Yan Guo

Background: Intraductal carcinoma (IDC) and invasive cribriform (Cr) histologic patterns are important adverse morphologies in prostate cancer (PCa) and may influence pretreatment risk stratification. This study evaluated the feasibility of time-dependent diffusion magnetic resonance imaging (t_d-dMRI)-based microstructural mapping for preoperative characterization of these aggressive morphologies. Methods: This retrospective study included 95 men with pathologically confirmed PCa on radical prostatectomy specimens from March 2023 to March 2025. T_d-dMRI was performed using pulsed and oscillating gradient diffusion sequences. Microstructural parameters, including extracellular diffusivity (D_ex), cell diameter (d), intracellular volume fraction (f_in), cellularity, and diffusivities at 0, 17, and 33 Hz (ADC_0Hz, ADC_17Hz, and ADC_33Hz), were estimated using a two-compartment model. Conventional apparent diffusion coefficient (ADC_DWI) values were obtained from standard diffusion-weighted imaging. Parameters were compared between tumors with and without Cr/IDC patterns, and diagnostic performance was assessed using receiver operating characteristic analysis. Pairwise comparisons of AUCs were performed using the DeLong test. Results: Among 95 participants, 62 (65.3%) had Cr/IDC patterns. Compared with Cr/IDC-negative tumors, Cr/IDC-positive tumors showed higher f_in and cellularity (both p < 0.001) and lower ADC_DWI, ADC_0Hz, ADC_17Hz, and ADC_33Hz values (all p < 0.05). D_ex and d did not differ significantly between groups. Among t_d-dMRI-derived parameters, f_in showed the highest diagnostic performance (AUC = 0.757; 95% CI, 0.654–0.860). Conclusions: T_d-dMRI-based microstructural mapping demonstrates promise for characterizing the Cr/IDC morphologies in PCa.

Background: The Vesical Imaging-Reporting and Data System (VI-RADS) has limited diagnostic accuracy in distinguishing non-muscle-invasive bladder cancer (NMIBC) within VI-RADS categories 2 and 3, despite its value for overall NMIBC assessment. Dynamic contrast-enhanced MRI (DCE-MRI), which reflects tumor vascularity, holds promise for improving these challenging cases but remains underutilized due to unexploited spatiotemporal information. Methods: We developed a deep learning model to comprehensively quantify spatiotemporal features from multiphase DCE-MRI in 184 patients with VI-RADS 2 or 3 (training: n = 115, validation: n = 20, testing: n = 49). The model integrated multiscale feature extraction and contextual attention mechanisms to enhance diagnostic performance. Results: The model outperformed established benchmarks (e.g., VGG, ResNet) and the conventional VI-RADS ≤ 2 threshold (sensitivity: 0.67 for NMIBC), achieving a sensitivity of 0.90 (95% CI: 0.81–0.96) for NMIBC and an area under the curve (AUC) of 0.82 (95% CI: 0.75–0.89) for overall classification. Visualizations confirmed its ability to identify key spatiotemporal patterns linked to muscle invasion. Conclusions: By leveraging comprehensive spatiotemporal information from DCE-MRI, our deep learning model significantly improves NMIBC diagnosis in VI-RADS 2/3 cases, offering a clinically valuable tool to address the limitations of current VI-RADS assessment.

Deuterium metabolic imaging (DMI) is a promising noninvasive technique for assessing tumor metabolism, yet its application in bladder cancer (BCa) remains unexplored. This study presents the first demonstration of DMI for evaluating therapeutic response in BCa through in vitro and in vivo experiments. Two types of deuterium‐labeled glucose tracers, [6,6′‐ ² H ₂ ]‐D‐glucose and [2,3,4,6,6′‐ ² H ₅ ]‐D‐glucose, are systematically compared for their efficacy in capturing glycolytic activity and treatment‐induced metabolic changes in BCa models. In subcutaneous tumors, deuterium magnetic resonance spectroscopy and spectroscopic imaging reveal pronounced suppression of glycolytic flux following chemotherapy, underscoring the potential of DMI for early therapeutic response assessment in BCa treatment. Both tracers consistently detect these chemotherapy‐related metabolism shifts in both vitro and in vivo experiments, indicating the translational advantage of [2,3,4,6,6′‐ ² H ₅ ]‐D‐glucose as a cost‐effective alternative to [6,6′‐ ² H ₂ ]‐D‐glucose. Notably, subcutaneous administration yields metabolic profiles comparable to intravenous delivery. Finally, the optimized lower‐dose, subcutaneous [2,3,4,6,6′‐ ² H ₅ ]‐D‐glucose protocol is successfully validated in orthotopic BCa models. These results demonstrate DMI as a reliable tool for non‐invasive monitoring of therapeutic response in BCa, with practical potential for future clinical translation.

Objective To evaluate the clinical utility of multiparametric MRI in differentiating pathological stages (ypT0 vs ypT1–4) in patients with muscle-invasive bladder cancer (MIBCa) following neoadjuvant therapy (NAT). Materials and methods In this double-center cohort study, post-NAT multiparametric MRI in all consecutive patients who underwent surgery after NAT was analyzed. Two experienced radiologists independently evaluated the MRI features obtained after NAT. The post-NAT yT stage was assigned based on T2-weighted diffusion-weighted imaging (T2DWI) and on contrast-enhanced MRI scans. The diagnostic accuracies for distinguishing post-NAT ypT0 from ypT1–4 tumors with the two protocols were evaluated. Cohen’s kappa (κ) statistics were used to evaluate the consistency between readers for the post-NAT yT stage. Results A total of 149 patients (mean age, 62 years ± 10 [SD]; 131 men) from two institutions were enrolled. The area under the receiver operating characteristic curve of the contrast-enhanced MRI protocol in predicting post-NAT ypT0 stage was 0.84 (95% CI: 0.77, 0.91), which was better than that of the T2DWI protocol (0.75; 95% CI: 0.67, 0.81; p = 0.002). The interobserver agreement was excellent for both the T2DWI protocol (κ = 0.89) and the contrast-enhanced MRI protocol (κ = 0.85). Conclusions Multiparametric MRI, particularly contrast-enhanced MRI, demonstrated superior accuracy in identifying ypT0 status following NAT in MIBCa, establishing it as an essential diagnostic tool for guiding bladder preservation in clinical decision-making. Key Points Question Accurately identifying pathological complete response (ypT0) after NAT is essential for selecting bladder-preservation strategies, yet remains clinically challenging. Findings Post-treatment contrast-enhanced MRI accurately identified ypT0 status with an AUC of 0.84 and excellent inter-reader agreement, outperforming T2DWI. Clinical relevance Contrast-enhanced MRI is a reliable, non-invasive method for detecting complete tumor response after NAT, enabling better patient selection for bladder-sparing approaches and potentially improving quality of life. Graphical Abstract

Background: The detection of prostate cancer (PCa) via conventional magnetic resonance imaging (MRI) in patients with prostate-specific antigen (PSA) levels within the grey zone remains challenging. Whether synthetic MRI can provide supplementary benefits for the accurate diagnosis of PCa in this specific population is still unknown. This study aims to investigate the diagnostic performance of synthetic MRI for differentiating PCa lesions from noncancerous lesions in patients with PSA levels within the grey zone (4–10 ng/mL). Methods: Clinical and MRI data, including synthetic MRI data of patients suspected of having PCa between August 2020 and August 2022, were retrospectively collected from The First Affiliated Hospital of Sun Yat-sen University and Sun Yat-sen University Cancer Center. Patients with PSA levels ranging from 4–10 ng/mL were enrolled. Pathology was obtained either from transrectal ultrasound-guided biopsy or radical prostatectomy. Regions of interest were manually drawn by two independent radiologists, and the values of quantitative parameters, including longitudinal relaxation time (T1), transverse relaxation time (T2), proton density (PD), and apparent diffusion coefficient (ADC), were separately measured. Interobserver agreement was evaluated using the interclass correlation coefficient (ICC). The differences in quantitative parameter values between PCa and noncancerous lesions were assessed using an independent sample t-test or the Mann-Whitney U test. Receiver operating characteristic curve analysis was performed to evaluate the diagnostic performance of each parameter (T1, T2, PD, and ADC values), as well as their combination. PResults: A total of 130 patients were enrolled in this study, with a mean age of 67.32±8.87 years. The interobserver agreement of all the T1, T2, PD, and ADC values was classified as good or above (ICC =0.60–1.00). The means of the T1, T2, PD, and ADC values were significantly different between PCa and noncancerous lesions (P=0.022, PConclusions: Quantitative parameters, including T1, T2, and PD, derived from synthetic MRI can be applied to differentiate PCa lesions from noncancerous lesions in patients with PSA levels within the grey zone. However, when these parameters were combined with the ADC, the diagnostic performance did not improve compared to that with the ADC value alone.

Original Article Hierarchical K-means clustering method for accelerated Lorentzian estimation (KALE) in chemical exchange saturation transfer-magnetic resonance imaging quantification Yanrong Chen, Yaozong Sun, Chongxue Bie, Xiaoli Wang, Xiaowei He, Xiaolei Song

Purpose To investigate the correlation between quantitative MR parameters and prognostic factors in prostate cancer (PCa). Method A total of 186 patients with pathologically confirmed PCa who underwent preoperative multiparametric MRI (mpMRI), including synthetic MRI (SyMRI), were enrolled from two medical centers. The histogram metrics of SyMRI [T1, T2, proton density (PD)] and apparent diffusion coefficient (ADC) values were extracted. The Mann‒Whitney U test or Student’s t test was employed to determine the association between these histogram features and the prognostically relevant factors. Receiver operating characteristic (ROC) curve analysis was conducted to evaluate the differentiation performance. Spearman’s rank correlation coefficients were calculated to determine the correlations between histogram parameters and the International Society of Urological Pathology (ISUP) grade group as well as pathological T stage. Results Significant correlations were found between the histogram parameters and the ISUP grade as well as pathological T stage of PCa. Among these histogram parameters, ADC_minimum had the strongest correlation with the ISUP grade (r = − 0.481, p < 0.001), and ADC_Median showed the strongest association with pathological T stage (r = − 0.285, p = 0.008). The ADC_10th percentile exhibited the highest performance in identifying clinically significant prostate cancer (csPCa) (AUC 0.833; 95% CI 0.771–0.883). When discriminating between the status of different prognostically relevant factors, a significant difference was observed between extraprostatic extension-positive and -negative cancers with regard to histogram parameters of the ADC map (10th percentile, 90th percentile, mean, median, minimum) and T1 map (minimum) (p = 0.002–0.032). Moreover, histogram parameters of the ADC map (90th percentile, maximum, mean, median), T2 map (10th percentile, median), and PD map (10th percentile, median) were significantly lower in PCa with perineural invasion (p = 0.009–0.049). The T2 values were significantly lower in patients with seminal vesicle invasion (minimum, p = 0.036) and positive surgical margin (10th percentile, 90th percentile, mean, median, and minimum, p = 0.015–0.025). Conclusion Quantitative histogram parameters derived from synthetic MRI and ADC maps may have great potential for predicting the prognostic features of PCa. Graphical abstract

Background: Synthetic magnetic resonance imaging (MRI) can provide quantitative information about inherent tissue properties and synthesize tailored contrast-weighted images simultaneously in a single scan. This study aimed to investigate the clinical feasibility of synthetic MRI in bladder tumors. Methods: A total of 47 patients (37 males; mean age: 66±10 years old) with postoperative pathology-confirmed papillary urothelial neoplasms of the bladder were enrolled in this retrospective study. A 2-dimensional (2D) multi-dynamic multi-echo pulse sequence was performed for synthetic MRI at 3T. The overall image quality, lesion conspicuity, contrast resolution, resolution of subtle anatomic structures, motion artifact, blurring, and graininess of images were subjectively evaluated by 2 radiologists independently using a 5-point Likert scale for qualitative analysis. The signal intensity ratio (SIR), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were measured for quantitative analysis. Linear weighted Kappa, Wilcoxon’s signed-rank test, and the Mann–Whitney U-test were used for statistical analysis. Results: The interobserver consistency was excellent (κ values: 0.607–1). Synthetic T1-weighted (syn-T1w) and synthetic T2-weighted (syn-T2w) images obtained scores of 4 in most subjective terms, which were relatively smaller than those of conventional images. The SIR and SNR of syn-T1w were significantly higher than those of con-T1w images (SIR 2.37±0.86 vs. 1.47±0.20, Pvs. 14.81±3.30, Pvs. 26.49±6.80, Pvs. 2.68±1.04; T2w 1.40±0.87 vs. 4.03±1.55, all PConclusions: Synthetic MRI generates morphologic magnetic resonance (MR) images with diagnostically acceptable image quality in bladder tumors, especially T1-weighted images with high image contrast of tumors relative to urine. Further technological improvements are needed for synthetic MRI to reduce noise. Combined with T1, T2, and proton density (PD) quantitative data, synthetic MRI has potential for clinical application in bladder tumors.

Amide proton transfer-weighted MRI has potential in improving the diagnostic performance of diffusion-weighted MRI for high-grade bladder cancer. Background Bladder cancer is classified into high and low grades with different clinical treatments and prognoses. Thus, accurate preoperative evaluation of the histologic grade through imaging tec...