External validation of an artificial intelligence model for Gleason grading of prostate cancer on prostatectomy specimens.

OBJECTIVES: To externally validate the performance of the DeepDx Prostate artificial intelligence (AI) algorithm (Deep Bio Inc., Seoul, South Korea) for Gleason grading on whole-mount prostate histopathology, considering potential variations observed when applying AI models trained on biopsy samples to radical prostatectomy (RP) specimens due to inherent differences in tissue representation and sample size. MATERIALS AND METHODS: The commercially available DeepDx Prostate AI algorithm is an automated Gleason grading system that was previously trained using 1133 prostate core biopsy images and validated on 700 biopsy images from two institutions. We assessed the AI algorithm's performance, which outputs Gleason patterns (3, 4, or 5), on 500 1-mm2 tiles created from 150 whole-mount RP specimens from a third institution. These patterns were then grouped into grade groups (GGs) for comparison with expert pathologist assessments. The reference standard was the International Society of Urological Pathology GG as established by two experienced uropathologists with a third expert to adjudicate discordant cases. We defined the main metric as the agreement with the reference standard, using Cohen's kappa. RESULTS: The agreement between the two experienced pathologists in determining GGs at the tile level had a quadratically weighted Cohen's kappa of 0.94. The agreement between the AI algorithm and the reference standard in differentiating cancerous vs non-cancerous tissue had an unweighted Cohen's kappa of 0.91. Additionally, the AI algorithm's agreement with the reference standard in classifying tiles into GGs had a quadratically weighted Cohen's kappa of 0.89. In distinguishing cancerous vs non-cancerous tissue, the AI algorithm achieved a sensitivity of 0.997 and specificity of 0.88; in classifying GG ≥2 vs GG 1 and non-cancerous tissue, it demonstrated a sensitivity of 0.98 and specificity of 0.85. CONCLUSION: The DeepDx Prostate AI algorithm had excellent agreement with expert uropathologists and performance in cancer identification and grading on RP specimens, despite being trained on biopsy specimens from an entirely different patient population.

Stockholm3 in a Multiethnic Cohort for Prostate Cancer Detection (SEPTA): A Prospective Multicentered Trial.

PURPOSE: Asian, Black, and Hispanic men are underrepresented in prostate cancer (PCa) clinical trials. Few novel prostate cancer biomarkers have been validated in diverse cohorts. We aimed to determine if Stockholm3 can improve prostate cancer detection in a diverse cohort. METHODS: An observational prospective multicentered (17 sites) clinical trial (2019-2023), supplemented by prospectively recruited participants (2008-2020) in a urology clinic setting included men with suspicion of PCa and underwent prostate biopsy. Before biopsy, sample was collected for measurement of the Stockholm3 risk score. Parameters include prostate-specific antigen (PSA), free PSA, KLK2, GDF15, PSP94, germline risk (single-nucleotide polymorphisms), age, family history, and previous negative biopsy. The primary endpoint was detection of International Society of Urological Pathology (ISUP) Grade ≥2 cancer (clinically significant PCa, csPC). The two primary aims were to (1) demonstrate noninferior sensitivity (0.8 lower bound 95% CI noninferiority margin) in detecting csPC using Stockholm3 compared with PSA (relative sensitivity) and (2) demonstrate superior specificity by reducing biopsies with benign results or low-grade cancers (relative specificity). RESULTS: A total of 2,129 biopsied participants were included: Asian (16%, 350), Black or African American (Black; 24%, 505), Hispanic or Latino and White (Hispanic; 14%, 305), and non-Hispanic or non-Latino and White (White; 46%, 969). Overall, Stockholm3 showed noninferior sensitivity compared with PSA ≥4 ng/mL (relative sensitivity: 0.95 [95% CI, 0.92 to 0.99]) and nearly three times higher specificity (relative specificity: 2.91 [95% CI, 2.63 to 3.22]). Results were consistent across racial and ethnic subgroups: noninferior sensitivity (0.91-0.98) and superior specificity (2.51-4.70). Compared with PSA, Stockholm3 could reduce benign and ISUP 1 biopsies by 45% overall and between 42% and 52% across racial and ethnic subgroups. CONCLUSION: In a substantially diverse population, Stockholm3 significantly reduces unnecessary prostate biopsies while maintaining a similar sensitivity to PSA in detecting csPC.

Patient Preferences for Benefit and Risk Associated With High Intensity Focused Ultrasound for the Ablation of Prostate Tissue in Men With Localized Prostate Cancer.

INTRODUCTION: Food and Drug Administration must make decisions about emerging high intensity focused ultrasound (HIFU) devices that may lack relevant clinical oncologic data but present with known side effects. This study aims to capture patients' perspective by quantifying their preferences regarding the available benefit and important side effects associated with HIFU for localized prostate cancer. MATERIALS AND METHODS: Preferences for HIFU outcomes were examined using a discrete choice experiment survey. Participants were asked to choose a preferred treatment option in 9 choice questions. Each included a pair of hypothetical treatment profiles that have similar attributes/outcomes with varying levels. Outcomes included prostate biopsy outcome and treatment-related risks of erectile dysfunction (ED) and urinary incontinence (UI). We calculated the maximum risk of side effect patients were willing to tolerate in exchange for increased benefit. Preferences were further explored via clinical and demographic data. RESULTS: About 223 subjects with a mean age of 64.8 years completed the survey. Respondents were willing to accept a 1.51%-point increase in new ED risk for a 1%-point increase in favorable biopsy outcome. They were also willing to accept a 0.93%-point increase in new UI risk for a 1%-point increase in biopsy outcome. Subjects who perceived their cancer to be more aggressive had higher risk tolerance for UI. Younger men were willing to tolerate less ED risk than older men. Respondents with greater than college level of education had a lower risk tolerance for ED or UI. CONCLUSIONS: Results may inform development and regulatory evaluation for future HIFU ablation devices by providing supplemental information from the patient perspective.

RAPHIA: A deep learning pipeline for the registration of MRI and whole-mount histopathology images of the prostate.

Image registration can map the ground truth extent of prostate cancer from histopathology images onto MRI, facilitating the development of machine learning methods for early prostate cancer detection. Here, we present RAdiology PatHology Image Alignment (RAPHIA), an end-to-end pipeline for efficient and accurate registration of MRI and histopathology images. RAPHIA automates several time-consuming manual steps in existing approaches including prostate segmentation, estimation of the rotation angle and horizontal flipping in histopathology images, and estimation of MRI-histopathology slice correspondences. By utilizing deep learning registration networks, RAPHIA substantially reduces computational time. Furthermore, RAPHIA obviates the need for a multimodal image similarity metric by transferring histopathology image representations to MRI image representations and vice versa. With the assistance of RAPHIA, novice users achieved expert-level performance, and their mean error in estimating histopathology rotation angle was reduced by 51% (12 degrees vs 8 degrees), their mean accuracy of estimating histopathology flipping was increased by 5% (95.3% vs 100%), and their mean error in estimating MRI-histopathology slice correspondences was reduced by 45% (1.12 slices vs 0.62 slices). When compared to a recent conventional registration approach and a deep learning registration approach, RAPHIA achieved better mapping of histopathology cancer labels, with an improved mean Dice coefficient of cancer regions outlined on MRI and the deformed histopathology (0.44 vs 0.48 vs 0.50), and a reduced mean per-case processing time (51 vs 11 vs 4.5 min). The improved performance by RAPHIA allows efficient processing of large datasets for the development of machine learning models for prostate cancer detection on MRI. Our code is publicly available at: https://github.com/pimed/RAPHIA.

Prediction and Mapping of Intraprostatic Tumor Extent with Artificial Intelligence.

Background: Magnetic resonance imaging (MRI) underestimation of prostate cancer extent complicates the definition of focal treatment margins. Objective: To validate focal treatment margins produced by an artificial intelligence (AI) model. Design setting and participants: Testing was conducted retrospectively in an independent dataset of 50 consecutive patients who had radical prostatectomy for intermediate-risk cancer. An AI deep learning model incorporated multimodal imaging and biopsy data to produce three-dimensional cancer estimation maps and margins. AI margins were compared with conventional MRI regions of interest (ROIs), 10-mm margins around ROIs, and hemigland margins. The AI model also furnished predictions of negative surgical margin probability, which were assessed for accuracy. Outcome measurements and statistical analysis: Comparing AI with conventional margins, sensitivity was evaluated using Wilcoxon signed-rank tests and negative margin rates using chi-square tests. Predicted versus observed negative margin probability was assessed using linear regression. Clinically significant prostate cancer (International Society of Urological Pathology grade ≥2) delineated on whole-mount histopathology served as ground truth. Results and limitations: The mean sensitivity for cancer-bearing voxels was higher for AI margins (97%) than for conventional ROIs (37%, p < 0.001), 10-mm ROI margins (93%, p = 0.24), and hemigland margins (94%, p < 0.001). For index lesions, AI margins were more often negative (90%) than conventional ROIs (0%, p < 0.001), 10-mm ROI margins (82%, p = 0.24), and hemigland margins (66%, p = 0.004). Predicted and observed negative margin probabilities were strongly correlated (R2 = 0.98, median error = 4%). Limitations include a validation dataset derived from a single institution's prostatectomy population. Conclusions: The AI model was accurate and effective in an independent test set. This approach could improve and standardize treatment margin definition, potentially reducing cancer recurrence rates. Furthermore, an accurate assessment of negative margin probability could facilitate informed decision-making for patients and physicians. Patient summary: Artificial intelligence was used to predict the extent of tumors in surgically removed prostate specimens. It predicted tumor margins more accurately than conventional methods.

Distinguishing Renal Cell Carcinoma From Normal Kidney Tissue Using Mass Spectrometry Imaging Combined With Machine Learning.

PURPOSE: Accurately distinguishing renal cell carcinoma (RCC) from normal kidney tissue is critical for identifying positive surgical margins (PSMs) during partial and radical nephrectomy, which remains the primary intervention for localized RCC. Techniques that detect PSM with higher accuracy and faster turnaround time than intraoperative frozen section (IFS) analysis can help decrease reoperation rates, relieve patient anxiety and costs, and potentially improve patient outcomes. MATERIALS AND METHODS: Here, we extended our combined desorption electrospray ionization mass spectrometry imaging (DESI-MSI) and machine learning methodology to identify metabolite and lipid species from tissue surfaces that can distinguish normal tissues from clear cell RCC (ccRCC), papillary RCC (pRCC), and chromophobe RCC (chRCC) tissues. RESULTS: From 24 normal and 40 renal cancer (23 ccRCC, 13 pRCC, and 4 chRCC) tissues, we developed a multinomial lasso classifier that selects 281 total analytes from over 27,000 detected molecular species that distinguishes all histological subtypes of RCC from normal kidney tissues with 84.5% accuracy. On the basis of independent test data reflecting distinct patient populations, the classifier achieves 85.4% and 91.2% accuracy on a Stanford test set (20 normal and 28 RCC) and a Baylor-UT Austin test set (16 normal and 41 RCC), respectively. The majority of the model's selected features show consistent trends across data sets affirming its stable performance, where the suppression of arachidonic acid metabolism is identified as a shared molecular feature of ccRCC and pRCC. CONCLUSION: Together, these results indicate that signatures derived from DESI-MSI combined with machine learning may be used to rapidly determine surgical margin status with accuracies that meet or exceed those reported for IFS.

NCCN Guidelines® Insights: Prostate Cancer Early Detection, Version 1.2023.

The NCCN Guidelines for Prostate Cancer Early Detection provide recommendations for individuals with a prostate who opt to participate in an early detection program after receiving the appropriate counseling on the pros and cons. These NCCN Guidelines Insights provide a summary of recent updates to the NCCN Guidelines with regard to the testing protocol, use of multiparametric MRI, and management of negative biopsy results to optimize the detection of clinically significant prostate cancer and minimize the detection of indolent disease.

A Pilot Study of 68Ga-PSMA11 and 68Ga-RM2 PET/MRI for Biopsy Guidance in Patients with Suspected Prostate Cancer.

Targeting of lesions seen on multiparametric MRI (mpMRI) improves prostate cancer (PC) detection at biopsy. However, 20%-65% of highly suspicious lesions on mpMRI (PI-RADS [Prostate Imaging-Reporting and Data System] 4 or 5) are false-positives (FPs), while 5%-10% of clinically significant PC (csPC) are missed. Prostate-specific membrane antigen (PSMA) and gastrin-releasing peptide receptors (GRPRs) are both overexpressed in PC. We therefore aimed to evaluate the potential of 68Ga-PSMA11 and 68Ga-RM2 PET/MRI for biopsy guidance in patients with suspected PC. Methods: A highly selective cohort of 13 men, aged 58.0 ± 7.1 y, with suspected PC (persistently high prostate-specific antigen [PSA] and PSA density) but negative or equivocal mpMRI results or negative biopsy were prospectively enrolled to undergo 68Ga-PSMA11 and 68Ga-RM2 PET/MRI. PET/MRI included whole-body and dedicated pelvic imaging after a delay of 20 min. All patients had targeted biopsy of any lesions seen on PET followed by standard 12-core biopsy. The SUVmax of suspected PC lesions was collected and compared with gold standard biopsy. Results: PSA and PSA density at enrollment were 9.8 ± 6.0 (range, 1.5-25.5) ng/mL and 0.20 ± 0.18 (range, 0.06-0.68) ng/mL2, respectively. Standardized systematic biopsy revealed a total of 14 PCs in 8 participants: 7 were csPC and 7 were nonclinically significant PC (ncsPC). 68Ga-PSMA11 identified 25 lesions, of which 11 (44%) were true-positive (TP) (5 csPC). 68Ga-RM2 showed 27 lesions, of which 14 (52%) were TP, identifying all 7 csPC and also 7 ncsPC. There were 17 concordant lesions in 11 patients versus 14 discordant lesions in 7 patients between 68Ga-PSMA11 and 68Ga-RM2 PET. Incongruent lesions had the highest rate of FP (12 FP vs. 2 TP). SUVmax was significantly higher for TP than FP lesions in delayed pelvic imaging for 68Ga-PSMA11 (6.49 ± 4.14 vs. 4.05 ± 1.55, P = 0.023) but not for whole-body images, nor for 68Ga-RM2. Conclusion: Our results show that 68Ga-PSMA11 and 68Ga-RM2 PET/MRI are feasible for biopsy guidance in suspected PC. Both radiopharmaceuticals detected additional clinically significant cancers not seen on mpMRI in this selective cohort. 68Ga-RM2 PET/MRI identified all csPC confirmed at biopsy.

Learn2Reg: Comprehensive Multi-Task Medical Image Registration Challenge, Dataset and Evaluation in the Era of Deep Learning.

Image registration is a fundamental medical image analysis task, and a wide variety of approaches have been proposed. However, only a few studies have comprehensively compared medical image registration approaches on a wide range of clinically relevant tasks. This limits the development of registration methods, the adoption of research advances into practice, and a fair benchmark across competing approaches. The Learn2Reg challenge addresses these limitations by providing a multi-task medical image registration data set for comprehensive characterisation of deformable registration algorithms. A continuous evaluation will be possible at https://learn2reg.grand-challenge.org. Learn2Reg covers a wide range of anatomies (brain, abdomen, and thorax), modalities (ultrasound, CT, MR), availability of annotations, as well as intra- and inter-patient registration evaluation. We established an easily accessible framework for training and validation of 3D registration methods, which enabled the compilation of results of over 65 individual method submissions from more than 20 unique teams. We used a complementary set of metrics, including robustness, accuracy, plausibility, and runtime, enabling unique insight into the current state-of-the-art of medical image registration. This paper describes datasets, tasks, evaluation methods and results of the challenge, as well as results of further analysis of transferability to new datasets, the importance of label supervision, and resulting bias. While no single approach worked best across all tasks, many methodological aspects could be identified that push the performance of medical image registration to new state-of-the-art performance. Furthermore, we demystified the common belief that conventional registration methods have to be much slower than deep-learning-based methods.

A Pilot Study of 68Ga-PSMA11 and 68Ga-RM2 PET/MRI for Evaluation of Prostate Cancer Response to High-Intensity Focused Ultrasound Therapy.

Focal therapy for localized prostate cancer (PC) using high-intensity focused ultrasound (HIFU) is gaining in popularity as it is noninvasive and associated with fewer side effects than standard whole-gland treatments. However, better methods to evaluate response to HIFU ablation are an unmet need. Prostate-specific membrane antigen (PSMA) and gastrin-releasing peptide receptors are both overexpressed in PC. In this study, we evaluated a novel approach of using both 68Ga-RM2 and 68Ga-PSMA11 PET/MRI in each patient before and after HIFU to assess the accuracy of target tumor localization and response to treatment. Methods: Fourteen men, 64.5 ± 8.0 y old (range, 48-78 y), with newly diagnosed PC were prospectively enrolled. Before HIFU, the patients underwent prostate biopsy, multiparametric MRI, 68Ga-PSMA11, and 68Ga-RM2 PET/MRI. Response to treatment was assessed at a minimum of 6 mo after HIFU with prostate biopsy (n = 13), as well as 68Ga-PSMA11 and 68Ga-RM2 PET/MRI (n = 14). The SUVmax and SUVpeak of known or suspected PC lesions were collected. Results: Pre-HIFU biopsy revealed 18 cancers, of which 14 were clinically significant (Gleason score ≥ 3 + 4). Multiparametric MRI identified 18 lesions; 14 of them were at least score 4 in the Prostate Imaging-Reporting and Data System. 68Ga-PSMA11 and 68Ga-RM2 PET/MRI each showed 23 positive intraprostatic lesions; 21 were congruent in 13 patients, and 5 were incongruent in 5 patients. Before HIFU, 68Ga-PSMA11 identified all target tumors, whereas 68Ga-RM2 PET/MRI missed 2 tumors. After HIFU, 68Ga-RM2 and 68Ga-PSMA11 PET/MRI both identified clinically significant residual disease in 1 patient. Three significant ipsilateral recurrent lesions were identified, whereas 1 was missed by 68Ga-PSMA11. The pretreatment level of prostate-specific antigen decreased significantly after HIFU, by 66%. Concordantly, the pretreatment SUVmax decreased significantly after HIFU for 68Ga-PSMA11 (P = 0.001) and 68Ga-RM2 (P = 0.005). Conclusion: This pilot study showed that 68Ga-PSMA11 and 68Ga-RM2 PET/MRI identified the target tumor for HIFU in 100% and 86% of cases, respectively, and accurately verified response to treatment. PET may be a useful tool in the guidance and monitoring of treatment success in patients receiving focal therapy for PC. These preliminary findings warrant larger studies for validation.

The Association of Tissue Change and Treatment Success During High-intensity Focused Ultrasound Focal Therapy for Prostate Cancer.

BACKGROUND: Tissue preservation strategies have been increasingly used for the management of localized prostate cancer. Focal ablation using ultrasound-guided high-intensity focused ultrasound (HIFU) has demonstrated promising short and medium-term oncological outcomes. Advancements in HIFU therapy such as the introduction of tissue change monitoring (TCM) aim to further improve treatment efficacy. OBJECTIVE: To evaluate the association between intraoperative TCM during HIFU focal therapy for localized prostate cancer and oncological outcomes 12 mo afterward. DESIGN, SETTING, AND PARTICIPANTS: Seventy consecutive men at a single institution with prostate cancer were prospectively enrolled. Men with prior treatment, metastases, or pelvic radiation were excluded to obtain a final cohort of 55 men. INTERVENTION: All men underwent HIFU focal therapy followed by magnetic resonance (MR)-fusion biopsy 12 mo later. Tissue change was quantified intraoperatively by measuring the backscatter of ultrasound waves during ablation. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Gleason grade group (GG) ≥2 cancer on postablation biopsy was the primary outcome. Secondary outcomes included GG ≥1 cancer, Prostate Imaging Reporting and Data System (PI-RADS) scores ≥3, and evidence of tissue destruction on post-treatment magnetic resonance imaging (MRI). A Student's t - test analysis was performed to evaluate the mean TCM scores and efficacy of ablation measured by histopathology. Multivariate logistic regression was also performed to identify the odds of residual cancer for each unit increase in the TCM score. RESULTS AND LIMITATIONS: A lower mean TCM score within the region of the tumor (0.70 vs 0.97, p = 0.02) was associated with the presence of persistent GG ≥2 cancer after HIFU treatment. Adjusting for initial prostate-specific antigen, PI-RADS score, Gleason GG, positive cores, and age, each incremental increase of TCM was associated with an 89% reduction in the odds (odds ratio: 0.11, confidence interval: 0.01-0.97) of having residual GG ≥2 cancer on postablation biopsy. Men with higher mean TCM scores (0.99 vs 0.72, p = 0.02) at the time of treatment were less likely to have abnormal MRI (PI-RADS ≥3) at 12 mo postoperatively. Cases with high TCM scores also had greater tissue destruction measured on MRI and fewer visible lesions on postablation MRI. CONCLUSIONS: Tissue change measured using TCM values during focal HIFU of the prostate was associated with histopathology and radiological outcomes 12 mo after the procedure. PATIENT SUMMARY: In this report, we looked at how well ultrasound changes of the prostate during focal high-intensity focused ultrasound (HIFU) therapy for the treatment of prostate cancer predict patient outcomes. We found that greater tissue change measured by the HIFU device was associated with less residual cancer at 1 yr. This tool should be used to ensure optimal ablation of the cancer and may improve focal therapy outcomes in the future.

A review of artificial intelligence in prostate cancer detection on imaging.

A multitude of studies have explored the role of artificial intelligence (AI) in providing diagnostic support to radiologists, pathologists, and urologists in prostate cancer detection, risk-stratification, and management. This review provides a comprehensive overview of relevant literature regarding the use of AI models in (1) detecting prostate cancer on radiology images (magnetic resonance and ultrasound imaging), (2) detecting prostate cancer on histopathology images of prostate biopsy tissue, and (3) assisting in supporting tasks for prostate cancer detection (prostate gland segmentation, MRI-histopathology registration, MRI-ultrasound registration). We discuss both the potential of these AI models to assist in the clinical workflow of prostate cancer diagnosis, as well as the current limitations including variability in training data sets, algorithms, and evaluation criteria. We also discuss ongoing challenges and what is needed to bridge the gap between academic research on AI for prostate cancer and commercial solutions that improve routine clinical care.

Domain generalization for prostate segmentation in transrectal ultrasound images: A multi-center study.

Prostate biopsy and image-guided treatment procedures are often performed under the guidance of ultrasound fused with magnetic resonance images (MRI). Accurate image fusion relies on accurate segmentation of the prostate on ultrasound images. Yet, the reduced signal-to-noise ratio and artifacts (e.g., speckle and shadowing) in ultrasound images limit the performance of automated prostate segmentation techniques and generalizing these methods to new image domains is inherently difficult. In this study, we address these challenges by introducing a novel 2.5D deep neural network for prostate segmentation on ultrasound images. Our approach addresses the limitations of transfer learning and finetuning methods (i.e., drop in performance on the original training data when the model weights are updated) by combining a supervised domain adaptation technique and a knowledge distillation loss. The knowledge distillation loss allows the preservation of previously learned knowledge and reduces the performance drop after model finetuning on new datasets. Furthermore, our approach relies on an attention module that considers model feature positioning information to improve the segmentation accuracy. We trained our model on 764 subjects from one institution and finetuned our model using only ten subjects from subsequent institutions. We analyzed the performance of our method on three large datasets encompassing 2067 subjects from three different institutions. Our method achieved an average Dice Similarity Coefficient (Dice) of 94.0±0.03 and Hausdorff Distance (HD95) of 2.28 mm in an independent set of subjects from the first institution. Moreover, our model generalized well in the studies from the other two institutions (Dice: 91.0±0.03; HD95: 3.7 mm and Dice: 82.0±0.03; HD95: 7.1 mm). We introduced an approach that successfully segmented the prostate on ultrasound images in a multi-center study, suggesting its clinical potential to facilitate the accurate fusion of ultrasound and MRI images to drive biopsy and image-guided treatments.

Evaluation of post-ablation mpMRI as a predictor of residual prostate cancer after focal high intensity focused ultrasound (HIFU) ablation.

PURPOSE: To evaluate the performance of multiparametric magnetic resonance imaging (mpMRI) and PSA testing in follow-up after high intensity focused ultrasound (HIFU) focal therapy for localized prostate cancer. METHODS: A total of 73 men with localized prostate cancer were prospectively enrolled and underwent focal HIFU followed by per-protocol PSA and mpMRI with systematic plus targeted biopsies at 12 months after treatment. We evaluated the association between post-treatment mpMRI and PSA with disease persistence on the post-ablation biopsy. We also assessed post-treatment functional and oncological outcomes. RESULTS: Median age was 69 years (Interquartile Range (IQR): 66-74) and median PSA was 6.9 ng/dL (IQR: 5.3-9.9). Of 19 men with persistent GG ≥ 2 disease, 58% (11 men) had no visible lesions on MRI. In the 14 men with PIRADS 4 or 5 lesions, 7 (50%) had either no cancer or GG 1 cancer at biopsy. Men with false negative mpMRI findings had higher PSA density (0.16 vs. 0.07 ng/mL2, P = 0.01). No change occurred in the mean Sexual Health Inventory for Men (SHIM) survey scores (17.0 at baseline vs. 17.7 post-treatment, P = 0.75) or International Prostate Symptom Score (IPSS) (8.1 at baseline vs. 7.7 at 24 months, P = 0.81) after treatment. CONCLUSIONS: Persistent GG ≥ 2 cancer may occur after focal HIFU. mpMRI alone without confirmatory biopsy may be insufficient to rule out residual cancer, especially in patients with higher PSA density. Our study also validates previously published studies demonstrating preservation of urinary and sexual function after HIFU treatment.

Multi-institutional analysis of clinical and imaging risk factors for detecting clinically significant prostate cancer in men with PI-RADS 3 lesions.

BACKGROUND: Most Prostate Imaging-Reporting and Data System (PI-RADS) 3 lesions do not contain clinically significant prostate cancer (CSPCa; grade group ≥2). This study was aimed at identifying clinical and magnetic resonance imaging (MRI)-derived risk fac- tors that predict CSPCa in men with PI-RADS 3 lesions. METHODS: This study analyzed the detection of CSPCa in men who underwent MRI-targeted biopsy for PI-RADS 3 lesions. Multivariable logistic regression models with goodness-of-fit testing were used to identify variables associated with CSPCa. Receiver operating curves and decision curve analyses were used to estimate the clinical utility of a predictive model. RESULTS: Of the 1784 men reviewed, 1537 were included in the training cohort, and 247 were included in the validation cohort. The 309 men with CSPCa (17.3%) were older, had a higher prostate-specific antigen (PSA) density, and had a greater likelihood of an anteriorly located lesion than men without CSPCa (p < .01). Multivariable analysis revealed that PSA density (odds ratio [OR], 1.36; 95% confidence interval [CI], 1.05-1.85; p < .01), age (OR, 1.05; 95% CI, 1.02-1.07; p < .01), and a biopsy-naive status (OR, 1.83; 95% CI, 1.38-2.44) were independently associated with CSPCa. A prior negative biopsy was negatively associated (OR, 0.35; 95% CI, 0.24-0.50; p < .01). The application of the model to the validation cohort resulted in an area under the curve of 0.78. A predicted risk threshold of 12% could have prevented 25% of biopsies while detecting almost 95% of CSPCas with a sensitivity of 94% and a specificity of 34%. CONCLUSIONS: For PI-RADS 3 lesions, an elevated PSA density, older age, and a biopsy-naive status were associated with CSPCa, whereas a prior negative biopsy was negatively associated. A predictive model could prevent PI-RADS 3 biopsies while missing few CSPCas. LAY SUMMARY: Among men with an equivocal lesion (Prostate Imaging-Reporting and Data System 3) on multiparametric magnetic resonance imaging (mpMRI), those who are older, those who have a higher prostate-specific antigen density, and those who have never had a biopsy before are at higher risk for having clinically significant prostate cancer (CSPCa) on subsequent biopsy. However, men with at least one negative biopsy have a lower risk of CSPCa. A new predictive model can greatly reduce the need to biopsy equivocal lesions noted on mpMRI while missing only a few cases of CSPCa.

MRI-guided focused ultrasound focal therapy for patients with intermediate-risk prostate cancer: a phase 2b, multicentre study.

BACKGROUND: Men with grade group 2 or 3 prostate cancer are often considered ineligible for active surveillance; some patients with grade group 2 prostate cancer who are managed with active surveillance will have early disease progression requiring radical therapy. This study aimed to investigate whether MRI-guided focused ultrasound focal therapy can safely reduce treatment burden for patients with localised grade group 2 or 3 intermediate-risk prostate cancer. METHODS: In this single-arm, multicentre, phase 2b study conducted at eight health-care centres in the USA, we recruited men aged 50 years and older with unilateral, MRI-visible, primary, intermediate-risk, previously untreated prostate adenocarcinoma (prostate-specific antigen ≤20 ng/mL, grade group 2 or 3; tumour classification ≤T2) confirmed on combined biopsy (combining MRI-targeted and systematic biopsies). MRI-guided focused ultrasound energy, sequentially titrated to temperatures sufficient for tissue ablation (about 60-70°C), was delivered to the index lesion and a planned margin of 5 mm or more of normal tissue, using real-time magnetic resonance thermometry for intraoperative monitoring. Co-primary outcomes were oncological outcomes (absence of grade group 2 and higher cancer in the treated area at 6-month and 24-month combined biopsy; when 24-month biopsy data were not available and grade group 2 or higher cancer had occurred in the treated area at 6 months, the 6-month biopsy results were included in the final analysis) and safety (adverse events up to 24 months) in all patients enrolled in the study. This study is registered with ClinicalTrials.gov, NCT01657942, and is no longer recruiting. FINDINGS: Between May 4, 2017, and Dec 21, 2018, we assessed 194 patients for eligibility and treated 101 patients with MRI-guided focused ultrasound. Median age was 63 years (IQR 58-67) and median concentration of prostate-specific antigen was 5·7 ng/mL (IQR 4·2-7·5). Most cancers were grade group 2 (79 [78%] of 101). At 24 months, 78 (88% [95% CI 79-94]) of 89 men had no evidence of grade group 2 or higher prostate cancer in the treated area. No grade 4 or grade 5 treatment-related adverse events were reported, and only one grade 3 adverse event (urinary tract infection) was reported. There were no treatment-related deaths. INTERPRETATION: 24-month biopsy outcomes show that MRI-guided focused ultrasound focal therapy is safe and effectively treats grade group 2 or 3 prostate cancer. These results support focal therapy for select patients and its use in comparative trials to determine if a tissue-preserving approach is effective in delaying or eliminating the need for radical whole-gland treatment in the long term. FUNDING: Insightec and the National Cancer Institute.

Computational Detection of Extraprostatic Extension of Prostate Cancer on Multiparametric MRI Using Deep Learning.

The localization of extraprostatic extension (EPE), i.e., local spread of prostate cancer beyond the prostate capsular boundary, is important for risk stratification and surgical planning. However, the sensitivity of EPE detection by radiologists on MRI is low (57% on average). In this paper, we propose a method for computational detection of EPE on multiparametric MRI using deep learning. Ground truth labels of cancers and EPE were obtained in 123 patients (38 with EPE) by registering pre-surgical MRI with whole-mount digital histopathology images from radical prostatectomy. Our approach has two stages. First, we trained deep learning models using the MRI as input to generate cancer probability maps both inside and outside the prostate. Second, we built an image post-processing pipeline that generates predictions for EPE location based on the cancer probability maps and clinical knowledge. We used five-fold cross-validation to train our approach using data from 74 patients and tested it using data from an independent set of 49 patients. We compared two deep learning models for cancer detection: (i) UNet and (ii) the Correlated Signature Network for Indolent and Aggressive prostate cancer detection (CorrSigNIA). The best end-to-end model for EPE detection, which we call EPENet, was based on the CorrSigNIA cancer detection model. EPENet was successful at detecting cancers with extraprostatic extension, achieving a mean area under the receiver operator characteristic curve of 0.72 at the patient-level. On the test set, EPENet had 80.0% sensitivity and 28.2% specificity at the patient-level compared to 50.0% sensitivity and 76.9% specificity for the radiologists. To account for spatial location of predictions during evaluation, we also computed results at the sextant-level, where the prostate was divided into sextants according to standard systematic 12-core biopsy procedure. At the sextant-level, EPENet achieved mean sensitivity 61.1% and mean specificity 58.3%. Our approach has the potential to provide the location of extraprostatic extension using MRI alone, thus serving as an independent diagnostic aid to radiologists and facilitating treatment planning.

Bridging the gap between prostate radiology and pathology through machine learning.

BACKGROUND: Prostate cancer remains the second deadliest cancer for American men despite clinical advancements. Currently, magnetic resonance imaging (MRI) is considered the most sensitive non-invasive imaging modality that enables visualization, detection, and localization of prostate cancer, and is increasingly used to guide targeted biopsies for prostate cancer diagnosis. However, its utility remains limited due to high rates of false positives and false negatives as well as low inter-reader agreements. PURPOSE: Machine learning methods to detect and localize cancer on prostate MRI can help standardize radiologist interpretations. However, existing machine learning methods vary not only in model architecture, but also in the ground truth labeling strategies used for model training. We compare different labeling strategies and the effects they have on the performance of different machine learning models for prostate cancer detection on MRI. METHODS: Four different deep learning models (SPCNet, U-Net, branched U-Net, and DeepLabv3+) were trained to detect prostate cancer on MRI using 75 patients with radical prostatectomy, and evaluated using 40 patients with radical prostatectomy and 275 patients with targeted biopsy. Each deep learning model was trained with four different label types: pathology-confirmed radiologist labels, pathologist labels on whole-mount histopathology images, and lesion-level and pixel-level digital pathologist labels (previously validated deep learning algorithm on histopathology images to predict pixel-level Gleason patterns) on whole-mount histopathology images. The pathologist and digital pathologist labels (collectively referred to as pathology labels) were mapped onto pre-operative MRI using an automated MRI-histopathology registration platform. RESULTS: Radiologist labels missed cancers (ROC-AUC: 0.75-0.84), had lower lesion volumes (~68% of pathology lesions), and lower Dice overlaps (0.24-0.28) when compared with pathology labels. Consequently, machine learning models trained with radiologist labels also showed inferior performance compared to models trained with pathology labels. Digital pathologist labels showed high concordance with pathologist labels of cancer (lesion ROC-AUC: 0.97-1, lesion Dice: 0.75-0.93). Machine learning models trained with digital pathologist labels had the highest lesion detection rates in the radical prostatectomy cohort (aggressive lesion ROC-AUC: 0.91-0.94), and had generalizable and comparable performance to pathologist label-trained-models in the targeted biopsy cohort (aggressive lesion ROC-AUC: 0.87-0.88), irrespective of the deep learning architecture. Moreover, machine learning models trained with pixel-level digital pathologist labels were able to selectively identify aggressive and indolent cancer components in mixed lesions on MRI, which is not possible with any human-annotated label type. CONCLUSIONS: Machine learning models for prostate MRI interpretation that are trained with digital pathologist labels showed higher or comparable performance with pathologist label-trained models in both radical prostatectomy and targeted biopsy cohort. Digital pathologist labels can reduce challenges associated with human annotations, including labor, time, inter- and intra-reader variability, and can help bridge the gap between prostate radiology and pathology by enabling the training of reliable machine learning models to detect and localize prostate cancer on MRI.