Artificial intelligence for liver disease detection using ultrasound images

Authors

  • Desiree Anne Villanueva ⋅ PH Institute of Mathematical Sciences and Physics, University of the Philippines Los Baños
  • Lei Rigi Baltazar ⋅ PH Institute of Mathematical Sciences and Physics, University of the Philippines Los Baños and Domingo AI Research Center
  • Ranzivelle Marianne Roxas-Villanueva ⋅ PH Institute of Mathematical Sciences and Physics, University of the Philippines Los Baños
  • Beatrice Tiangco ⋅ PH National Institutes of Health, University of the Philippines Manila and Department of Medicine, The Medical City
  • Ethel Dominique Viray ⋅ PH Department of Medicine, The Medical City
  • Jason Albia ⋅ PH Institute of Mathematical Sciences and Physics, University of the Philippines Los Baños and Domingo AI Center

Abstract

Artificial intelligence (AI) could facilitate an automated and accurate early detection of liver diseases. In this study, we optimized via transfer learning Visual Geometry Group 19 (VGG19), a convolutional neural network (CNN) architecture to classify liver ultrasound images into different disease classes. The dataset used to develop the classifier model consists of 1895 ultrasound images generated from a clinical study of Filipino cohorts. Results show that the fine-tuned classifier model achieved an overall testing accuracy of 86.7 ± 1.1% with both cirrhotic and hepatic classes achieving an AUC score of 1.00, while the fatty, normal, and parenchymal classes achieved AUC scores of 0.96, 0.95, and 0.96, respectively. To a certain extent, this study illustrates the applicability of an AI-driven model for an automated disease detection using medical images.

Downloads

Issue

Article ID

SPP-2021-2G-06

Section

Biological and Medical Physics

Published

2021-10-10

How to Cite

[1]
DA Villanueva, LR Baltazar, RM Roxas-Villanueva, B Tiangco, ED Viray, and J Albia, Artificial intelligence for liver disease detection using ultrasound images, Proceedings of the Samahang Pisika ng Pilipinas 39, SPP-2021-2G-06 (2021). URL: https://proceedings.spp-online.org/article/view/SPP-2021-2G-06.