the estimated area and the area annotated by the doctor exceeded 50%; otherwise, the results were considered inaccurate. The evaluation was performed using a five-fold cross-validation test.RESULTS: For the test dataset, containing 1,650 cystoscopy images (WLI 217 and NBI 64 images of bladders with tumors and WLI 1,104 and NBI 265 images of normal bladders), and at the threshold where the F1 score in the training dataset was the maximum, the proposed AI model exhibited average sensitivity, specificity, and F1 scores of 83.7%, 82.3%, and 0.637, respectively. We adapted the AI model to all frames of a clinical cystoscopy video of a case and detected the lesion sites.CONCLUSIONS: By applying the analysis of still images to video, real-time detection of bladder tumor lesions for both WLI and NBI is possible, with AI showing the probability map of the lesion sites using the proposed method. This may improve diagnostic accuracy by creating awareness among urologists of all skill levels and by encouraging more robust observations.

Introduction: Prostate cancers are infiltrated with Programmed Death-1 (PD-1) expressing Cluster of Differentiation (CD)8+ T-cells which interact with Programmed Death Ligand-1 (PDL-1) receptors on Tumour Cells (TC). However, in many studies, male with prostate cancer did not respond to monotherapy (PDL blockade). This unresponsiveness could be due to the fact that prostate cancer usually does not express PD-L1. The PDL-1 expression has demonstrated a significant correlation with increased risk of disease progression in various tumours but data regarding its role in prostate cancer is conflicting. Aim: To study the occurrence rate of PDL-1 expression and itsassociation with tumour aggressiveness in prostate cancer. Materials and Methods: This cross-sectional observational study was conducted at ABVIMS and Dr. Ram Manohar Hospital, New Delhi, India, from October 1st, 2018 to April 30th, 2020. A total of 120 males with prostate cancer who had their diagnosis established by a prostate biopsy were included. Histopathology reports were analysed and PDL-1 immunohistochemical staining was carried out with PD-L1 monoclonal antibodies. PD-L1 expression on TCs was defined by the percentage of PD-L1 positive TCs (<1%= 0 or negative, 1 to 5% =+1, ≥5 %=+2). The relationship between PDL-1 expression in prostate cancer cells and clinicopathological factors like Gleason grade, lymph node positivity, perineural invasion, lymphovascular invasion, distant metastasis and Prostate Specific Antigen (PSA) level was investigated using univariate tests and multivariate logistic regression analyses. Results: Overall, high PD-L1 expression was observed in 21.7% of patients. PDL-1 positivity 1+ and 2+ was found among 11.67% and 10% cases, respectively. Significantly higher expression (p-value <0.05) of PDL-1 was noted in cases with higher preoperative PSA levels (>40), high Gleason score (≥7), distant metastasis and cases with lymphovascular invasion. Conclusion: Present study suggests that PD-L1 correlates with the tumour aggressiveness in prostate cancer patients and can be used for the identification of more aggressive diseases.

No abstract

No abstract