Liver Fat Quantification Network with Body Shape

TL;DR

This paper introduces a deep neural network that estimates liver fat content from body shape data, providing a non-invasive, cost-effective alternative to traditional medical methods with high accuracy.

Contribution

It presents a novel neural network architecture combining a flexible baseline and attention module to accurately predict liver fat percentage from body shape.

Findings

Achieved RMSE of 5.26% in liver fat estimation

R-Squared value over 0.8 indicating high correlation

State-of-the-art performance on public dataset

Abstract

It is critically important to detect the content of liver fat as it is related to cardiac complications and cardiovascular disease mortality. However, existing methods are either associated with high cost and/or medical complications (e.g., liver biopsy, imaging technology) or only roughly estimate the grades of steatosis. In this paper, we propose a deep neural network to estimate the percentage of liver fat using only body shapes. The proposed is composed of a flexible baseline network and a lightweight Attention module. The attention module is trained to generate discriminative and diverse features which significant improve the performance. In order to validate the method, we perform extensive tests on the public medical dataset. The results verify that our proposed method yields state-of-the-art performance with Root mean squared error (RMSE) of 5.26% and R-Squared value over 0.8. It offers an accurate and more accessible assessment of hepatic steatosis.