Abstract
BACKGROUND: To develop a parameter-driven habitat imaging based on intravoxel incoherent motion (IVIM) MRI and to validate its effectiveness in preoperatively predicting muscle invasion in bladder cancer (BC). METHODS: This prospective study enrolled 693 pathology-confirmed BC patients who preoperatively underwent multi-b-value diffusion-weighted imaging (DWI). DWI images were acquired using a 3.0 T MRI scanner with 11 b values. Patients were randomly divided into training and testing sets (7:3). K-means clustering was applied to diffusion coefficient (D), pseudo-diffusion coefficient (D(*)), and perfusion fraction (f) maps to assign all voxels to distinct intra-tumoral habitats. The voxel proportion (p) and corresponding IVIM values were extracted for each habitat. Features were selected using intraclass correlation coefficient and Pearson correlation analysis. Three random forest models were then constructed: a habitat model, a clinical-radiologic model, and a combined model integrating both. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), and Shapley additive explanations (SHAP) was used to interpret feature contributions. RESULTS: Two habitats (K = 2) were identified, including a low perfusion and restricted diffusion (LP-RD) habitat with decreased D, D(*) and f, and a high perfusion and unrestricted diffusion (HP-UD) habitat with increased D, D(*) and f. The habitat model achieved AUCs of 0.950 and 0.814 in the training and testing sets, respectively. Incorporating clinical-radiologic factors into the combined model improved its performance, reaching AUC values of 0.987 and 0.832. SHAP analysis identified the p and D(*) values in the HP-UD habitat, and tumor location as the top contributors to the combined model’s predictions. CONCLUSIONS: The parameter-driven habitat imaging based on IVIM MRI offers a promising and noninvasive tool for preoperative assessment of muscle invasion in BC. It may help guide treatment stratification and reduce unnecessary interventions. Future studies will validate these findings in multi-center cohorts and advance integration into clinical workflows. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s40644-025-00948-z.