Clinical Utility of Tumor-Detect Artificial Intelligence Algorithm for Detection of Prostate Cancer on Transurethral Resection Specimen

Artificial intelligence (AI)-based tumor detection algorithms are increasingly being integrated into digital pathology workflows. This study evaluated the performance of the Tumor-Detect AI algorithm for identifying prostate cancer in transurethral resection of prostate (TURP) specimens, which are diagnostically challenging due to tissue fragmentation and small incidental tumor foci. Eighty-one whole-slide images from 11 TURP specimens, including six specimens diagnosed as benign prostatic hyperplasia and five specimens with incidental prostate adenocarcinoma, were analyzed using the Tumor-Detect algorithm (PathAI, Boston, MA). The algorithm flags slides with suspected malignancy and generates heatmaps highlighting tumor regions. Results were compared with ground truth established by a genitourinary pathologist. All malignant specimens were correctly identified, achieving 100% specimen-level sensitivity. Slide-level sensitivity and specificity were 88% and 86%, respectively. False-positive results were primarily related to complex glandular architecture, clear cell change, or high-grade prostatic intraepithelial neoplasia. These findings demonstrate that Tumor-Detect AI shows high diagnostic accuracy in TURP specimens and may improve efficiency while reducing missed diagnoses in routine pathology practice.