Computer-aided classification of hepatocellular ballooning in liver biopsies from patients with NASH using persistent homology

• Published in: Computer methods and programs in biomedicine 2020-10, Vol.195, p.105614-105614, Article 105614
• Main Authors: Teramoto, Takashi, Shinohara, Toshiya, Takiyama, Akihiro
• Format: Article
• Language: English
• Subjects: Biopsy; Carcinoma, Hepatocellular; Computational homology; Computers; Humans; Image processing; Linear machine learning; Liver - diagnostic imaging; Liver biopsy; Liver Neoplasms; NAFLD; Non-alcoholic Fatty Liver Disease - diagnostic imaging
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2020.105614

•We introduce persistence images as novel mathematical descriptors for the classification of ballooning degeneration in the pathological diagnosis.•We implemented and tested a topological data analysis methodology combined with linear machine learning techniques and applied this to the classification of tissue images into NAFLD subtypes using Matteoni classification in liver biopsies.•We obtained accuracy rates of more than 90% for the classification between NASH and non-NASH NAFLD groups. The highest area under the curve from the receiver operating characteristic analysis was 0.946 for the classification of NASH and NAFL2 (type 2 of Matteoni classification), when both 0- and 1-dimensional persistence images were used.•Our methodology using persistent homology provides quantitative measurements of the topological features in liver biopsies of NAFLD groups with considerable accuracy. Background and Objective:Hepatocellular ballooning is an important histological parameter in the diagnosis of nonalcoholic steatohepatitis (NASH), and it is considered to be a morphological pattern that indicates the severity and the progression to cirrhosis and liver-related deaths. There remains uncertainty about the pathological criteria for evaluating the spectrum of non-alcoholic fatty liver disease (NAFLD) in liver biopsies. We introduce persistence images as novel mathematical descriptors for the classification of ballooning degeneration in the pathological diagnosis. Methods:We implemented and tested a topological data analysis methodology combined with linear machine learning techniques and applied this to the classification of tissue images into NAFLD subtypes using Matteoni classification in liver biopsies. Results:Digital images of hematoxylin- and eosin-stained specimens with a pathologist’s visual assessment were obtained from 79 patients who were clinically diagnosed with NAFLD. We obtained accuracy rates of more than 90% for the classification between NASH and non-NASH NAFLD groups. The highest area under the curve from the receiver operating characteristic analysis was 0.946 for the classification of NASH and NAFL2 (type 2 of Matteoni classification), when both 0- and 1-dimensional persistence images were used. Conclusions:Our methodology using persistent homology provides quantitative measurements of the topological features in liver biopsies of NAFLD groups with considerable accuracy.