Prostate-Specific Membrane Antigen-Targeted Radioguided Pelvic Lymph Node Dissection in Newly Diagnosed Prostate Cancer Patients with a Suspicion of Locoregional Lymph Node Metastases: The DETECT Trial.

Prostate-specific membrane antigen (PSMA)-targeted radioguided surgery (RGS) aims to optimize the peroperative detection and removal of PSMA-avid lymph node (LN) metastases (LNMs) and has been described in patients with recurrent prostate cancer (PCa). In newly diagnosed PCa patients undergoing pelvic LN dissections, PSMA RGS could guide the urologist toward PSMA-expressing LNMs as identified on preoperative 18F-PSMA PET/CT imaging. The objective was to evaluate the safety and feasibility of 111In-PSMA RGS in primary PCa patients with one or more suggestive LNs on preoperative 18F-PSMA PET/CT. Methods: This prospective, phase I/II study included 20 newly diagnosed PCa patients with at least 1 suggestive LN on preoperative 18F-PSMA PET/CT. PSMA RGS was performed 24 h after 111In-PSMA-I&T administration, and postoperative 18F-PSMA PET/CT was performed to verify successful removal of the suggestive lesions. The primary endpoint was determination of the safety and feasibility of 111In-PSMA RGS. Safety was assessed by monitoring adverse events. Feasibility was described as the possibility to peroperatively detect suggestive LNs as identified on preoperative imaging. Secondary outcomes included the accuracy of 111In-PSMA RGS compared with histopathology, tumor- and lesion-to-background ratios, and biochemical recurrence. Results: No tracer-related adverse events were reported. In 20 patients, 43 of 49 (88%) 18F-PSMA PET-suggestive lesions were successfully removed. 111In-PSMA RGS facilitated peroperative identification and resection of 29 of 49 (59%) RGS-target lesions, of which 28 (97%) contained LNMs. Another 14 of 49 (29%) resected LNs were not detected with 111In-PSMA RGS, of which 2 contained metastases. Conclusion: 111In-PSMA RGS is a safe and feasible procedure that allows peroperative detection of 18F-PSMA PET/CT-suggestive lesions in newly diagnosed PCa patients. The use of a radioactive PSMA tracer and a detection device (γ-probe) during surgery helps in identifying LNs that were suggestive of PCa metastases on the 18F-PSMA PET/CT before surgery and thus may improve the peroperative identification and removal of these LNs.

Endometrial Pipelle Biopsy Computer-Aided Diagnosis: A Feasibility Study.

Endometrial biopsies are important in the diagnostic workup of women who present with abnormal uterine bleeding or hereditary risk of endometrial cancer. In general, approximately 10% of all endometrial biopsies demonstrate endometrial (pre)malignancy that requires specific treatment. As the diagnostic evaluation of mostly benign cases results in a substantial workload for pathologists, artificial intelligence (AI)-assisted preselection of biopsies could optimize the workflow. This study aimed to assess the feasibility of AI-assisted diagnosis for endometrial biopsies (endometrial Pipelle biopsy computer-aided diagnosis), trained on daily-practice whole-slide images instead of highly selected images. Endometrial biopsies were classified into 6 clinically relevant categories defined as follows: nonrepresentative, normal, nonneoplastic, hyperplasia without atypia, hyperplasia with atypia, and malignant. The agreement among 15 pathologists, within these classifications, was evaluated in 91 endometrial biopsies. Next, an algorithm (trained on a total of 2819 endometrial biopsies) rated the same 91 cases, and we compared its performance using the pathologist's classification as the reference standard. The interrater reliability among pathologists was moderate with a mean Cohen's kappa of 0.51, whereas for a binary classification into benign vs (pre)malignant, the agreement was substantial with a mean Cohen's kappa of 0.66. The AI algorithm performed slightly worse for the 6 categories with a moderate Cohen's kappa of 0.43 but was comparable for the binary classification with a substantial Cohen's kappa of 0.65. AI-assisted diagnosis of endometrial biopsies was demonstrated to be feasible in discriminating between benign and (pre)malignant endometrial tissues, even when trained on unselected cases. Endometrial premalignancies remain challenging for both pathologists and AI algorithms. Future steps to improve reliability of the diagnosis are needed to achieve a more refined AI-assisted diagnostic solution for endometrial biopsies that covers both premalignant and malignant diagnoses.