Large-scale inference of liver fat with neural networks on UK Biobank body MRI

TL;DR

This study introduces a neural network-based method to automatically estimate liver fat from UK Biobank neck-to-knee MRI scans, enabling large-scale, fast, and accurate liver fat quantification without manual segmentation.

Contribution

A novel deep learning framework that infers liver fat from body MRI scans without requiring ground truth segmentations, significantly expanding available measurements.

Findings

Achieved high agreement with reference liver fat measurements.

Outperformed traditional segmentation baseline methods.

Inferred liver fat for six times more subjects than with existing data.

Abstract

The UK Biobank Imaging Study has acquired medical scans of more than 40,000 volunteer participants. The resulting wealth of anatomical information has been made available for research, together with extensive metadata including measurements of liver fat. These values play an important role in metabolic disease, but are only available for a minority of imaged subjects as their collection requires the careful work of image analysts on dedicated liver MRI. Another UK Biobank protocol is neck-to-knee body MRI for analysis of body composition. The resulting volumes can also quantify fat fractions, even though they were reconstructed with a two- instead of a three-point Dixon technique. In this work, a novel framework for automated inference of liver fat from UK Biobank neck-to-knee body MRI is proposed. A ResNet50 was trained for regression on two-dimensional slices from these scans and the reference values as target, without any need for ground truth segmentations. Once trained, it performs fast, objective, and fully automated predictions that require no manual intervention. On the given data, it closely emulates the reference method, reaching a level of agreement comparable to different gold standard techniques. The network learned to rectify non-linearities in the fat fraction values and identified several outliers in the reference. It outperformed a multi-atlas segmentation baseline and inferred new estimates for all imaged subjects lacking reference values, expanding the total number of liver fat measurements by factor six.