Realistic Ultrasound Image Synthesis for Improved Classification of Liver Disease

TL;DR

This paper introduces a new GAN-based method to generate realistic liver ultrasound images, which enhances CNN performance in classifying liver diseases like NAFLD by addressing data scarcity.

Contribution

A novel stacking GAN architecture for realistic liver US image synthesis that improves disease classification accuracy.

Findings

Synthesized images are realistic and diverse.

Using generated data improves CNN classification performance.

The method effectively addresses data scarcity in medical imaging.

Abstract

With the success of deep learning-based methods applied in medical image analysis, convolutional neural networks (CNNs) have been investigated for classifying liver disease from ultrasound (US) data. However, the scarcity of available large-scale labeled US data has hindered the success of CNNs for classifying liver disease from US data. In this work, we propose a novel generative adversarial network (GAN) architecture for realistic diseased and healthy liver US image synthesis. We adopt the concept of stacking to synthesize realistic liver US data. Quantitative and qualitative evaluation is performed on 550 in-vivo B-mode liver US images collected from 55 subjects. We also show that the synthesized images, together with real in vivo data, can be used to significantly improve the performance of traditional CNN architectures for Nonalcoholic fatty liver disease (NAFLD) classification.