation.

[11]  Jun Kong,et al.  Deep Learning Based Accurate Hepatic Steatosis Quantification for Histological Assessment of Liver Biopsies , 2020, Laboratory Investigation.

[12]  R. L. Panqueva Histopathological Evaluation of Liver Donors: An Approach to Intraoperative Consultation during Liver Transplantation , 2016 .

[13]  A. Tzallas,et al.  High-Throughput, Machine Learning–Based Quantification of Steatosis, Inflammation, Ballooning, and Fibrosis in Biopsies From Patients With Nonalcoholic Fatty Liver Disease , 2019, Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association.

[14]  J. Goss,et al.  Cold ischemia time is an important risk factor for post–liver transplant prolonged length of stay , 2018, Liver transplantation : official publication of the American Association for the Study of Liver Diseases and the International Liver Transplantation Society.

[15]  A. Dare,et al.  Donor Hepatic Steatosis and Outcome After Liver Transplantation: a Systematic Review , 2015, Journal of Gastrointestinal Surgery.

[16]  Jyotirmoy Chatterjee,et al.  Quantification of malaria parasitaemia using trainable semantic segmentation and capsnet , 2020, Pattern Recognit. Lett..

[17]  Andrew G. Dempster,et al.  Blood Cell Segmentation Using Minimum Area Watershed and Circle Radon Transformations , 2005, ISMM.

[18]  Scott L Nyberg,et al.  Assessment of donor liver steatosis: pathologist or automated software? , 2004, Human pathology.

[19]  John Hart,et al.  Comparing morphometric, biochemical, and visual measurements of macrovesicular steatosis of liver. , 2011, Human pathology.

[20]  Pedro J. Navarro,et al.  Machine Learning and Computer Vision System for Phenotype Data Acquisition and Analysis in Plants , 2016, Sensors.

[21]  Sinan Akosman,et al.  Update on Liver Transplantation: What is New Recently? , 2019, Euroasian journal of hepato-gastroenterology.

[22]  Miguel Angel García Ureña,et al.  Hepatic Steatosis in Liver Transplant Donors: Common Feature of Donor Population? , 1998, World Journal of Surgery.

[23]  T. Boyles,et al.  A validated method for quantifying macrovesicular hepatic steatosis in chronic hepatitis C. , 2007, Analytical and quantitative cytology and histology.

[24]  John M. Chambers,et al.  An Interface to Python , 2017 .

[25]  A. Lin,et al.  Safe use of highly steatotic livers by utilizing a donor/recipient clinical algorithm , 2013, Clinical transplantation.

[26]  Alberto Diaspro,et al.  Computer-assisted liver graft steatosis assessment via learning-based texture analysis , 2018, International Journal of Computer Assisted Radiology and Surgery.

[27]  Joseph Bockhorst,et al.  Automatic classification of white regions in liver biopsies by supervised machine learning. , 2014, Human pathology.

[28]  M. Fiorentino,et al.  Predictive value of frozen‐section analysis in the histological assessment of steatosis before liver transplantation , 2009, Liver transplantation : official publication of the American Association for the Study of Liver Diseases and the International Liver Transplantation Society.

[29]  Can Fahrettin Koyuncu,et al.  Smart Markers for Watershed-Based Cell Segmentation , 2012, PloS one.

[30]  Ali Zarrinpar,et al.  Assessment of hepatic steatosis by transplant surgeon and expert pathologist: A prospective, double‐blind evaluation of 201 donor livers , 2013, Liver transplantation : official publication of the American Association for the Study of Liver Diseases and the International Liver Transplantation Society.

[31]  Jj Allaire,et al.  Web Application Framework for R , 2016 .