Role of Additional MRI-Based Morphologic Measurements on the Performance of VI-RADS for Muscle-Invasive Bladder Cancer.

BACKGROUND: Vesical Imaging-Reporting and Data System (VI-RADS) is a pathway for the standardized imaging and reporting of bladder cancer staging using multiparametric (mp) MRI. PURPOSE: To investigate additional role of morphological (MOR) measurements to VI-RADS for the detection of muscle-invasive bladder cancer (MIBC) with mpMRI. STUDY TYPE: Retrospective. POPULATION: A total of 198 patients (72 MIBC and 126 NMIBC) underwent bladder mpMRI was included. FIELD STRENGTH/SEQUENCE: 3.0 T/T2-weighted imaging with fast-spin-echo sequence, spin-echo-planar diffusion-weighted imaging and dynamic contrast-enhanced imaging with fast 3D gradient-echo sequence. ASSESSMENT: VI-RADS score and MOR measurement including tumor location, number, stalk, cauliflower-like surface, type of tumor growth, tumor-muscle contact margin (TCM), tumor-longitudinal length (TLL), and tumor cellularity index (TCI) were analyzed by three uroradiologists (3-year, 8-year, and 15-year experience of bladder MRI, respectively) who were blinded to histopathology. STATISTICAL TESTS: Significant MOR measurements associated with MIBC were tested by univariable and multivariable logistic regression (LR) analysis with odds ratio (OR). Area under receiver operating characteristic curve (AUC) with DeLong's test and decision curve analysis (DCA) were used to compared the performance of unadjusted vs. adjusted VI-RADS. A P-value <0.05 was considered statistically significant. RESULTS: TCM (OR 9.98; 95% confidence interval [CI] 4.77-20.8), TCI (OR 5.72; 95% CI 2.37-13.8), and TLL (OR 3.35; 95% CI 1.40-8.03) were independently associated with MIBC at multivariable LR analysis. VI-RADS adjusted by three MORs achieved significantly higher AUC (reader 1 0.908 vs. 0.798; reader 2 0.906 vs. 0.855; reader 3 0.907 vs. 0.831) and better clinical benefits than unadjusted VI-RADS at DCA. Specially in VI-RADS-defined equivocal lesions, MOR-based adjustment resulted in 55.5% (25/45), 70.4% (38/54), and 46.4% (26/56) improvement in accuracy for discriminating MIBC in three readers, respectively. DATA CONCLUSION: MOR measurements improved the performance of VI-RADS in detecting MIBC with mpMRI, especially for equivocal lesions. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.

Biopsy-free AI-aided precision MRI assessment in prediction of prostate cancer biochemical recurrence.

BACKGROUND: To investigate the predictive ability of high-throughput MRI with deep survival networks for biochemical recurrence (BCR) of prostate cancer (PCa) after prostatectomy. METHODS: Clinical-MRI and histopathologic data of 579 (train/test, 463/116) PCa patients were retrospectively collected. The deep survival network (iBCR-Net) is based on stepwise processing operations, which first built an MRI radiomics signature (RadS) for BCR, and predicted the T3 stage and lymph node metastasis (LN+) of tumour using two predefined AI models. Subsequently, clinical, imaging and histopathological variables were integrated into iBCR-Net for BCR prediction. RESULTS: RadS, derived from 2554 MRI features, was identified as an independent predictor of BCR. Two predefined AI models achieved an accuracy of 82.6% and 78.4% in staging T3 and LN+. The iBCR-Net, when expressed as a presurgical model by integrating RadS, AI-diagnosed T3 stage and PSA, can match a state-of-the-art histopathological model (C-index, 0.81 to 0.83 vs 0.79 to 0.81, p > 0.05); and has maximally 5.16-fold, 12.8-fold, and 2.09-fold (p < 0.05) benefit to conventional D'Amico score, the Cancer of the Prostate Risk Assessment (CAPRA) score and the CAPRA Postsurgical score. CONCLUSIONS: AI-aided iBCR-Net using high-throughput MRI can predict PCa BCR accurately and thus may provide an alternative to the conventional method for PCa risk stratification.

Performance of Artificial Intelligence-Aided Diagnosis System for Clinically Significant Prostate Cancer with MRI: A Diagnostic Comparison Study.

BACKGROUND: The high level of expertise required for accurate interpretation of prostate MRI. PURPOSE: To develop and test an artificial intelligence (AI) system for diagnosis of clinically significant prostate cancer (CsPC) with MRI. STUDY TYPE: Retrospective. SUBJECTS: One thousand two hundred thirty patients from derivation cohort between Jan 2012 and Oct 2019, and 169 patients from a publicly available data (U-Net: 423 for training/validation and 49 for test and TrumpeNet: 820 for training/validation and 579 for test). FIELD STRENGTH/SEQUENCE: 3.0T/scanners, T2 -weighted imaging (T2 WI), diffusion-weighted imaging, and apparent diffusion coefficient map. ASSESSMENT: Close-loop AI system was trained with an Unet for prostate segmentation and a TrumpetNet for CsPC detection. Performance of AI was tested in 410 internal and 169 external sets against 24 radiologists categorizing into junior, general and subspecialist group. Gleason score >6 was identified as CsPC at pathology. STATISTICAL TESTS: Area under the receiver operating characteristic curve (AUC-ROC); Delong test; Meta-regression I2 analysis. RESULTS: In average, for internal test, AI had lower AUC-ROC than subspecialists (0.85 vs. 0.92, P < 0.05), and was comparable to junior (0.84, P = 0.76) and general group (0.86, P = 0.35). For external test, both AI (0.86) and subspecialist (0.86) had higher AUC than junior (0.80, P < 0.05) and general reader (0.83, P < 0.05). In individual, it revealed moderate diagnostic heterogeneity in 24 readers (Mantel-Haenszel I2  = 56.8%, P < 0.01), and AI outperformed 54.2% (13/24) of readers in summary ROC analysis. In multivariate test, Gleason score, zonal location, PI-RADS score and lesion size significantly impacted the accuracy of AI; while effect of data source, MR device and parameter settings on AI performance is insignificant (P > 0.05). DATA CONCLUSION: Our AI system can match and to some case exceed clinicians for the diagnosis of CsPC with prostate MRI. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

[Gonadoblastoma: Clinicopathological study and literature review of 3 cases].

OBJECTIVE: To investigate the clinical feature, pathological morphology, special histopathological subtype and immunohistochemical characteristic of gonadoblastoma. METHODS: Three patients of gonadoblastoma treated from 2014 to 2020 were enrolled, and the clinical characteristics, histological morphology and immunophenotype were analyzed, and the literatures were also reviewed. RESULT: Three phenotypical females were 14,17 and 27 years old. Case 1 was 46,XX with normal gonadal development. Case 2 was 46,XY and case 3 was chromosomal chimeric type (46, XY 90%/45,X 10%), both with dysgenetic gonads. Microscopically, the morphology of classic type was observed in all cases more or less, manifesting small nests of primitive germ cells and surrounding clustered sex cord-like cells, usually with Call-Exner like bodies and calcification. In additon, the morphology of special subtype can be seen in case 1,exhibiting cord-like tumor cells, which was segmentated by cellular fibrous stroma. Cases 2 and 3 were accompanied by dysgerminoma components. Immunohistochemically,all the primal germ cells were positive for OCT3/4, PLAP and CDll7 , and sexcord-like cells were positive for inhibin, SF-1, SOX9 and FOXL2 . Patients were followed up for 10 years, 6 years and 4 years respectively without recurrence. CONCLUSION: Gonadoblastoma is a rare germ cell-sex cord stromal tumor, which is usually accompanied by gonadal hypoplasia. As a special subtype, dissecting gonadoblastoma will be easily confused with dysgerminoma/seminoma, but the prognosis is better. So we should improve the understanding of this subtype and avoid overdiagnosis.

Artificial intelligence is a promising prospect for the detection of prostate cancer extracapsular extension with mpMRI: a two-center comparative study.

PURPOSE: A balance between preserving urinary continence as well as sexual potency and achieving negative surgical margins is of clinical relevance while implementary difficulty. Accurate detection of extracapsular extension (ECE) of prostate cancer (PCa) is thus crucial for determining appropriate treatment options. We aimed to develop and validate an artificial intelligence (AI)-based tool for detecting ECE of PCa using multiparametric magnetic resonance imaging (mpMRI). METHODS: Eight hundred and forty nine consecutive PCa patients who underwent mpMRI and prostatectomy without previous radio- or hormonal therapy from two medical centers were retrospectively included. The AI tool was built on a ResNeXt network embedded with a spatial attention map of experts' prior knowledge (PAGNet) from 596 training patients. Model validation was performed in 150 internal and 103 external patients. Performance comparison was made between AI, two experts using a criteria-based ECE grading system, and expert-AI interaction. RESULTS: An index PAGNet model using a single-slice image yielded the highest areas under the receiver operating characteristic curve (AUC) of 0.857 (95% confidence interval [CI], 0.827-0.884), 0.807 (95% CI, 0.735-0.867), and 0.728 (95% CI, 0.631-0.811) in training, internal, and external validation data, respectively. The performance of two experts (AUC, 0.632 to 0.741 vs 0.715 to 0.857) was lower (paired comparison, all p values < 0.05) than that of AI assessment. When experts' interpretations were adjusted by AI assessments, the performance of two experts was improved. CONCLUSION: Our AI tool, showing improved accuracy, offers a promising alternative to human experts for ECE staging using mpMRI.

Longitudinal Multiparametric MRI Assessment of Irradiated Salivary Gland in a Rat Model: Correlated With Histological Findings.

BACKGROUND: Several magnetic resonance imaging (MRI) sequences have been applied to assess injured glands but without histological validation. PURPOSE: To evaluate longitudinal changes in multiparametric MRI (mp-MRI) of irradiated salivary glands in a rat model and investigate correlations between mp-MRI and histological findings. STUDY TYPE: Prospective. ANIMAL MODEL: Submandibular glands of 36 rats were radiated using a single dose of 15 Gy X-ray (irradiation [IR] group), and 6 other rats were enrolled into sham-IR group. mp-MRI were scanned 1 day after sham-IR (n = 6), or 1, 2, 4, 8, 12, 24 weeks after IR (n = 36, 6 per subgroup). FIELD STRENGTH/SEQUENCE: A 3.0-T/Diffusion-weighted imaging (DWI), readout-segmented echo-planar imaging (EPI) sequence; intravoxel incoherent motion DWI, single-shot EPI sequence; T1 mapping, dual-flip-angle gradient-echo sequence with volumetric interpolated breath-hold examination; T2 mapping, turbo spin-echo sequence. ASSESSMENT: Parameters including apparent diffusion coefficient (ADC), pure diffusion coefficient (D), pseudo-diffusion coefficient (D* ), perfusion fraction (f), T1 and T2 value were obtained. Histological examinations, including hematoxylin and eosin staining (for acinar cell fraction [AC%] detection), Masson's trichrome staining (for degree of fibrosis [F%] determination) and CD34-immunohistochemical staining (for microvessel density [MVD] calculation), were performed at corresponding time points. STATISTICAL TESTS: One-way analysis of variance was used to compare the mp-MRI and histological parameters among different groups. Spearman correlation analysis was applied to determine the correlation between mp-MRI and histological parameters. Two-sided P ≤ 0.05 was considered statistically significant. RESULTS: Changes of mp-MRI parameters (ADC, D, D* , f, T1, T2) and histological results (AC%, F%, MVD) among the seven groups were all significant. ADC, D, and T2 values negatively correlated with AC% (ADC, r = -0.728; D, r = -0.773; T2, r = -0.600), f positively correlated with MVD (r = 0.496), and T1 values positively correlated with F% (r = 0.714). DATA CONCLUSION: mp-MRI might be able to noninvasively and quantitatively evaluate the dynamic pathological changes within the irradiated salivary glands. EVIDENCE LEVEL: 1 TECHNICAL EFFICACY: Stage 2.

[Clinical characteristics and treatment strategies of prostatic mucinous adenocarcinoma: A report of 10 cases and literature review].

OBJECTIVE: To investigate the clinical characteristics and treatment strategies of prostatic mucinous adenocarcinoma (PMAC). METHODS: We retrospectively analyzed the clinical data on 10 cases of PMAC treated in the First Affiliated Hospital of Nanjing Medical University from January 2014 to June 2018. The patients were aged 51－79 (65 ± 14) years, with a medium PSA level of 89 (14.63－128.05) µg/L and Gleason scores of 3 + 3 in 1 case, 3 + 4 in 2, 4 + 3 in 1 and 8 in 6 cases preoperatively, 1 treated by robot-assisted radical prostatectomy and the other 9 by laparoscopic radical prostatectomy. We conducted pelvic cavity lymph node dissection for all the patients and analyzed their prognosis and survival. RESULTS: Operations were successfully completed in all the cases. Pathological examination revealed 2 cases of mucinous adenocarcinoma with signet ring cell carcinoma in the 10 PMAC patients, 2 at stage ≤T2b, 5 at stage ≥T2c, 3 positive at pelvic lymph node dissection and 5 positive at the incision margin. The patients were followed up for 6－48 (median 26) months. Four of the patients were found with biochemical recurrence within 2 years after operation and treated by androgen-deprivation therapy, radiotherapy and chemotherapy, which reduced the PSA level to <1.0 µg/ml in all the 4 cases. CONCLUSIONS: PMAC has a good prognosis. Radical surgery is recommended for moderate and low-risk PMAC and the patients with postoperative biochemical recurrence can benefit from comprehensive treatment of total androgen blockade.

A machine learning-assisted decision-support model to better identify patients with prostate cancer requiring an extended pelvic lymph node dissection.

OBJECTIVES: To develop a machine learning (ML)-assisted model to identify candidates for extended pelvic lymph node dissection (ePLND) in prostate cancer by integrating clinical, biopsy, and precisely defined magnetic resonance imaging (MRI) findings. PATIENTS AND METHODS: In all, 248 patients treated with radical prostatectomy and ePLND or PLND were included. ML-assisted models were developed from 18 integrated features using logistic regression (LR), support vector machine (SVM), and random forests (RFs). The models were compared to the Memorial SloanKettering Cancer Center (MSKCC) nomogram using receiver operating characteristic-derived area under the curve (AUC) calibration plots and decision curve analysis (DCA). RESULTS: A total of 59/248 (23.8%) lymph node invasions (LNIs) were identified at surgery. The predictive accuracy of the ML-based models, with (+) or without (-) MRI-reported LNI, yielded similar AUCs (RFs+ /RFs- : 0.906/0.885; SVM+ /SVM- : 0.891/0.868; LR+ /LR- : 0.886/0.882) and were higher than the MSKCC nomogram (0.816; P < 0.001). The calibration of the MSKCC nomogram tended to underestimate LNI risk across the entire range of predicted probabilities compared to the ML-assisted models. The DCA showed that the ML-assisted models significantly improved risk prediction at a risk threshold of ≤80% compared to the MSKCC nomogram. If ePLNDs missed was controlled at <3%, both RFs+ and RFs- resulted in a higher positive predictive value (51.4%/49.6% vs 40.3%), similar negative predictive value (97.2%/97.8% vs 97.2%), and higher number of ePLNDs spared (56.9%/54.4% vs 43.9%) compared to the MSKCC nomogram. CONCLUSIONS: Our ML-based model, with a 5-15% cutoff, is superior to the MSKCC nomogram, sparing ≥50% of ePLNDs with a risk of missing <3% of LNIs.

Using support vector machine analysis to assess PartinMR: A new prediction model for organ-confined prostate cancer.

BACKGROUND: Partin tables represent the most widely used predictive tool for prostate cancer stage at prostatectomy but with potential limitations. PURPOSE: To develop a new PartinMR model for organ-confined prostate cancer (OCPCA) by incorporating Partin table and mp-MRI with a support vector machine (SVM) analysis. STUDY TYPE: Retrospective. POPULATION: In all, 541 patients with biopsy-confirmed prostate cancer underwent mp-MRI. FIELD STRENGTH: T2 -weighted, diffusion-weighted imaging with a 3.0T MR scanner. ASSESSMENT: Candidate predictors included age, prostate-specific antigen, clinical stage, biopsy Gleason score (GS), and mp-MRI findings, ie, tumor location, Prostate Imaging and Reporting and Data System (PI-RADS) score, diameter (D-max), and 6-point MR stage. The PartinMR model with combination of a Partin table and mp-MRI findings was developed using SVM and 5-fold crossvalidation analysis. STATISTICAL TESTS: The predicted ability of the PartinMR model was compared with a standard Partin and a modified Partin table (mPartin) which used for mp-MRI staging. Statistical tests were made by area under receiver operating characteristic curve (AUC), adjusted proportional hazard ratio (HR), and a cost-effective benefit analysis. RESULTS: The rate of OCPCA at prostatectomy was 46.4% (251/541). Using MR staging, mPartin table (AUC, 0.814, 95% confidence interval [CI]: 0.779-0.846, P = 0.001) is appreciably better than the Partin table (AUC, 0.730, 95% CI: 0.690-0.767). Contrarily, adding all MR variables, the PartinMR model (AUC, 0.891, 95% CI: 0.884-0.899, P < 0.001) outperformed any other scheme, with 79.3% sensitivity, 75.7% specificity, 79% positive predictive value, and 76.0% negative predictive value for OCPCA. MR stage represented the most influential predictor of extracapsular extension (HR, 2.77, 95% CI: 1.54-3.33), followed by D-max (2.01, 95% CI: 1.31-2.68), biopsy GS (1.64, 95% CI: 1.35-2.12), and PI-RADS score (1.21, 95% CI: 1.01-1.98). DATA CONCLUSION: The new PartinMR model is superior to the conventional Partin table for OCPCA. Clinical implications of mp-MRI for prostate cancer stage must be confirmed in further trials. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 2 J. MAGN. RESON. IMAGING 2018;48:499-506.

Construction of a Preoperative Radiologic-Risk Signature for Predicting the Pathologic Status of Prostate Cancer at Radical Prostatectomy.

OBJECTIVE: We developed a radiologic-risk signature (RRS) that serves as a surrogate for the pathologic status of prostate cancer (PCA) and investigated its ability to predict disease-free survival. MATERIALS AND METHODS: This study included 631 patients with localized PCA who underwent prostatic multiparametric MRI before prostatectomy. Images from 426 training datasets were structurally interpreted and correlated to a postoperative Memorial Sloan Kettering Cancer Center (MSKCC) score by a stepwise partial least-squares regression analysis. The developed RRS, compared with a preoperative Kattan nomogram, was validated in a cohort of 205 patients with 3-year follow-up data after prostatectomy in terms of calibration, discrimination, and clinical usefulness. Statistical tests were performed by AUC analysis, Kaplan-Meier test, and decision curve analysis. RESULTS: The RRS, which consists of 12 preoperative variables, faithfully represented postoperative MSKCC score in 426 training (r = 0.75; p < 0.001) and 205 validation (r = 0.79; p < 0.001) datasets. For patients in the validation group, RRS showed better discriminative power (C-index, 0.859; 95% CI, 0.779-0.939; p = 0.013) than did the preoperative Kattan nomogram (C-index, 0.780; 95% CI, 0.701-0.859) for predicting 3-year biochemical recurrence and showed higher net benefits for a probability threshold of greater than 10%. CONCLUSION: Characteristics of RRS can faithfully represent the tumor pathologic status and predict accurately the disease postoperative outcome before prostatectomy.

MR-based prognostic nomogram for prostate cancer after radical prostatectomy.

PURPOSE: To assess a magnetic resonance imaging (MRI)-based nomogram in the prediction of prostate cancer (PCa) biochemical recurrence (BCR) within 3 years after prostatectomy. MATERIALS AND METHODS: Between 2009 and 2013, 205 patients with biopsy-confirmed PCa had MRI before prostatectomy. BCR was defined as a PSA failure (>0.2 ng/ml) after prostatectomy. MR features (cancer location, diameter, apparent diffusion coefficients [ADCs], PI-RADS v2 score, dynamic contrast-enhanced [DCE] type, and MR T-stage) were retrospectively evaluated for predicting 3-year BCR based on partial least square regression analysis. Second, imaging features were added to a popularized D'Amico and CAPRA scheme to determine imaging contribution to published nomograms. Lastly, a multivariable Cox regression analysis was employed to determine the independent risk factors of time to BCR. RESULTS: Three-year BCR rate (median follow-up of 44.9 mo) was 25.4% (52/205). The area under receiver operating characteristic (ROC) curve (Az) for MR nomogram (0.909, 95% confidence interval [CI]: 0.861-0.944) was higher than popularized D'Amico (0.793, 95% CI: 0.731-0.846, P = 0.001) and CAPRA (0.809, 95% CI: 0.748-0.860, P = 0.001). The performance of D'Amico (Az: 0.901, 95% CI: 0.852-0.938, P < 0.001) and CAPRA (Az: 0.894, 95% CI: 0.843-0.932, P = 0.004) was significantly improved by adding MR findings. Tumor ADCs (hazard ratio [HR] = 1.747; P = 0.011), PI-RADS score (HR = 4.123; P = 0.039), pathological Gleason score (HR = 3.701; P = 0.004), and surgical-T3b (HR = 6.341; P < 0.001) were independently associated with time to BCR. CONCLUSION: Multiparametric MRI, when converted into a prognostic nomogram, can predict the clinical outcome in patients with PCa after prostatectomy. LEVEL OF EVIDENCE: 3 J. Magn. Reson. Imaging 2017;45:586-596.

Acute kidney damage induced by low- and iso-osmolar contrast media in rats: Comparison study with physiologic MRI and histologic-gene examination.

PURPOSE: To investigate the physiopathological effects of low- and iso-osmolar contrast media (CM) on renal function with physiologic MRI and histologic-gene examination. MATERIALS AND METHODS: Forty-eight rats underwent time-course DWI and DCE-MRI at 3.0 Tesla (T) before and 5-15 min after exposure of CM or saline (Iop.370: 370 mgI/mL iopromide; Iod.320: 320 mgI/mL iodixanol; Iod.270: 270 mgI/mL iodixanol; 4 gI/kg body weight). Intrarenal viscosity was reflected by apparent diffusion coefficient (ADC). Renal physiologies were evaluated by DCE-derived glomerular filtration rate (GFR), renal blood flow (RBF), and renal blood volume (RBV). Potential acute kidney injury (AKI) was determined by histology and the expression of kidney injury molecule 1 (Kim-1). RESULTS: Iop.370 mainly increased ADC in inner-medulla (△ADCIM : 12.3 ± 11.1%; P < 0.001). Iod.320 and Iod.270 mainly decreased ADC in outer-medulla (△ADCIM ; Iod.320: 16.8 ± 7.5%; Iod.270: 18.1 ± 9.5%; P < 0.001) and inner-medulla (△ADCIM ; Iod.320: 28.4 ± 9.3%; Iod.270: 30.3 ± 6.3%; P < 0.001). GFR, RBF and RBV were significantly decreased by Iod.320 (△GFR: 45.5 ± 24.1%; △RBF: 44.6 ± 19.0%; △RBV: 35.2 ± 10.1%; P < 0.001) and Iod.270 (33.2 ± 19.0%; 38.1 ± 15.6%; 30.1 ± 10.1%; P < 0.001), while rarely changed by Iop.370 and saline. Formation of vacuoles and increase in Kim-1 expression was prominently detected in group of Iod.320, while rarely in Iod.270 and Iop.370. CONCLUSION: Iso-osmolar iodixanol, given at high-dose, produced prominent AKI in nonhydrated rats. This renal dysfunction could be assessed noninvasively by physiologic MRI. LEVEL OF EVIDENCE: 1 J. Magn. Reson. Imaging 2017;45:291-302.

Machine learning-based analysis of MR radiomics can help to improve the diagnostic performance of PI-RADS v2 in clinically relevant prostate cancer.

OBJECTIVE: To investigate whether machine learning-based analysis of MR radiomics can help improve the performance PI-RADS v2 in clinically relevant prostate cancer (PCa). METHODS: This IRB-approved study included 54 patients with PCa undergoing multi-parametric (mp) MRI before prostatectomy. Imaging analysis was performed on 54 tumours, 47 normal peripheral (PZ) and 48 normal transitional (TZ) zone based on histological-radiological correlation. Mp-MRI was scored via PI-RADS, and quantified by measuring radiomic features. Predictive model was developed using a novel support vector machine trained with: (i) radiomics, (ii) PI-RADS scores, (iii) radiomics and PI-RADS scores. Paired comparison was made via ROC analysis. RESULTS: For PCa versus normal TZ, the model trained with radiomics had a significantly higher area under the ROC curve (Az) (0.955 [95% CI 0.923-0.976]) than PI-RADS (Az: 0.878 [0.834-0.914], p < 0.001). The Az between them was insignificant for PCa versus PZ (0.972 [0.945-0.988] vs. 0.940 [0.905-0.965], p = 0.097). When radiomics was added, performance of PI-RADS was significantly improved for PCa versus PZ (Az: 0.983 [0.960-0.995]) and PCa versus TZ (Az: 0.968 [0.940-0.985]). CONCLUSION: Machine learning analysis of MR radiomics can help improve the performance of PI-RADS in clinically relevant PCa. KEY POINTS: • Machine-based analysis of MR radiomics outperformed in TZ cancer against PI-RADS. • Adding MR radiomics significantly improved the performance of PI-RADS. • DKI-derived Dapp and Kapp were two strong markers for the diagnosis of PCa.

Diffusion Kurtosis Imaging Helps to Predict Upgrading in Biopsy-Proven Prostate Cancer With a Gleason Score of 6.

OBJECTIVE: The purpose of this study was to investigate whether diffusion kurtosis imaging (DKI) is useful for predicting upgrades in Gleason score (GS) in biopsy-proven prostate cancer with a GS of 6. MATERIALS AND METHODS: A total of 46 patients with biopsy-proven GS 6 prostate cancer, 3-T DWI results, and surgical pathologic results were retrospectively included in the study. DWI data were postprocessed with monoexponential and DK models to quantify the apparent diffusion coefficient (ADC), apparent diffusion for gaussian distribution (Dapp), and apparent kurtosis coefficient (Kapp). The volume of the lesions, prostate-specific antigen (PSA) level, and diffusion variables (ADCmin, Dappmin, Kappmax, ADCmean, Dappmean, and Kappmean) were evaluated. PSA and DKI were combined as a parameter in a logistic regression model. The utility of these parameters in predicting an upgrade in GS was analyzed with ROC regression. RESULTS: The rate of GS upgrade was 50.0% (23/46). The GS upgrade group had significantly lower ADCmin (p = 0.007), ADC mean (p = 0.003), D appmin (p < 0.001), and Dappmean (p = 0.001) values and significantly higher Kappmax (p = 0.003), Kappmean (p = 0.005), and PSA (p = 0.004) values than the group that did not have an upgrade. Among single parameters, Kappmax had the highest ROC AUC value (0.819, p < 0.05), and among all the parameters and models, PSA-Kappmax had the highest AUC (0.868, p < 0.05) and Youden index (0.6522). CONCLUSION: The results showed that DKI may help in prediction of GS upgrade in biopsy-proven GS 6 prostate cancer. The comprehensive consideration of DKI and PSA may be a promising approach to predicting GS upgrade.

New RESOLVE-Based Diffusional Kurtosis Imaging in MRI-Visible Prostate Cancer: Effect of Reduced b Value on Image Quality and Diagnostic Effectiveness.

OBJECTIVE: The purpose of this article was to investigate whether a new readout segmentation of long variable echo-trains (RESOLVE)-based diffusional kurtosis imaging (DKI) with reduced b value technique can affect image quality and diagnostic effectiveness in MRI-visible prostate cancer (PCA). SUBJECTS AND METHODS: Prostatic RESOLVE DKI (0-1400 s/mm2) was prospectively performed for 12 volunteers. The optimal protocol was then performed in 108 MRI-visible PCAs to determine whether it can compete against a preferred b-value set (0-2000 s/mm(2)) regarding image quality and diagnostic effectiveness. Images were interpreted by two independent radiologists using the prostate imaging reporting and data system (PI-RADS). Readers' concordance and diagnostic effectiveness were tested with the Fleiss kappa and area under the ROC curve (Az) analyses. RESULTS: A b value of 1400 s/mm(2) generated a larger apparent diffusion coefficient of gaussian distribution (Dapp) (1.35 ± 0.31 vs 1.30 ± 0.30 mm(2)/s; p < 0.001) and apparent kurtosis coefficient (Kapp) (1.11 ± 0.26 vs 1.00 ± 0.21; p < 0.001) in PCA than did a b value of 2000 s/mm(2). Interreader agreement using PI-RADS was relatively low when Dapp and Kapp maps were excluded from image interpretations (κ = 0.39-0.41 vs κ = 0.66-0.68 with Dapp and Kapp maps). Interreader agreement in staging PCA was relatively high (κ > 0.80) and was not influenced by reducing the b value. The power of Dapp and Kapp to differentiate PCA from normal tissue (Az = 0.97-0.98), tissue with a Gleason score less than or equal to 3 + 4 from tissue with a Gleason score greater than 3 + 4 (Az = 0.77-0.82), and PCA stage lower than pT3 from stage pT3 and higher PCA (Az = 0.70-0.75) was not significantly degraded by reducing the b value. CONCLUSION: We found that b values significantly influenced image quality, PI-RADS score, and DKI outputs but did not degrade the diagnostic effectiveness of DKI parameters to detect and classify PCA.

Enzalutamide and olaparib synergistically suppress castration-resistant prostate cancer progression by promoting apoptosis through inhibiting nonhomologous end joining pathway.

Recent studies revealed the relationship among homologous recombination repair (HRR), androgen receptor (AR), and poly(adenosine diphosphate-ribose) polymerase (PARP); however, the synergy between anti-androgen enzalutamide (ENZ) and PARP inhibitor olaparib (OLA) remains unclear. Here, we showed that the synergistic effect of ENZ and OLA significantly reduced proliferation and induced apoptosis in AR-positive prostate cancer cell lines. Next-generation sequencing followed by Gene Ontology and Kyoto Encyclopedia of Genes and Genomes enrichment analyses revealed the significant effects of ENZ plus OLA on nonhomologous end joining (NHEJ) and apoptosis pathways. ENZ combined with OLA synergistically inhibited the NHEJ pathway by repressing DNA-dependent protein kinase catalytic subunit (DNA-PKcs) and X-ray repair cross complementing 4 (XRCC4). Moreover, our data showed that ENZ could enhance the response of prostate cancer cells to the combination therapy by reversing the anti-apoptotic effect of OLA through the downregulation of anti-apoptotic gene insulin-like growth factor 1 receptor ( IGF1R ) and the upregulation of pro-apoptotic gene death-associated protein kinase 1 ( DAPK1 ). Collectively, our results suggested that ENZ combined with OLA can promote prostate cancer cell apoptosis by multiple pathways other than inducing HRR defects, providing evidence for the combined use of ENZ and OLA in prostate cancer regardless of HRR gene mutation status.

A clinical available decision support scheme for optimizing prostate biopsy based on mpMRI.

BACKGROUND: Combined MRI/Ultrasound fusion targeted biopsy (TBx) and systematic biopsy (SBx) results in better prostate cancer (PCa) detection relative to either TBx or SBx alone, while at the cost of higher number of biopsy cores and greater detection of clinically insignificant PCa. We therefore developed and evaluated a simple decision support scheme for optimizing prostate biopsy based on multiparametric (mp) MRI assessment. METHODS: Total 229 patients with suspicion of PCa underwent mpMRI before combined TBx/SBx were retrospectively included. Impacts of MRI characteristics such as Prostate Imaging-Reporting and Data System (PI-RADS) score, lesion size, zonal origination, and location on biopsy performance were evaluated. A clinically available decision support scheme relying on mpMRI assessment was subsequently developed as a triage test to optimize prostate biopsy process. Cost (downgrade, upgrade, and biopsy core)-to-Effectiveness (detection rate) was systemically compared. RESULTS: TBx achieved comparable detection rate to combined TBx/SBx in diagnosis of PCa and clinically significant PCa (csPCa) (PCa, 59% [135/229] vs 60.7% [139/229]; csPCa, 45.9% [105/229] vs 47.2% [108/229]; p-values > 0.05) and outperformed SBx (PCa, 42.4% [97/229]; csPCa, 28.4% [65/229]; p-values < 0.001). Specially, in personalized decision support scheme, TBx accurately detected all PCa (72.5% [74/102]) in PI-RADS 5 and larger (≥1 cm) PI-RADS 3-4 observations, adding SBx to TBx only resulted in 1.4% (1/74) upgrading csPCa. For smaller (<1 cm) PI-RADS 3-4 lesions, combined TBx/SBx resulted in relatively higher detection rate (51.2% [65/127] vs 48.0% [61/127]) and lower upgrading rate (30.6% [15/49] vs 36.7% [18/49]) than TBx. CONCLUSIONS: The benefit of SBx added to TBx was largely restricted to smaller PI-RADS score 3-4 lesions. Using our personalized strategy of solo TBx for PI-RADS 5 and larger (≥1 cm) PI-RADS score 3-4 lesions would avoid excess SBx in 44.5% (102/229) of all biopsy-naïve patients without compromising detection rate.

Integration of clinicopathologic identification and deep transferrable image feature representation improves predictions of lymph node metastasis in prostate cancer.

BACKGROUND: Accurate identification of pelvic lymph node metastasis (PLNM) in patients with prostate cancer (PCa) is crucial for determining appropriate treatment options. Here, we built a PLNM-Risk calculator to obtain a precisely informed decision about whether to perform extended pelvic lymph node dissection (ePLND). METHODS: The PLNM-Risk calculator was developed in 280 patients and verified internally in 71 patients and externally in 50 patients by integrating a set of radiologists' interpretations, clinicopathological factors and newly refined imaging indicators from MR images with radiomics machine learning and deep transfer learning algorithms. Its clinical applicability was compared with Briganti and Memorial Sloan Kettering Cancer Center (MSKCC) nomograms. FINDINGS: The PLNM-Risk achieved good diagnostic discrimination with areas under the receiver operating characteristic curve (AUCs) of 0.93 (95% CI, 0.90-0.96), 0.92 (95% CI, 0.84-0.97) and 0.76 (95% CI, 0.62-0.87) in the training/validation, internal test and external test cohorts, respectively. If the number of ePLNDs missed was controlled at < 2%, PLNM-Risk provided both a higher number of ePLNDs spared (PLNM-Risk 59.6% vs MSKCC 44.9% vs Briganti 38.9%) and a lower number of false positives (PLNM-Risk 59.3% vs MSKCC 70.1% and Briganti 72.7%). In follow-up, patients stratified by the PLNM-Risk calculator showed significantly different biochemical recurrence rates after surgery. INTERPRETATION: The PLNM-Risk calculator offers a noninvasive clinical biomarker to predict PLNM for patients with PCa. It shows improved accuracy of diagnosis support and reduced overtreatment burdens for patients with findings suggestive of PCa. FUNDING: This work was supported by the Key Research and Development Program of Jiangsu Province (BE2017756) and the Suzhou Science and Technology Bureau-Science and Technology Demonstration Project (SS201808).

A radiomics machine learning-based redefining score robustly identifies clinically significant prostate cancer in equivocal PI-RADS score 3 lesions.

PURPOSE: PI-RADS score 3 is recognized as equivocal likelihood of clinically significant prostate cancer (csPCa) occurrence. We aimed to develop a Radiomics machine learning (RML)-based redefining score to screen out csPCa in equivocal PI-RADS score 3 category. METHODS: Total of 263 patients with the dominant index lesion scored PI-RADS 3 who underwent biopsy and/or follow-up formed the primary cohort. One-step RML (RML-i) model integrated radiomic features of T2WI, DWI, and ADC images all together, and two-step RML (RML-ii) model integrated the three independent radiomic signatures from T2WI (T2WIRS), DWI (DWIRS), and ADC (ADCRS) separately into a regression model. The two RML models, as well as T2WIRS, DWIRS, and ADCRS, were compared using the receiver operating characteristic-derived area under the curve (AUC), calibration plot, and decision-curve analysis (DCA). Two radiologists were asked to give a subjective binary assessment, and Cohen's kappa statistics were calculated. RESULTS: A total of 59/263 (22.4%) csPCa were identified. Inter-reader agreement was moderate (Kappa = 0.435). The AUC of RML-i (0.89; 95% CI 0.88-0.90) is higher (p = 0.003) than that of RML-ii (0.87; 95% CI 0.86-0.88). The DCA demonstrated that the RML-i and RML-ii significantly improved risk prediction at threshold probabilities of csPCa at 20% to 80% compared with doing-none or doing-all by PI-RADS score 3 or stratifying by separated DWIRS, ADCRS, or T2WIRS. CONCLUSION: Our RML models have the potential to predict csPCa in PI-RADS score 3 lesions, thus can inform the decision making process of biopsy.

An imaging-based approach predicts clinical outcomes in prostate cancer through a novel support vector machine classification.

Preoperatively predict the probability of Prostate cancer (PCa) biochemical recurrence (BCR) is of definite clinical relevance. The purpose of this study was to develop an imaging-based approach in the prediction of 3-years BCR through a novel support vector machine (SVM) classification. We collected clinicopathologic and MR imaging datasets in 205 patients pathologically confirmed PCa after radical prostatectomy. Univariable and multivariable analyses were used to assess the association between MR findings and 3-years BCR, and modeled the imaging variables and follow-up data to predict 3-year PCa BCR using SVM analysis. The performance of SVM was compared with conventional Logistic regression (LR) and D'Amico risk stratification scheme by area under the receiver operating characteristic curve (Az) analysis. We found that SVM had significantly higher Az (0.959 vs. 0.886; p = 0.007), sensitivity (93.3% vs. 83.3%; p = 0.025), specificity (91.7% vs. 77.2%; p = 0.009) and accuracy (92.2% vs. 79.0%; p = 0.006) than LR analysis. Performance of popularized D'Amico scheme was effectively improved by adding MRI-derived variables (Az: 0.970 vs. 0.859, p < 0.001; sensitivity: 91.7% vs. 86.7%, p = 0.031; specificity: 94.5% vs. 78.6%, p = 0.001; and accuracy: 93.7% vs. 81.0%, p = 0.007). Additionally, beside pathological Gleason score (hazard ratio [HR] = 1.560, p = 0.008), surgical-T3b (HR = 4.525, p < 0.001) and positive surgical margin (HR = 1.314, p = 0.007), apparent diffusion coefficient (HR = 0.149, p = 0.035) was the only independent imaging predictor of time to PSA failure. Therefore, We concluded that imaging-based approach using SVM was superior to LR analysis in predicting PCa outcome. Adding MR variables improved the performance of D'Amico scheme.