Development and validation of an artificial intelligence model based on liver CSE-MRI fat maps for predicting dyslipidemia

TL;DR

This paper introduces an AI model that uses liver MRI scans to predict dyslipidemia without blood tests, offering a non-invasive early warning tool.

Contribution

The novel contribution is an AI model using liver CSE-MRI fat maps to predict lipid abnormalities with high accuracy, enabling non-invasive dyslipidemia screening.

Findings

A ResNet18-based AI model achieved high accuracy in predicting lipid abnormalities from liver CSE-MRI fat maps.

The model showed strong performance for low-density and high-density lipoprotein cholesterol prediction.

The approach enables opportunistic screening for dyslipidemia using existing MRI scans without additional cost or time.

Abstract

This study aimed to develop and validate an artificial intelligence (AI) model for the non-invasive early detection of dyslipidemia using liver chemical shift-encoded MRI (CSE-MRI) fat maps. An automated AI pipeline was developed to predict abnormalities in four lipid indicators: triglyceride, total cholesterol, low-density lipoprotein cholesterol, and high-density lipoprotein cholesterol. The study utilized 1,757 liver CSE-MRI fat images from 89 patients who underwent MRI scans and contemporaneous blood lipid testing. Transfer learning was applied using several pre-trained networks, including ResNet18, MobileNet, DenseNet, AlexNet, and SqueezeNet. Model performance was evaluated via 8-fold cross-validation, with the optimal model further assessed on a held-out test set using confusion matrices and derived metrics. Significant performance differences were observed among models. The optimal model, based on ResNet18, demonstrated high accuracy in the internal validation set. On the independent test set, this model achieved accuracies of 0.853 for triglyceride, 0.833 for total cholesterol, 0.937 for low-density lipoprotein cholesterol, and 0.936 for high-density lipoprotein cholesterol, with corresponding F1-Scores of 0.885, 0.571, 0.886, and 0.897. The AI model based on liver CSE-MRI fat maps shows high accuracy and generalization in predicting abnormalities for three key lipid indices, validating its potential as an early warning tool for dyslipidemia. Expanding the training dataset could further enhance performance for all lipid indices.

Dyslipidemia, a major risk factor for chronic diseases, is traditionally diagnosed via invasive blood tests. We explored a non-invasive alternative by developing an artificial intelligence (AI) model that predicts blood lipid abnormalities using routine liver MRI scans. Our model analyzes chemical shift-encoded MRI (CSE-MRI) fat maps—images that quantify liver fat content—to forecast levels of triglycerides, cholesterol, and other key lipids. We trained and compared multiple deep learning models, finding that a model based on ResNet18 performed best. It demonstrated high accuracy, particularly in predicting abnormal levels of triglycerides and certain cholesterol types. This approach can provide an “opportunistic screening” tool; when patients undergo abdominal MRI for other reasons, their existing scan data could be simultaneously analyzed to assess dyslipidemia risk, adding value without extra cost or scan time. This work pioneers a new, non-invasive method for early dyslipidemia warning using clinical imaging data.

Figures