Prostate cancer risk assessment and avoidance of prostate biopsies using fully automatic deep learning in prostate MRI: comparison to PI-RADS and integration with clinical data in nomograms.

OBJECTIVES: Risk calculators (RCs) improve patient selection for prostate biopsy with clinical/demographic information, recently with prostate MRI using the prostate imaging reporting and data system (PI-RADS). Fully-automated deep learning (DL) analyzes MRI data independently, and has been shown to be on par with clinical radiologists, but has yet to be incorporated into RCs. The goal of this study is to re-assess the diagnostic quality of RCs, the impact of replacing PI-RADS with DL predictions, and potential performance gains by adding DL besides PI-RADS. MATERIAL AND METHODS: One thousand six hundred twenty-seven consecutive examinations from 2014 to 2021 were included in this retrospective single-center study, including 517 exams withheld for RC testing. Board-certified radiologists assessed PI-RADS during clinical routine, then systematic and MRI/Ultrasound-fusion biopsies provided histopathological ground truth for significant prostate cancer (sPC). nnUNet-based DL ensembles were trained on biparametric MRI predicting the presence of sPC lesions (UNet-probability) and a PI-RADS-analogous five-point scale (UNet-Likert). Previously published RCs were validated as is; with PI-RADS substituted by UNet-Likert (UNet-Likert-substituted RC); and with both UNet-probability and PI-RADS (UNet-probability-extended RC). Together with a newly fitted RC using clinical data, PI-RADS and UNet-probability, existing RCs were compared by receiver-operating characteristics, calibration, and decision-curve analysis. RESULTS: Diagnostic performance remained stable for UNet-Likert-substituted RCs. DL contained complementary diagnostic information to PI-RADS. The newly-fitted RC spared 49% [252/517] of biopsies while maintaining the negative predictive value (94%), compared to PI-RADS ≥ 4 cut-off which spared 37% [190/517] (p < 0.001). CONCLUSIONS: Incorporating DL as an independent diagnostic marker for RCs can improve patient stratification before biopsy, as there is complementary information in DL features and clinical PI-RADS assessment. CLINICAL RELEVANCE STATEMENT: For patients with positive prostate screening results, a comprehensive diagnostic workup, including prostate MRI, DL analysis, and individual classification using nomograms can identify patients with minimal prostate cancer risk, as they benefit less from the more invasive biopsy procedure. KEY POINTS: The current MRI-based nomograms result in many negative prostate biopsies. The addition of DL to nomograms with clinical data and PI-RADS improves patient stratification before biopsy. Fully automatic DL can be substituted for PI-RADS without sacrificing the quality of nomogram predictions. Prostate nomograms show cancer detection ability comparable to previous validation studies while being suitable for the addition of DL analysis.

Multiparameter MRI-based radiomics analysis for preoperative prediction of type II endometrial cancer.

Objectives: This study aimed to develop and validate a radiomics nomogram based on multiparameter MRI for preoperative differentiation of type II and type I endometrial carcinoma (EC). Methods: A total of 403 EC patients from two centers were retrospectively recruited (training cohort, 70 %; validation cohort, 30 %). Radiomics features were extracted from T2-weighted imaging, dynamic contrast-enhanced T1-weighted imaging at delayed phase(DCE4), and apparent diffusion coefficient (ADC) maps. Following dimensionality reduction, radiomics models were developed by logistic regression (LR), random forest (RF), bootstrap aggregating (Bagging), support vector machine (SVM), artificial neural network (ANN), and naive bayes (NB) algorithms. The diagnostic performance of each radiomics model was evaluated using the ROC curve. A nomogram was constructed by incorporating the optimal radiomics signatures with significant clinical-radiological features and immunohistochemistry (IHC) markers obtained from preoperative curettage specimens. The diagnostic performance and clinical value of the nomogram were evaluated using ROC curves, calibration curves, and decision curve analysis (DCA). Results: Among the radiomics models, the NB model, developed from 12 radiomics features derived from ADC and DCE4 sequences, exhibited strong performance in both training and validation sets, with the AUC values of 0.927 and 0.869, respectively. The nomogram, incorporating the radiomics model with significant clinical-radiological features and IHC markers, demonstrated superior performance in both the training (AUC = 0.951) and the validation sets (AUC = 0.915). Additionally, it exhibited excellent calibration and clinical utility. Conclusions: The radiomics nomogram has great potential to differentiate type II from type I EC, which may be an effective tool to guide clinical decision-making for EC patients.

A nomogram to predict the absence of clinically significant prostate cancer in males with negative MRI

ABSTRACT Purpose: To create a nomogram to predict the absence of clinically significant prostate cancer (CSPCa) in males with non-suspicion multiparametric magnetic resonance imaging (mpMRI) undergoing prostate biopsy (PBx). Materials and Methods: We identified consecutive patients who underwent 3T mpMRI followed by PBx for suspicion of PCa or surveillance follow-up. All patients had Prostate Imaging Reporting and Data System score 1-2 (negative mpMRI). CSPCa was defined as Grade Group ≥2. Multivariate logistic regression analysis was performed via backward elimination. Discrimination was evaluated with area under the receiver operating characteristic (AUROC). Internal validation with 1,000x bootstrapping for estimating the optimism corrected AUROC. Results: Total 327 patients met inclusion criteria. The median (IQR) age and PSA density (PSAD) were 64 years (58-70) and 0.10 ng/mL2 (0.07-0.15), respectively. Biopsy history was as follows: 117 (36%) males were PBx-naive, 130 (40%) had previous negative PBx and 80 (24%) had previous positive PBx. The majority were White (65%); 6% of males self-reported Black. Overall, 44 (13%) patients were diagnosed with CSPCa on PBx. Black race, history of previous negative PBx and PSAD ≥0.15ng/mL2 were independent predictors for CSPCa on PBx and were included in the nomogram. The AUROC of the nomogram was 0.78 and the optimism corrected AUROC was 0.75. Conclusions: Our nomogram facilitates evaluating individual probability of CSPCa on PBx in males with PIRADS 1-2 mpMRI and may be used to identify those in whom PBx may be safely avoided. Black males have increased risk of CSPCa on PBx, even in the setting of PIRADS 1-2 mpMRI

Radical Prostatectomy Without Prior Biopsy in Selected Patients Evaluated by 18F-Labeled Prostate-Specific Membrane Antigen-Ligand Positron Emission Tomography/Computed Tomography and Multiparameter Magnetic Resonance Imaging: A Single-Center, Prospective, Single-Arm Trial.

PURPOSE: This study aimed to verify the feasibility and short-term prognosis of prostatectomy without biopsy. MATERIALS AND METHODS: Patients with a rising PSA level ranging from 4 to 30 ng/mL were scheduled for multiparametric (mp) MRI and 18F-labeled prostate-specific membrane antigen (PSMA) positron emission tomography (PET). Forty-seven patients (cT2N0M0) with Prostate Imaging Reporting and Data System ≥ 4 and molecular imaging PSMA score ≥ 2 were enrolled. All candidates underwent robot-assisted laparoscopic radical prostatectomy without biopsy. Prostate cancer detection rate, index tumors localization correspondence rate, positive surgical margin, complications, postoperative hospital stay, and PSA level in a 6-week postoperative follow-up visit were collected. RESULTS: All the patients with positive mpMRI and PSMA PET were diagnosed with clinically significant prostate cancer. A total of 80 lesions were verified as cancer by pathology, of which 63 cancer lesions were clinically significant prostate cancer. Fifty-one lesions were simultaneously found by mpMRI and PSMA PET. A total of 23 lesions were invisible on either image, and all lesions were ≤ International Society of Urological Pathology 2 or ≤ 15 mm. Forty-five (95.7%) index tumors found by mpMRI combined with PSMA PET were consistent with pathology. Nine patients reported positive surgical margin. CONCLUSIONS: Biopsy-free prostatectomy is safe and feasible for patients with evaluation strictly by mpMRI combined with 18F-PSMA PET/CT.

Pictorial review of the diagnosis of muscle-invasive bladder cancer using vesical imaging-reporting and data system (VI-RADS).

The Vesical Imaging-Reporting and Data System (VI-RADS) is a standard magnetic resonance imaging (MRI) and diagnostic method for muscle-invasive bladder cancer that was published in 2018. Several studies have demonstrated that VI-RADS has high diagnostic power and reproducibility. However, reading VI-RADS requires a certain amount of expertise, and radiologists need to be aware of the various pitfalls. MRI of the bladder includes T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and dynamic contrast-enhanced imaging (DCEI). T2WI is excellent for understanding anatomy. DWI and DCEI show high contrast between the tumor and normal anatomical structures and are suitable for staging local tumors. Bladder tumors are classified into five categories according to their size and morphology and their positional relationship to the bladder wall based on the VI-RADS diagnostic criteria. If the T2WI, DWI, and DCEI categories are the same, the category is the VI-RADS category. If the categories do not match, the DWI category is the VI-RADS category. If image quality of DWI is not evaluable, the DCEI category is the final category. In many cases, DWI is dominant, but this does not mean that T2WI and DCEI can be omitted from the reading of the bladder. In this educational review, typical and atypical teaching cases are demonstrated, and how to resolve misdiagnosis and the limitations of VI-RADS are discussed. The most important aspect of VI-RADS reading is to practice multiparametric reading with a solid understanding of the characteristics and role of each sequence and an awareness of the various pitfalls.

Synchronous neuroendocine liver metastases in comparison to primary pancreatic neuroendocrine tumors on MRI and SSR-PET/CT.

Background: The study aimed to compare and correlate morphological and functional parameters in pancreatic neuroendocrine tumors (pNET) and their synchronous liver metastases (NELM), while also assessing prognostic imaging parameters. Methods: Patients with G1/G2 pNET and synchronous NELM underwent pretherapeutic abdominal MRI with DWI and 68Ga-DOTATATE/TOC PET/CT were included. ADC (mean, min), SNR_art and SNT_T2 (SNR on arterial phase and on T2) and SUV (max, mean) for three target NELM and pNET, as well as tumor-free liver and spleen (only in PET/CT) were measured. Morphological parameters including size, location, arterial enhancement, cystic components, T2-hyperintensity, ductal dilatation, pancreatic atrophy, and vessel involvement were noted. Response evaluation used progression-free survival (PFS) with responders (R;PFS>24 months) and non-responders (NR;PFS ≤ 24 months). Results: 33 patients with 33 pNETs and 95 target NELM were included. There were no significant differences in ADC and SUV values between NELM and pNET. 70% of NELM were categorized as hyperenhancing lesions, whereas the pNETs exhibited significantly lower rate (51%) of hyperenhancement (p<0.01) and significant lower SNR_art. NELM were qualitatively and quantitatively (SNR_T2) significantly more hyperintense on T2 compared to pNET (p=0.01 and p<0.001). NELM of R displayed significantly lower ADCmean value in comparison to the ADC mean value of pNET (0.898 versus 1.037x10-3mm²/s,p=0.036). In NR, T2-hyperintensity was notably higher in NELM compared to pNET (p=0.017). The hepatic tumor burden was significantly lower in the R compared to the NR (10% versus 30%). Conclusions: Arterial hyperenhancement and T2-hyperintensity differ between synchronous NELM and pNET. These findings emphasize the importance of a multifaceted approach to imaging and treatment planning in patients with these tumors as well as in predicting treatment responses.

Transperineal 3-Core Magnetic Resonance Imaging Ultrasound Fusion Targeted Plus Laterally 6-Core Systematic Biopsy in Prostate Cancer Diagnosis.

INTRODUCTION: It is important to explore strategies reducing the number of SB cores taken to minimize biopsy-related morbidity and patient's discomfort during biopsy. This study aims to optimize prostate biopsy procedures by reducing the number of systematic biopsy (SB) cores while preserving cancer detection rates in the era of combined biopsy. PATIENTS AND METHODS: We prospectively recruited patients with ≥1 magnetic resonance imaging (MRI) lesions and they underwent transperineal combined 12-core SB+3-core targeted prostate biopsy (TB, reference standard). New strategy was defined as a laterally 6-core SB+3-core TB. Patients were served as their own control. Detection rates for overall prostate cancer (PCa) and clinically significant PCa (csPCa) were compared among the standard SB, MRI-TB, 6-core SB +3-core TB, and reference standard. Pathology consistency was assessed using the Kappa test. RESULTS: A total of 204 men were included, of which 111 (54.41%) and 92 (45.10%) harbored overall PCa and csPCa. Referenced combined biopsy detected significantly 6.86% (P = .0005) or 4.90% (P = .0044) more csPCa than performing only SB or 3-core TB, but was comparable to the new biopsy strategy. (45.10% vs. 43.14%, P = .1336) Similar results persisted when limiting patients in biopsy-naïve men or stratified by Prostate Imaging Reporting and Data System scores, PSAD, and index lesion parameters. Additionally, performing 6-core SB+3-core TB demonstrated high consistency with reference standard in grade group distribution (Kappa coefficient: 0.952 for all, 0.961 for biopsy-naïve men) and achieved superior sensitivity of 95.7% (All: 95% CI: 89.2%-99.8%) and 96.9% (Biopsy-naïve: 95% CI: 91.1%-99.7%), respectively. CONCLUSIONS: The 6-core SB+3-core TB approach maintains expected detection rates while reducing the total core count, offering a promising alternative to the reference standard, which may help to tailor transperineal combined biopsy procedures.

Prediction of Clinically Significant Prostate Cancer by a Specific Collagen-related Transcriptome, Proteome, and Urinome Signature.

BACKGROUND AND OBJECTIVE: While collagen density has been associated with poor outcomes in various cancers, its role in prostate cancer (PCa) remains elusive. Our aim was to analyze collagen-related transcriptomic, proteomic, and urinome alterations in the context of detection of clinically significant PCa (csPCa, International Society of Urological Pathology [ISUP] grade group ≥2). METHODS: Comprehensive analyses for PCa transcriptome (n = 1393), proteome (n = 104), and urinome (n = 923) data sets focused on 55 collagen-related genes. Investigation of the cellular source of collagen-related transcripts via single-cell RNA sequencing was conducted. Statistical evaluations, clustering, and machine learning models were used for data analysis to identify csPCa signatures. KEY FINDINGS AND LIMITATIONS: Differential expression of 30 of 55 collagen-related genes and 34 proteins was confirmed in csPCa in comparison to benign prostate tissue or ISUP 1 cancer. A collagen-high cancer cluster exhibited distinct cellular and molecular characteristics, including fibroblast and endothelial cell infiltration, intense extracellular matrix turnover, and enhanced growth factor and inflammatory signaling. Robust collagen-based machine learning models were established to identify csPCa. The models outcompeted prostate-specific antigen (PSA) and age, showing comparable performance to multiparametric magnetic resonance imaging (mpMRI) in predicting csPCa. Of note, the urinome-based collagen model identified four of five csPCa cases among patients with Prostate Imaging-Reporting and Data System (PI-IRADS) 3 lesions, for which the presence of csPCa is considered equivocal. The retrospective character of the study is a limitation. CONCLUSIONS AND CLINICAL IMPLICATIONS: Collagen-related transcriptome, proteome, and urinome signatures exhibited superior accuracy in detecting csPCa in comparison to PSA and age. The collagen signatures, especially in cases of ambiguous lesions on mpMRI, successfully identified csPCa and could potentially reduce unnecessary biopsies. The urinome-based collagen signature represents a promising liquid biopsy tool that requires prospective evaluation to improve the potential of this collagen-based approach to enhance diagnostic precision in PCa for risk stratification and guiding personalized interventions. PATIENT SUMMARY: In our study, collagen-related alterations in tissue, and urine were able to predict the presence of clinically significant prostate cancer at primary diagnosis.

Natural history of histologically benign PIRADS 4-5 lesions in multiparametric MRI: Real-life experience in an academic center.

INTRODUCTION: The follow-up findings of patients who underwent prostate biopsy for prostate image reporting and data system (PIRADS) 4 or 5 multiparametric magnetic resonance imaging (mpMRI) findings and had benign histology were retrospectively reviewed. METHODS: There were 190 biopsy-naive patients. Patients with at least 12 months of follow-up between 2012 and 2023 were evaluated. All MRIs were interpreted by two very experienced uroradiologists. Of the patients, 125 had either cognitive or software fusion MR-targeted biopsies with 4 + 8/10 cores. The remaining 65 patients had in-bore biopsies with 4-5 cores. Prostate-specific antigen (PSA) levels below 4 ng/mL were defined as PSA regression following biopsy. PIRADS 1-3 lesions on new MRI images were classified as MRI regression. RESULTS: Median patient age and PSA were 62 (39-82) years and six (0.4-33) ng/mL, respectively, at the initial work-up. During a median follow-up period of 44 months, 37 (19.4%) patients were lost to follow-up. Of the remaining 153 patients, 82 (53.6%) had persistently high PSA. Among them, 72 (87.8%) had repeat mpMRI within 6-24 months which showed regressive findings (PIRADS 1-3) in 53 patients (73.6%) and PIRADS 4-5 index lesion persistence in 19 cases (26.4%). The latter group was recommended to have rebiopsy. Of these 19 patients, 16 underwent MRI-targeted rebiopsy. Prostate cancer was diagnosed in six (37.5%) patients and of these four (25%) were clinically significant (>Grade Group 1). Totally, clinically significant prostate cancer was detected in 4/153 (2.6%) patients followed up. CONCLUSION: Patients should be warned against the relative relaxing effect of a negative biopsy after identification of PIRADS 4-5 index lesion. While PSA decrease was observed in many patients during follow-up, persistent MRI findings were present in nearly a quarter of patients with persistently high PSA. A rebiopsy is warranted in these patients, with significant prostate cancer diagnosed in a quarter of patients with rebiopsy.

Deep learning model based on contrast-enhanced MRI for predicting post-surgical survival in patients with hepatocellular carcinoma.

Objective: To develop a deep learning model based on contrast-enhanced magnetic resonance imaging (MRI) data to predict post-surgical overall survival (OS) in patients with hepatocellular carcinoma (HCC). Methods: This bi-center retrospective study included 564 surgically resected patients with HCC and divided them into training (326), testing (143), and external validation (95) cohorts. This study used a three-dimensional convolutional neural network (3D-CNN) ResNet to learn features from the pretreatment MR images (T1WIpre, late arterial phase, and portal venous phase) and got the deep learning score (DL score). Three cox regression models were established separately using the DL score (3D-CNN model), clinical features (clinical model), and a combination of above (combined model). The concordance index (C-index) was used to evaluate model performance. Results: We trained a 3D-CNN model to get DL score from samples. The C-index of the 3D-CNN model in predicting 5-year OS for the training, testing, and external validation cohorts were 0.746, 0.714, and 0.698, respectively, and were higher than those of the clinical model, which were 0.675, 0.674, and 0.631, respectively (P = 0.009, P = 0.204, and P = 0.092, respectively). The C-index of the combined model for testing and external validation cohorts was 0.750 and 0.723, respectively, significantly higher than the clinical model (P = 0.017, P = 0.016) and the 3D-CNN model (P = 0.029, P = 0.036). Conclusions: The combined model integrating the DL score and clinical factors showed a higher predictive value than the clinical and 3D-CNN models and may be more useful in guiding clinical treatment decisions to improve the prognosis of patients with HCC.

Energetic dysfunction and iron overload in early Parkinson's disease: Two distinct mechanisms?

INTRODUCTION: Identifying biomarkers reflecting cellular dysfunctions in early Parkinson's disease patients (ePD) is needed to develop targeted therapeutic strategies. We aimed to determine if cellular energetic dysfunction related to increased brain sodium concentration would be co-located to microstructural alterations and iron deposition in ePD. METHODS: We prospectively included 12 ePD (mean disease duration 20.0 ± 10.2 months) and 13 healthy controls (HC), scanned with a 7 T 1H and 23Na MRI. Complementary voxel-based and region-based assessments were performed, the latter utilizing a high-resolution multimodal template we created (combining quantitative T1 maps (qT1), transverse relaxation rate (R2*), quantitative magnetic susceptibility mapping (QSM) images) from 200 subjects. This template allowed a precise multiparametric assessment of sodium concentration, QSM, R2*, qT1, mean diffusivity, and fractional anisotropy values. A two-sided p-value<0.05 was considered statistically significant after the Bonferroni correction. RESULTS: Relative to HC, ePD showed significantly higher sodium concentration in left Substantia nigra (SN) pars reticulata (46.13 mM ± 3.52 vs 38.60 mM ± 6.10, p = 0.038), a subpart of the SN pars compacta (SNc) and ventral tegmental area, Putamen, Globus Pallidum external, accumbens nucleus and claustrum. Significantly increased QSM and R2* values, and decreased T1 values, were limited to the Nigrosomes 1 (Nig) and right SNc (all p < 0.05). QSM values in the Nig were significantly correlated to UPDRS-III scores (r = 0.91,p < 0.001). CONCLUSION: In ePD, brain sodium accumulation was broad and dissociated from iron accumulation. As with iron accumulation, a sodium-related pathophysiological approach could lead to identifying potential new therapeutic agents and deserves further investigation.

The Impact of Prostate Volume on Prostate Cancer Detection: Comparing Magnetic Resonance Imaging with Transrectal Ultrasound in Biopsy-naïve Men.

Background and objective: This study aimed to determine the difference in prostate volume (PV) derived from transrectal ultrasound (TRUS) and multiparametric magnetic resonance imaging (mpMRI), and to further investigate the role of TRUS prostate-specific antigen density (PSAD) and mpMRI-PSAD in prostate cancer (PCa) detection in biopsy-naïve men. Methods: Patients who underwent an initial prostate biopsy within 3 mo after mpMRI between January 2016 and December 2021 were analyzed retrospectively. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of both TRUS-PSAD and mpMRI-PSAD for PCa detection were calculated and compared. The Pearson correlation coefficient, Bland-Altman plot, and receiver operating characteristic curve were also utilized to explore the interests of this study. Key findings and limitations: The median prostate-specific antigen level of 875 patients was 9.79 (interquartile range [IQR]: 7.09-13.50) ng/ml. The median mpMRI-PV and TRUS-PV were 41.92 (IQR: 29.29-60.73) and 41.04 (IQR: 29.24-57.27) ml, respectively, demonstrating a strong linear correlation (r = 0.831, 95% confidence interval: 0.809, 0.850; p < 0.01) and sufficient agreement. No significant difference was observed in terms of the sensitivity, specificity, PPV, and NPV between TRUS-PSAD and mpMRI-PSAD for any PCa and clinically significant PCa (csPCa) detection. The overall discriminative ability of TRUS-PSAD for detecting PCa or non-PCa, as well as csPCa and non-csPCa, was comparable with that of mpMRI-PSAD, and similar results were also observed in the subsequent analysis stratified by mpMRI-PV quartiles, prostate-specific antigen level, and age. The limitations include the retrospective and single-center nature and a lack of follow-up information. Conclusions and clinical implications: TRUS-PV and MRI-PV exhibited a strong linear correlation and reached sufficient agreement. The efficiency of TRUS-PSAD and mpMRI-PSAD for PCa detection was comparable. TRUS could be used for PV estimation and dynamic monitoring of PSAD, and TRUS-PSAD could effectively guide clinical decision-making and optimize diagnostic strategies. Patient summary: In this work, prostate volume (PV) derived from transrectal ultrasound (TRUS) exhibited a strong linear correlation with the PV derived from multiparametric magnetic resonance imaging (mpMRI). The efficiency of TRUS prostate-specific antigen density (PSAD) and mpMRI-PSAD for the detection of prostate cancer was comparable. TRUS could be used for PV estimation and TRUS-PSAD could help in clinical decision-making and optimizing diagnostic strategies.

Computer-aided detection of prostate cancer in early stages using multi-parameter MRI: A promising approach for early diagnosis.

BACKGROUND: Transrectal ultrasound-guided prostate biopsy is the gold standard diagnostic test for prostate cancer, but it is an invasive examination of non-targeted puncture and has a high false-negative rate. OBJECTIVE: In this study, we aimed to develop a computer-assisted prostate cancer diagnosis method based on multiparametric MRI (mpMRI) images. METHODS: We retrospectively collected 106 patients who underwent radical prostatectomy after diagnosis with prostate biopsy. mpMRI images, including T2 weighted imaging (T2WI), diffusion weighted imaging (DWI), and dynamic-contrast enhanced (DCE), and were accordingly analyzed. We extracted the region of interest (ROI) about the tumor and benign area on the three sequential MRI axial images at the same level. The ROI data of 433 mpMRI images were obtained, of which 202 were benign and 231 were malignant. Of those, 50 benign and 50 malignant images were used for training, and the 333 images were used for verification. Five main feature groups, including histogram, GLCM, GLGCM, wavelet-based multi-fractional Brownian motion features and Minkowski function features, were extracted from the mpMRI images. The selected characteristic parameters were analyzed by MATLAB software, and three analysis methods with higher accuracy were selected. RESULTS: Through prostate cancer identification based on mpMRI images, we found that the system uses 58 texture features and 3 classification algorithms, including Support Vector Machine (SVM), K-nearest Neighbor (KNN), and Ensemble Learning (EL), performed well. In the T2WI-based classification results, the SVM achieved the optimal accuracy and AUC values of 64.3% and 0.67. In the DCE-based classification results, the SVM achieved the optimal accuracy and AUC values of 72.2% and 0.77. In the DWI-based classification results, the ensemble learning achieved optimal accuracy as well as AUC values of 75.1% and 0.82. In the classification results based on all data combinations, the SVM achieved the optimal accuracy and AUC values of 66.4% and 0.73. CONCLUSION: The proposed computer-aided diagnosis system provides a good assessment of the diagnosis of the prostate cancer, which may reduce the burden of radiologists and improve the early diagnosis of prostate cancer.

Predicting cytogenetic risk in multiple myeloma using conventional whole-body MRI, spinal dynamic contrast-enhanced MRI, and spinal diffusion-weighted imaging.

OBJECTIVES: Cytogenetic abnormalities are predictors of poor prognosis in multiple myeloma (MM). This paper aims to build and validate a multiparametric conventional and functional whole-body MRI-based prediction model for cytogenetic risk classification in newly diagnosed MM. METHODS: Patients with newly diagnosed MM who underwent multiparametric conventional whole-body MRI, spinal dynamic contrast-enhanced (DCE-)MRI, spinal diffusion-weighted MRI (DWI) and had genetic analysis were retrospectively included (2011-2020/Ghent University Hospital/Belgium). Patients were stratified into standard versus intermediate/high cytogenetic risk groups. After segmentation, 303 MRI features were extracted. Univariate and model-based methods were evaluated for feature and model selection. Testing was performed using receiver operating characteristic (ROC) and precision-recall curves. Models comparing the performance for genetic risk classification of the entire MRI protocol and of all MRI sequences separately were evaluated, including all features. Four final models, including only the top three most predictive features, were evaluated. RESULTS: Thirty-one patients were enrolled (mean age 66 ± 7 years, 15 men, 13 intermediate-/high-risk genetics). None of the univariate models and none of the models with all features included achieved good performance. The best performing model with only the three most predictive features and including all MRI sequences reached a ROC-area-under-the-curve of 0.80 and precision-recall-area-under-the-curve of 0.79. The highest statistical performance was reached when all three MRI sequences were combined (conventional whole-body MRI + DCE-MRI + DWI). Conventional MRI always outperformed the other sequences. DCE-MRI always outperformed DWI, except for specificity. CONCLUSIONS: A multiparametric MRI-based model has a better performance in the noninvasive prediction of high-risk cytogenetics in newly diagnosed MM than conventional MRI alone. CRITICAL RELEVANCE STATEMENT: An elaborate multiparametric MRI-based model performs better than conventional MRI alone for the noninvasive prediction of high-risk cytogenetics in newly diagnosed multiple myeloma; this opens opportunities to assess genetic heterogeneity thus overcoming sampling bias. KEY POINTS: • Standard genetic techniques in multiple myeloma patients suffer from sampling bias due to tumoral heterogeneity. • Multiparametric MRI noninvasively predicts genetic risk in multiple myeloma. • Combined conventional anatomical MRI, DCE-MRI, and DWI had the highest statistical performance to predict genetic risk. • Conventional MRI alone always outperformed DCE-MRI and DWI separately to predict genetic risk. DCE-MRI alone always outperformed DWI separately, except for the parameter specificity to predict genetic risk. • This multiparametric MRI-based genetic risk prediction model opens opportunities to noninvasively assess genetic heterogeneity thereby overcoming sampling bias in predicting genetic risk in multiple myeloma.

A comparison study of 68gallium-prostate-specific membrane antigen positron emission tomography-computed tomography and multiparametric magnetic resonance imaging for locoregional staging of prostate cancer.

Purpose: Prostate cancer (PCa) is the most common malignancy in men aged 50 years and older and the second cause of cancer death among men. Accurate staging of PCa preoperatively is of high importance for treatment decisions and patient management. Conventional imaging modalities (ultrasound, computed tomography [CT], and magnetic resonance imaging) are inaccurate for the staging of PCa. Newer modality multiparametric magnetic resonance imaging (mpMRI) and prostate-specific membrane antigen (PSMA) positron emission tomography (PET) scan show promising results for the staging of PCa. Only fewer studies are available for comparison of these modalities with histopathology as reference. The objective of our study is to evaluate the diagnostic accuracy of independent 68gallium PSMA (68Ga-PSMA) PET-CT compared with mpMRI for preoperative staging of PCa, using histopathology as the reference standard. Materials and methods: From August 2021 to December 2022, 30 patients of biopsy-proven PCa were prospectively enrolled as per eligibility criteria. Preoperatively, 68Ga-PSMA PET scan and mpMRI were done in all the patients. Extracapsular extension (ECE), seminal vesicle invasion (SVI), and lymph node metastasis (LNM) were investigated separately. Subsequently, the patients underwent robotic-assisted radical prostatectomy with bilateral pelvic lymph node dissection. Results: mpMRI prostate was more sensitive (66.66%) but less specific than PSMA PET-CT (55.55%) for ECE. mpMRI and PSMA PET-CT both had similar sensitivity (83.3%) and specificity (87.5%) for SVI. PSMA PET-CT was more sensitive (85.71%) and specific (95.6%) than mpMRI prostate (62.5% and 91.30%, respectively) for LNM. Conclusion: PSMA PET-CT is more specific for the detection of ECE and more sensitive and specific for the detection of LNM than mpMRI, and similar for the detection of SVI. mpMRI provides only local staging, while PSMA PET-CT provides information about local, regional, and distal staging. Overall, PSMA PET-CT is superior to mpMRI for locoregional staging of PCa.

The role of multiparametric magnetic resonance imaging in the diagnosis of granulomatous prostatitis mimicking prostate cancer.

PURPOSE: Aimed to investigate the role of multiparametric magnetic resonance imaging (mp-MRI) in the diagnosis of granulomatous prostatitis caused by intravesical Bacillus Calmette-Guérin (BCG). METHODS: In this prospective, single-center study, 10 male patients who were given intravesical BCG due to intermediate- and high-risk bladder cancer were included. Before transurethral resection of bladder tumors (TURB), all patients were evaluated by mp-MRI, serum prostate-specific antigen (PSA), and digital rectal examination (DRE). Serum PSA levels and DRE findings were evaluated before and after intravesical BCG treatment. Prostate mp-MRI was performed for patients with elevated levels of serum PSA and/or with abnormal DRE findings. Then, MRI fusion + systematic prostate biopsy was performed. Demographic data of the patients before and after intravesical BCG were compared. RESULTS: The average age of the patients was 66.9 years (55-87 years). While PSA was 1.7 ng/ml before intravesical BCG treatment, it was 4.3 ng/ml after intravesical BCG treatment (p = 0.005). PSA density (PSAD) was 0.04 and 0.10 before and after the treatment, respectively (p = 0.012). DRE findings of all patients were normal before the treatment. However, abnormal findings were detected in 80% of them after the treatment (p = 0.008). PI-RADS ≥ 3 lesions were found to be significantly higher in all patients after intravesical BCG (p = 0.004). CONCLUSION: Granulomatous prostatitis is a rare complication of intravesical BCG. High PSA, abnormal DRE, and PI-RADS ≥ 3 lesions detected after intravesical BCG should suggest granulomatous prostatitis and unnecessary biopsies may be avoided.

Multi-Dynamic-Multi-Echo-based MRI for the Pre-Surgical Determination of Sellar Tumor Consistency: a Quantitative Approach for Predicting Lesion Resectability.

PURPOSE: Pre-surgical information about tumor consistency could facilitate neurosurgical planning. This study used multi-dynamic-multi-echo (MDME)-based relaxometry for the quantitative determination of pituitary tumor consistency, with the aim of predicting lesion resectability. METHODS: Seventy-two patients with suspected pituitary adenomas, who underwent preoperative 3 T MRI between January 2020 and January 2022, were included in this prospective study. Lesion-specific T1-/T2-relaxation times (T1R/T2R) and proton density (PD) metrics were determined. During surgery, data about tumor resectability were collected. A Receiver Operating Characteristic (ROC) curve analysis was performed to investigate the diagnostic performance (sensitivity/specificity) for discriminating between easy- and hard-to-remove by aspiration (eRAsp and hRAsp) lesions. A Mann-Whitney-U-test was done for group comparison. RESULTS: A total of 65 participants (mean age, 54 years ± 15, 33 women) were enrolled in the quantitative analysis. Twenty-four lesions were classified as hRAsp, while 41 lesions were assessed as eRAsp. There were significant differences in T1R (hRAsp: 1221.0 ms ± 211.9; eRAsp: 1500.2 ms ±â€¯496.4; p = 0.003) and T2R (hRAsp: 88.8 ms ± 14.5; eRAsp: 137.2 ms ± 166.6; p = 0.03) between both groups. The ROC analysis revealed an area under the curve of 0.72 (95% CI: 0.60-0.85) at p = 0.003 for T1R (cutoff value: 1248 ms; sensitivity/specificity: 78%/58%) and 0.66 (95% CI: 0.53-0.79) at p = 0.03 for T2R (cutoff value: 110 ms; sensitivity/specificity: 39%/96%). CONCLUSION: MDME-based relaxometry enables a non-invasive, pre-surgical characterization of lesion consistency and, therefore, provides a modality with which to predict tumor resectability.

Magnetic Resonance Imaging-based Prostate Cancer Screening in Carriers of Pathogenic Germline Mutations: Interim Results from the Initial Screening Round of the Prostate Cancer Genetic Risk Evaluation and Screening Study.

BACKGROUND: The risk of early-onset and clinically aggressive prostate cancer is elevated in carriers of certain rare pathogenic germline mutations. The utility of augmenting traditional prostate-specific antigen (PSA)-based screening measures with multiparametric magnetic resonance imaging (MRI) in this population is not yet known. OBJECTIVE: To evaluate MRI-based screening in comparison with traditional PSA-based screening among individuals at an elevated genetic risk for prostate cancer. DESIGN, SETTING, AND PARTICIPANTS: Male germline carriers of pathogenic/likely pathogenic variants in any of 19 prostate cancer risk genes between the ages of 35 and 74 yr with no prior history of prostate cancer were recruited. Intervention Enrolled participants underwent screening with annual PSA, digital rectal examination (DRE), and triennial multiparametric MRI. Individuals with abnormal DRE, elevated age-adjusted PSA (>1.5 ng/ml for 35-49 yr, >2.0 ng/ml for 50-54 yr, and >3.0 ng/ml for 55-74 yr), or suspicious multiparametric MRI (Prostate Imaging Reporting and Data System [PI-RADS] ≥3 lesion) were offered prostate biopsy. Outcome measurements and statistical analysis Endpoints were diagnosis of any and clinically significant prostate cancer, and alternative screening strategies were compared by a decision curve analysis. RESULTS AND LIMITATIONS: To date, 101 males have completed the first round of screening. The greatest proportion of participants are carriers of BRCA2 (n = 44), BRCA1 (n = 35), and ATM (n = 7) variants. Twenty-one have undergone biopsy, resulting in the detection of nine cases of cancer (seven clinically significant). For the detection of clinically significant prostate cancer, abnormal MRI (PI-RADS ≥3) demonstrated 100% sensitivity (7/7) with a negative predictive value (NPV) of 100%, whereas PSA-based screening alone had 57% (4/7) sensitivity with an NPV of 73%. Of six screening strategies evaluated in the decision curve analysis, MRI-based screening alone achieved superior net benefit at all threshold probabilities compared with PSA screening-detecting one additional cancer case per 7.5 patients, while avoiding more unnecessary biopsies at the same threshold probability. CONCLUSIONS: Disease prevalence is high among carriers of prostate cancer-associated pathogenic germline mutations. Early results suggest that MRI-based screening enhances early detection of clinically significant disease beyond PSA screening alone. PATIENT SUMMARY: In this study, we present the interim results from the PROGRESS prostate cancer screening trial. We found that in certain germline carriers of prostate cancer risk mutations, magnetic resonance imaging-based screening enhances detection of prostate cancer while reducing biopsies triggered, in comparison with traditional prostate-specific antigen screening strategies.

MRI-based radiomics for prediction of extraprostatic extension of prostate cancer: a systematic review and meta-analysis.

PURPOSE: We to systematically evaluate the diagnostic performance of MRI radiomics in detecting extracapsular extension (EPE) of prostate cancer (PCa). METHODS: A literature search of online databases of PubMed, EMBASE, Cochrane Library, Web of Science, and Google Scholar online scientific publication databases was performed to identify studies published up to July 2023. The summary estimates were pooled with the hierarchical summary receiver-operating characteristic (HSROC) model. This study was reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement, the quality of included studies was assessed with the Quality Assessment of Diagnostic Accuracy Studies-2 tool (QUADAS-2) and the radiomics quality score (RQS). Meta-regression and subgroup analyses were performed to explore the impact of varying clinical settings. RESULTS: A total of ten studies met the inclusion criteria. The pooled sensitivity and specificity were 0.77 (95% CI 0.68-0.84, I2 = 83.5%) and 0.75 (95% CI 0.67-0.82, I2 = 83.5%), respectively, with an area under the HSROC curve of 0.88 (95% CI 0.85-0.91). Study quality was not high while assessing with the RQS. Substantial heterogeneity was observed between studies; however, meta-regression analysis did not reveal any significant contributing factors. CONCLUSIONS: MRI radiomics demonstrated moderate sensitivity and specificity, offering similar diagnostic performance with previous risk stratifications and models that primarily based on radiologists' subjective experience. However, all studies included were retrospective, thus the performance of radiomics needs to validate in prospective, multicenter studies.

Differentiation of Muscular Invasion in Bladder Cancer: Additional Value of Synthetic Magnetic Resonance Imaging.

RATIONALE AND OBJECTIVES: To evaluate the potential of Synthetic Magnetic Resonance Imaging (SynMRI) in identifying muscular invasion in bladder cancer (BCa), and explore whether there is additional value in combination with the Vesical Imaging-Reporting and Data System (VI-RADS). METHODS: In this prospective single-center study, pathologically-confirmed BCa were enrolled between May 2023 and November 2023. All participants underwent preoperative multiparametric MRI, including T1/T2 weighted, SynMRI and diffusion-weighted imaging. T1/T2/PD values and apparent diffusion coefficient (ADC) values were compared between muscle invasive (MIBC) and non-invasive (NMIBC) groups. Receiver operating characteristic (ROC) analysis with the variables and their combination was performed to explore the performance of distinguishing the MIBC from NMIBC, and the ROC curves were compared using DeLong's test. RESULTS: A total of 54 BCa patients were enrolled (38 males; NMIBC/MIBC=37/19) and all assessed with VI-RADS without dynamic enhanced imaging (DCE). Compared to NMIBC group, MIBC group had significantly larger diameter, higher VI-RADS score, lower T2 and ADC values (P < 0.05). VI-RADS score and T2 showed independent predictive value in differentiating NMIBC and MIBC. The combined model (T2 + VI-RADS+Diameter) resulted in significantly improved specificity (0.842), sensitivity (0.914), and AUC (0.943), in comparison to VI-RADS or ADC alone (P < 0.05). CONCLUSION: T2 relaxation time can be easily obtained from SynMRI in routine clinical protocol and assist VI-RADS score system without DCE to improve differentiation performance in identifying NMIBC and MIBC.