Value of multimodal MRI radiomics and machine learning in predicting staging liver fibrosis and grading inflammatory activity.

Abstract

To evaluate the value of radiomics models created based on non-contrast enhanced T1 weighted (T1W) and T2W fat-saturated (T2WFS) images for staging hepatic fibrosis (HF) and grading inflammatory activity. Data of 280 patients with pathologically confirmed HF and 48 healthy volunteers were included. The participants were divided into the training set and the test set at the proportion of 4:1 by the random seed method. We used the Pyradiomics software to extract radiomics features, and then use the least absolute shrinkage and selection operator to select the optimal subset. Finally, we used the stochastic gradient descent classifier to build the prediction models. DeLong test was used to compare the diagnostic performance of the models. Receiver operating characteristics was used to evaluate the prediction ability of the models. The diagnostic efficiency of the models based on T1W & T2WFS images were the highest (all p < 0.05). When discriminating significant fibrosis (≥ F2), there were significant differences in the AUCs between the machine learning models based on T1W and T2WFS images (p < 0.05), but there were no significant differences in area under the receiver operating characteristic curves between the two models in other groups (all p > 0.05). The radiomics models built on T1W and T2WFS images are effective in assessing HF and inflammatory activity. Based on conventional MR sequences that are readily available in the clinic, namely unenhanced T1W and T2W images. Radiomics can be used for diagnosis and differential diagnosis of liver fibrosis staging and inflammatory activity grading.