Machine learning-based multimodal MRI texture analysis for assessing renal function and fibrosis in diabetic nephropathy: a retrospective study

Abstract

IntroductionDiabetic nephropathy (DN) has become a major public health burden in China. A more stable method is needed to reflect the different stages of renal function impairment. We aimed to determine the possible practicability of machine learning (ML)-based multimodal MRI texture analysis (mMRI-TA) for assessing renal function in DN.MethodsFor this retrospective study, 70 patients (between 1 January 2013 and 1 January 2020) were included and randomly assigned to the training cohort (n1 = 49) and the testing cohort (n2 = 21). According to the estimated glomerular filtration rate (eGFR), patients were assigned into the normal renal function (normal-RF) group, the non-severe renal function impairment (non-sRI) group, and the severe renal function impairment (sRI) group. Based on the largest coronal image of T2WI, the speeded up robust features (SURF) algorithm was used for texture feature extraction. Analysis of variance (ANOVA) and relief and recursive feature elimination (RFE) were applied to select the important features and then support vector machine (SVM), logistic regression (LR), and random forest (RF) algorithms were used for the model construction. The values of area under the curve (AUC) on receiver operating characteristic (ROC) curve analysis were used to assess their performance. The robust T2WI model was selected to construct a multimodal MRI model by combining the measured BOLD (blood oxygenation level-dependent) and diffusion-weighted imaging (DWI) values.ResultsThe mMRI-TA model achieved robust and excellent performance in classifying the sRI group, non-sRI group, and normal-RF group, with an AUC of 0.978 (95% confidence interval [CI]: 0.963, 0.993), 0.852 (95% CI: 0.798, 0.902), and 0.972 (95% CI: 0.995, 1.000), respectively, in the training cohort and 0.961 (95% CI: 0.853, 1.000), 0.809 (95% CI: 0.600, 0.980), and 0.850 (95% CI: 0.638, 0.988), respectively, in the testing cohort.DiscussionThe model built from multimodal MRI on DN outperformed other models in assessing renal function and fibrosis. Compared to the single T2WI sequence, mMRI-TA can improve the performance in assessing renal function.

Utility of a Three-dimensional Convolutional Neural Network-based Renal Function Prediction Using Kidney MRI in Chronic Kidney Disease

“…In the present study, the classi cation performance seemed to be improved compared to the previous report [13], probably owing to the convolutional network we used this time, although statistical evaluation was somewhat different between the two, making precise comparison di cult. Chen et al reported excellent models classifying the renal function status in diabetic nephropathy, with coronal T2WI-based radiomics analysis and machine-learning model combined with the measured BOLD and DWI values [24]. They suggested that renal brosis causes decreased signal intensity on T2WI, thus these changes can be evaluated quantitatively [24].…”

“…Chen et al reported excellent models classifying the renal function status in diabetic nephropathy, with coronal T2WI-based radiomics analysis and machine-learning model combined with the measured BOLD and DWI values [24]. They suggested that renal brosis causes decreased signal intensity on T2WI, thus these changes can be evaluated quantitatively [24]. Their models were superior to our results, though the accurate comparison was di cult due to several reasons: they focused only on diabetic nephropathy and the CKD groups they classi ed were slightly different from ours.…”

Serological Biomarker-Based Machine Learning Models for Predicting the Relapse of Ulcerative Colitis

“…RF is an idea of ensemble learning, which inputs many weak learners through random sampling of data, and it could measure the relative importance of each feature for the prediction. 14 The DT is a classification and regression model based on a tree structure, which classifies or predicts data through a series of decisions. 18 The NN is an updated technology based on models with fewer assumptions, which relies on multi-layers of representation of data with continuous transformations, and it is capable of handling more complex data.…”

“… 13 For example, the random forest (RF) model has proven useful in Alzheimer’s disease and diabetic nephropathy. 14 In addition, the logistic regression model (LR), the decision tree (DT), and the neural network (NN) have shown strong capabilities in medical data processing. 15 , 16 Previous studies have demonstrated that machine learning algorithms improve the accuracy of identifying and distinguishing UC compared to using serological markers alone.…”