What question did this study set out to answer?

The study aims to develop a two-stage artificial intelligence framework for noninvasive renal fibrosis evaluation in chronic kidney disease patients.

March 6, 2026BMC Nephrology1 citationsOpen Access

Multimodal MRI-based two-stage artificial intelligence framework for renal fibrosis classification in chronic kidney disease

XLXiaojing LiSoochow University YLYirui LiSoochow University QMQing MaSoochow University

Key Points

The study aims to develop a two-stage artificial intelligence framework for noninvasive renal fibrosis evaluation in chronic kidney disease patients.
Developed a two-stage AI model combining multimodal MRI features and clinical indicators.
Included 152 patients with biopsy-proven CKD classified into three fibrosis stages.
Utilized nested cross-validation and bootstrapping for model validation and performance assessment.
Measured model performance using area under the curve (AUC) and decision curve analysis.
The multimodal deep learning model achieved a test AUC of 0.930 for renal fibrosis classification.
XGBoost model achieved a mean AUC of 0.986 for RF presence detection and 0.935 for RF severity assessment.
ExtraTree classifier demonstrated an accuracy of 0.886 for RF severity, indicating strong predictive reliability.

Abstract

Renal fibrosis (RF) is a key pathological hallmark and prognostic indicator of chronic kidney disease (CKD). Accurate evaluation of RF is critical for risk stratification and therapeutic decision-making, yet the current assessment relies mainly on renal biopsy, which has several limitations. This study aimed to develop a two-stage artificial intelligence framework that integrates multimodal MRI (native T1 mapping, ADC, and T2* mapping) and clinical indicators for the noninvasive assessment of RF in patients with CKD. This prospective study included 152 patients with biopsy-proven CKD (RF 1: no RF, 34 patients; RF 2: mild RF, 69 patients; and RF 3: moderate to severe RF, 49 patients). The dataset was randomly partitioned into training and test cohorts at a 2:1 ratio. A two-stage model combining MobileNetV2-SE-based deep learning features with clinical indicators was developed for RF classification. Two binary tasks were performed: RF presence (RF 1 vs. RF 2 and RF 3) and severity (RF 2 vs. RF 3). Nested cross-validation was applied for model development and hyperparameter tuning, and bootstrapping was used to assess performance robustness. Model performance was evaluated with the area under the curve (AUC), calibration curves, decision curve analysis (DCA), and SHapley Additive exPlanations (SHAP) visualization. Compared with single-modality models, the multimodal deep learning model (DL-combine), which is based exclusively on native T1 mapping, ADC, and T2* mapping, demonstrated favourable and stable performance (test AUC: 0.930). Among the 14 classifiers, XGBoost performed numerically better in terms of RF presence (mean AUCs: 0.986, 0.887; accuracy: 0.947, 0.829), whereas ExtraTree performed better in terms of RF severity assessment (mean AUCs: 0.935, 0.883; accuracy: 0.886, 0.848). Calibration curves and DCA confirmed robust predictive reliability and clinical utility. SHAP analysis highlighted the relative contributions of the DL-sign and eGFR. This two-stage multimodal MRI-based framework provides accurate and interpretable assessment of RF across different stages of CKD, supporting noninvasive risk stratification and complementary clinical decision-making.

AIに質問

Bookmark

View Full Paper