2020/09/22 by Ananya Jana, Hui Qu, Jana, Ananya +9
Health Professions · Medicine · #Artificial Intelligence in Healthcare #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Liver Disease Diagnosis and Treatment #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2009.10687
openalex publication_date 2020/09/22 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
Non-Alcoholic Fatty Liver Disease (NAFLD) is becoming increasingly prevalent\nin the world population. Without diagnosis at the right time, NAFLD can lead to\nnon-alcoholic steatohepatitis (NASH) and subsequent liver damage. The diagnosis\nand treatment of NAFLD depend on the NAFLD activity score (NAS) and the liver\nfibrosis stage, which are usually evaluated from liver biopsies by\npathologists. In this work, we propose a novel method to automatically predict\nNAS score and fibrosis stage from CT data that is non-invasive and inexpensive\nto obtain compared with liver biopsy. We also present a method to combine the\ninformation from CT and H &E stained pathology data to improve the performance\nof NAS score and fibrosis stage prediction, when both types of data are\navailable. This is of great value to assist the pathologists in computer-aided\ndiagnosis process. Experiments on a 30-patient dataset illustrate the\neffectiveness of our method.\n