Purpose: The Ki67 index and the Gleason grade group (GGG) are vital prognostic indicators of prostate cancer (PCa). This study investigated the value of biparametric magnetic resonance imaging (bpMRI) radiomics feature-based machine learning (ML) models in predicting the Ki67 index and GGG of PCa. Methods: A total of 122 patients with pathologically proven PCa who had undergone preoperative MRI were retrospectively included. Radiomics features were extracted from T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) maps. Then, recursive feature elimination (RFE) was applied to remove redundant features. ML models for predicting Ki67 expression and GGG were constructed based on bpMRI and different algorithms, including logistic regression (LR), support vector machine (SVM), random forest (RF), and K-nearest neighbor (KNN). The performances of different models were evaluated with receiver operating characteristic (ROC) analysis. In addition, a joint analysis of Ki67 expression and GGG was performed by assessing their Spearman correlation and calculating the diagnostic accuracy for both indices. Results: The ML model based on LR and ADC + T2 (LR_ADC + T2, AUC = 0.8882) performed best in predicting Ki67 expression, and ADC_wavelet-LHH_firstorder_Maximum had the highest feature weighting. The SVM_DWI + T2 (AUC = 0.9248) performed best in predicting GGG, and DWI_wavelet HLL_glcm_SumAverage had the highest feature weighting. The Ki67 and GGG exhibited a weak positive correlation (r = 0.382, p < 0.001), and LR_ADC + DWI had the highest diagnostic accuracy in predicting both (0.6230). Conclusion: The proposed ML models are suitable for predicting both Ki67 expression and GGG in PCa. This algorithm could be used to identify indolent or invasive PCa with a noninvasive, repeatable, and accurate diagnostic method.

Background: Assessing liver function is crucial for managing chronic liver diseases. This study aimed to evaluate the efficacy of hepatocyte uptake and the longitudinal relaxation time (T1) mapping indices from gadoxetic acid-enhanced magnetic resonance imaging (MRI) for evaluating liver function and its correlation with the albumin-bilirubin (ALBI) grading system. Methods: We retrospectively studied 183 patients who were grouped based on ALBI score: normal liver function (NLF), ALBI 1, ALBI 2, and ALBI 3. We calculated T1 indices and analyzed their correlation with ALBI grade, and differences among ALBI groups were evaluated. Receiver operating characteristic curves were used to assess the discriminative power of hepatocyte uptake and T1 indices for liver function groups, with significance set at P<0.05. Results: Significant differences were observed in hepatocyte uptake and T1 indices across the NLF and ALBI groups (P<0.001). T1 value before enhancement (T1pre), T1 value after enhancement (T1post) prolonged, and rate of decrease in the T1 relaxation time (ΔT1), hepatocyte uptake rate (K_hep) decreased with the advancement of liver function impairment, except for T1pre shortened in ALBI 3 grade. T1post (rho =0.762, P<0.001), K_hep (rho =−0.759, P<0.001) and ΔT1 (rho =−0.673, P<0.01) showed strong correlations with ALBI grades. T1post and K_hep were superior to T1pre and ΔT1 across all liver function groups not only in pairwise comparison but also in stratified analysis. Conclusions: K_hep and T1post provide good diagnostic performance in distinguishing ALBI groups. T1post exhibits the highest area under the curve (AUC) when predicting lower liver function groups, whereas K_hep excels in predicting high-grade liver function. Gadoxetic acid-enhanced MRI with T1 mapping shows potential as a tool for assessing liver function.

Objectives: This study aimed to develop and validate a biparametric MRI (bpMRI)-based radiomics model for the noninvasive prediction of tumor–stroma ratio (TSR) in prostate cancer (PCa). Additionally, we sought to explore lesion distribution patterns in the peripheral zone (PZ) and transition zone (TZ) to provide deeper insights into the biological behavior of PCa. Methods: This multicenter retrospective study included 223 pathologically confirmed PCa patients, with 146 for training and 39 for internal validation at Center 1, and 38 for external testing at Center 2. All patients underwent preoperative bpMRI (T2WI, DWI acquired with a b-value of 1400 s/mm², and ADC maps), with TSR histopathologically quantified. Regions of interest (ROIs) were manually segmented on bpMRI images using ITK-SNAP software (version 4.0.1), followed by high-throughput radiomic feature extraction. Redundant features were eliminated via Spearman correlation analysis and least absolute shrinkage and selection operator (LASSO) regression. Five machine learning (ML) classifiers—Logistic Regression (LR), Support Vector Machine (SVM), BernoulliNBBayes, Ridge, and Stochastic Gradient Descent (SGD)—were trained and optimized. Model performance was rigorously evaluated using receiver operating characteristic (ROC) curves and decision curve analysis (DCA). Results: The Ridge demonstrated superior diagnostic performance, achieving AUCs of 0.846, 0.789, and 0.745 in the training, validation, and test cohorts, respectively. Lesion distribution analysis revealed no significant differences between High-TSR and Low-TSR groups (p = 0.867), suggesting that TSR may not be strongly associated with zonal localization. Conclusions: This exploratory study suggests that a bpMRI-based radiomic model holds promise for noninvasive TSR estimation in prostate cancer and may provide complementary insights into tumor aggressiveness beyond conventional pathology.

Background: Limited evidence exists on the diagnostic performance of Artificial Intelligence (AI)‐assisted Simplified Prostate Imaging Reporting and Data System version 2.1 (S‐PI‐RADS v2.1) combined with quantitative MRI parameters for detecting clinically significant prostate cancer (csPCa). Purpose: To develop and validate a nomogram incorporating AI‐assisted S‐PI‐RADS v2.1 (based on biparametric MRI [bpMRI]) and R2* mapping for csPCa prediction. Methods: This prospective study enrolled 345 patients grouped by pathology: non‐csPCa with benign prostatic hyperplasia ( n = 230) and csPCa ( n = 115). Clinical (age, body mass index [BMI], prostate‐specific antigen [PSA], free PSA) and imaging parameters (prostate volume [PV], S‐PI‐RADS score, R2*) were analyzed. Independent predictors were identified via logistic regression. A nomogram was developed using R software with the DynNom package (Version 2.0) and validated (1000 bootstrap iterations), with performance assessed by area under the curve (AUC), calibration, decision curve analysis (DCA), and DeLong test ( p < 0.05 significant). Results: Independent csPCa predictors included BMI, PSA ≥ 10 ng/mL, PV, S‐PI‐RADS scores 4–5, and R2* (all p < 0.05). The full model (BMI + PSA + PV + S‐PI‐RADS + R2*) showed superior discrimination (AUC = 0.915) versus the baseline model (AUC = 0.891, p = 0.008), with 85.2% sensitivity and 80.9% specificity. Internal validation was robust (C‐index = 0.884). DCA confirmed clinical utility. An interactive nomogram was deployed ( https://aiguangyong2025.shinyapps.io/dynnomapp/ ). Conclusion: The AI‐enhanced nomogram integrating clinical and multiparametric MRI data accurately predicts csPCa noninvasively, with R2* significantly improving performance. This tool facilitates personalized clinical decision‐making.