A Novel Artificial Intelligence-Powered Method for Prediction of Early Recurrence of Prostate Cancer After Prostatectomy and Cancer Drivers.

PURPOSE: To develop a novel artificial intelligence (AI)-powered method for the prediction of prostate cancer (PCa) early recurrence and identification of driver regions in PCa of all Gleason Grade Group (GGG). MATERIALS AND METHODS: Deep convolutional neural networks were used to develop the AI model. The AI model was trained on The Cancer Genome Atlas Prostatic Adenocarcinoma (TCGA-PRAD) whole slide images (WSI) and data set (n = 243) to predict 3-year biochemical recurrence after radical prostatectomy (RP) and was subsequently validated on WSI from patients with PCa (n = 173) from the University of Wisconsin-Madison. RESULTS: Our AI-powered platform can extract visual and subvisual morphologic features from WSI to identify driver regions predictive of early recurrence of PCa (regions of interest [ROIs]) after RP. The ROIs were ranked with AI-morphometric scores, which were prognostic for 3-year biochemical recurrence (area under the curve [AUC], 0.78), which is significantly better than the GGG overall (AUC, 0.62). The AI-morphometric scores also showed high accuracy in the prediction of recurrence for low- or intermediate-risk PCa-AUC, 0.76, 0.84, and 0.81 for GGG1, GGG2, and GGG3, respectively. These patients could benefit the most from timely adjuvant therapy after RP. The predictive value of the high-scored ROIs was validated by known PCa biomarkers studied. With this focused biomarker analysis, a potentially new STING pathway-related PCa biomarker-TMEM173-was identified. CONCLUSION: Our study introduces a novel approach for identifying patients with PCa at risk for early recurrence regardless of their GGG status and for identifying cancer drivers for focused evolution-aware novel biomarker discovery.

Combined mpMRI/US fusion targeted and concurrent standard biopsies in the detection of prostate cancer: a retrospective study.

In this retrospective study we compared the PCa detection rates between combined (combined MRI/US fusion targeted biopsy with concurrent standard biopsy) and standard systemic, combined and targeted (component), and targeted (component) and concurrent standard (component) biopsies. DESIGN: Two cohorts, totaling 735 cases, were selected from the University of Wisconsin Pathology archive. 390 cases (cohort 1) were combined biopsies from 2017-2020 and 345 cases (cohort 2) were part of the standard US-guided systematic biopsies from the same period. PCa was stratified into three categories: low, intermediate, and high risks. RESULTS: We found that combined biopsy was significantly better than the standard biopsy in detection of PCa (65.4% vs. 51.6%, P<0.01) and intermediate-risk PCa (18.7% vs. 10.4%, P=0.05) but only slightly better at detecting high-risk PCa (26.7% vs. 23.5%, P=0.32). Further examining the biopsy results in cohort 1, we found that combined biopsy was superior to targeted biopsy (65.4% vs. 56.9%, P=0.02) or concurrent standard biopsy (65.4% vs. 52.1%, P=0.0002) in PCa detection. Combined biopsy detected significantly more high-risk PCa than concurrent standard biopsy (26.7% vs. 17.4, P=0.002), but the difference in detecting high-risk PCa between combined and targeted biopsies was not significant (26.7% vs. 22.1%, P=0.133). Similarly, the differences in detecting PCa and high-risk PCa between targeted and concurrent standard biopsies were not significant (56.9% vs. 52.1%, P=0.172 and 22.1% vs. 17.4, P=0.133, respectively). Both targeted and concurrent standard biopsies missed PCa of each risk level. CONCLUSION: Combined MRI/US fusion targeted plus standard prostate biopsy is a superior technique for the detection of PCa and clinically significant PCa.

Development and Validation of an Artificial Intelligence-Powered Platform for Prostate Cancer Grading and Quantification.

Importance: The Gleason grading system has been the most reliable tool for the prognosis of prostate cancer since its development. However, its clinical application remains limited by interobserver variability in grading and quantification, which has negative consequences for risk assessment and clinical management of prostate cancer. Objective: To examine the impact of an artificial intelligence (AI)-assisted approach to prostate cancer grading and quantification. Design, Setting, and Participants: This diagnostic study was conducted at the University of Wisconsin-Madison from August 2, 2017, to December 30, 2019. The study chronologically selected 589 men with biopsy-confirmed prostate cancer who received care in the University of Wisconsin Health System between January 1, 2005, and February 28, 2017. A total of 1000 biopsy slides (1 or 2 slides per patient) were selected and scanned to create digital whole-slide images, which were used to develop and validate a deep convolutional neural network-based AI-powered platform. The whole-slide images were divided into a training set (n = 838) and validation set (n = 162). Three experienced academic urological pathologists (W.H., K.A.I., and R.H., hereinafter referred to as pathologists 1, 2, and 3, respectively) were involved in the validation. Data were collected between December 29, 2018, and December 20, 2019, and analyzed from January 4, 2020, to March 1, 2021. Main Outcomes and Measures: Accuracy of prostate cancer detection by the AI-powered platform and comparison of prostate cancer grading and quantification performed by the 3 pathologists using manual vs AI-assisted methods. Results: Among 589 men with biopsy slides, the mean (SD) age was 63.8 (8.2) years, the mean (SD) prebiopsy prostate-specific antigen level was 10.2 (16.2) ng/mL, and the mean (SD) total cancer volume was 15.4% (20.1%). The AI system was able to distinguish prostate cancer from benign prostatic epithelium and stroma with high accuracy at the patch-pixel level, with an area under the receiver operating characteristic curve of 0.92 (95% CI, 0.88-0.95). The AI system achieved almost perfect agreement with the training pathologist (pathologist 1) in detecting prostate cancer at the patch-pixel level (weighted κ = 0.97; asymptotic 95% CI, 0.96-0.98) and in grading prostate cancer at the slide level (weighted κ = 0.98; asymptotic 95% CI, 0.96-1.00). Use of the AI-assisted method was associated with significant improvements in the concordance of prostate cancer grading and quantification between the 3 pathologists (eg, pathologists 1 and 2: 90.1% agreement using AI-assisted method vs 84.0% agreement using manual method; P < .001) and significantly higher weighted κ values for all pathologists (eg, pathologists 2 and 3: weighted κ = 0.92 [asymptotic 95% CI, 0.90-0.94] for AI-assisted method vs 0.76 [asymptotic 95% CI, 0.71-0.80] for manual method; P < .001) compared with the manual method. Conclusions and Relevance: In this diagnostic study, an AI-powered platform was able to detect, grade, and quantify prostate cancer with high accuracy and efficiency and was associated with significant reductions in interobserver variability. These results suggest that an AI-powered platform could potentially transform histopathological evaluation and improve risk stratification and clinical management of prostate cancer.

Comparison of two commonly used methods in measurement of cancer volume in prostate biopsy.

Currently, cancer volume in prostate biopsy samples is commonly calculated as linear length of carcinoma divided by total core length and reported as percentage involvement. The measurement of the linear length of carcinoma can be problematic particularly when there are two or more separate foci of carcinoma in a single core. There are two most methods commonly used by practicing pathologists. One method is to measure the exact linear extent of each discrete carcinoma foci in millimeters and then add up the linear length (the exact method, E method). The other method is to measure the core length encompassing all carcinoma foci including the intervening benign prostate tissue (glands and/or stroma) (the scattered method, S method). In this study, we used digital pathology to compare the site-specific and overall cancer volumes measured with the E and S methods and analyzed their correlation with the cancer volume in the corresponding prostatectomy specimens. Our results showed that prostate-cancer volumes estimated with both E and S methods on biopsy samples positively correlate with cancer volume at radical prostatectomy. However, the cancer volumes measured with both E and S methods in the majority of biopsy samples were significantly larger than that in prostatectomy (P<0.001). The E method more closely predicts the cancer volume compared to the S method. The overall cancer volume is better than site-specific cancer volume at biopsy in predicting cancer volume at prostatectomy.