Search

Abstract Objective The objective of this study is to compare detection rates of extracapsular extension (ECE) of prostate cancer (PCa) using artificial intelligence (AI)‐generated cancer maps versus MRI and conventional nomograms. Materials and methods We retrospectively analysed data from 147 patients who received MRI‐targeted biopsy and subsequent radical prostatectomy between September 2016 and May 2022. AI‐based software cleared by the United States Food and Drug Administration (Unfold AI, Avenda Health) was used to map 3D cancer probability and estimate ECE risk. Conventional ECE predictors including MRI Likert scores, capsular contact length of MRI‐visible lesions, PSMA T stage, Partin tables, and the “PRedicting ExtraCapsular Extension” nomogram were used for comparison. Postsurgical specimens were processed using whole‐mount histopathology sectioning, and a genitourinary pathologist assessed each quadrant for ECE presence. ECE predictors were then evaluated on the patient (Unfold AI versus all comparators) and quadrant level (Unfold AI versus MRI Likert score). Receiver operator characteristic curves were generated and compared using DeLong's test. Results Unfold AI had a significantly higher area under the curve (AUC = 0.81) than other predictors for patient‐level ECE prediction. Unfold AI achieved 68% sensitivity, 78% specificity, 71% positive predictive value, and 75% negative predictive value. At the quadrant level, Unfold AI exceeded the AUC of MRI Likert scores for posterior (0.89 versus 0.82, p = 0.003), anterior (0.84 versus 0.80, p = 0.34), and all quadrants (0.89 versus 0.82, p = 0.002). The false negative rate of Unfold AI was lower than MRI in both the anterior (−60%) and posterior prostate (−40%). Conclusions Unfold AI accurately predicted ECE risk, outperforming conventional methodologies. It notably improved ECE prediction over MRI in posterior quadrants, with the potential to inform nerve‐spare technique and prevent positive margins. By enhancing PCa staging and risk stratification, AI‐based cancer mapping may lead to better oncological and functional outcomes for patients.

Abstract Micro-ultrasound has recently been introduced as a low-cost alternative to multi-parametric MRI for imaging prostate cancer. Early clinical studies have demonstrated promising results; however, robust validation via comparison with whole-mount pathology has yet to be achieved. Due to micro-ultrasound probe design and tissue deformation during scanning, it is difficult to accurately correlate micro-ultrasound imaging planes with ground truth whole-mount pathology slides. In this study, we developed a multi-step methodology to co-register micro-ultrasound and MRI to whole-mount pathology. The three-step process had a registration error of 3.90 ± 0.11 mm and consists of: (1) micro-ultrasound image reconstruction, (2) 3D landmark registration of micro-ultrasound to MRI, and (3) 2D capsule registration of MRI to whole-mount pathology. This process was then used in a preliminary reader study to compare the diagnostic accuracy of micro-ultrasound and MRI in 15 patients who underwent radical prostatectomy for prostate cancer. Micro-ultrasound was found to have equivalent performance to retrospective MRI review for index lesion detection (91.7% vs. 80%), while demonstrating an increased detection of tumor extent (52.5% vs. 36.7%) with similar false positive regions-of-interest (38.3% vs. 40.8%). Prospective MRI review had reduced detection of index lesions (73.3%) and tumor extent (18.9%) but improved false positive regions-of-interest (22.7%) relative to micro-ultrasound and retrospective MRI. Further evaluation is needed with a larger sample size.

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