Objectives: To establish the role of BCG instillations in the incidence and mortality of COVID-19. Patients and methods: NMIBC patients in instillations with BCG (induction or maintenance) during 2019/2020 were included, establishing a COVID-19 group (with a diagnosis according to the national registry) and a control group (NO-COVID). The cumulative incidence (cases/total patients) and the case fatality rate (deaths/cases) were established, and compared with the national statistics for the same age group. T-test was used for continuous variables and Fisher's exact test for categorical variables. Results: 175 patients were included. Eleven patients presented CIS (11/175, 6.3%), 84/175 (48.0%) Ta and 68/175 (38.9%) T1. Average number of instillations = 13.25 ± 7.4. One hundred sixty-seven patients (95.4%) had complete induction. Forty-three patients (cumulative incidence 24.6%) were diagnosed with COVID-19. There is no difference between COVID-19 and NO-COVID group in age, gender or proportion of maintenance completed. COVID-19 group fatality rate = 1/43 (2.3%). Accumulated Chilean incidence 70–79 years = 6.3%. Chilean fatality rate 70–79 years = 14%. Conclusions: According to our results, patients with NMIBC submitted to instillations with BCG have a lower case-fatality rate than the national registry of patients between 70 and 79 years (2.3% vs. 14%, respectively). Intravesical BCG could decrease the mortality due to COVID-19, so instillation schemes should not be suspended in a pandemic.

Bladder cancer (BC) is the most common malignancy of the urinary tract. Approximately 75% of cases are non-muscle-invasive BC (NMIBC), while muscle-invasive BC (MIBC) and advanced tumors account for most cancer-specific mortality. Accurate assessment of tumor invasion is essential, as staging variability may lead to inappropriate treatments. Tumor invasion involves several mechanisms including extracellular matrix (ECM) remodeling mediated by metalloproteinases, angiogenesis, and cell adhesions. Masson’s trichrome staining (MTS) provides relevant information on ECM composition. This study evaluated the application of machine learning to MTS-stained bladder biopsies to predict muscle invasion. A retrospective analysis of bladder biopsy images obtained from transurethral resections and cystectomies (2022–2024). A total of 702 histological images were analyzed. A convolutional neural network (CNN) was trained to classify tumors as MIBC or NMIBC and model outputs were correlated with clinical variables. The CNN achieved an accuracy of 95.2% in the training set and 90.1% in validation. Model-derived probabilities were significantly associated with tumor grade, lesion size, and muscle invasion. Logistic regression demonstrated a strong association with invasive disease (OR = 0.07, p = 0.017). CNN-based analysis of MTS-stained bladder biopsy images enable accurate prediction of muscle invasion, with potential to improve diagnostic precision.

Background: Bladder cancer (BC) is the most common malignancy of the urinary tract. Approximately 75% of cases are non–muscle-invasive BC (NMIBC), while muscle-invasive BC (MIBC) and advanced tumors account for most cancer-specific mortality. Accurate assessment of tumor invasion is essential, as staging variability may lead to inappropriate treatments. Tumor invasion involves several mechanisms including extracellular matrix (ECM) remodeling mediated by metalloproteinases, angiogenesis, and cell adhesions. Masson’s trichrome staining (MTS) provides relevant information on ECM composition. This study evaluated the application of machine learning to MTS-stained bladder biopsies to predict muscle invasion. Methods: A retrospective analysis of bladder biopsies images obtained from transurethral resections and cystectomies (2022–2024). A total of 702 histological images were analyzed. A convolutional neural network (CNN) was trained to classify tumors as MIBC or NMIBC and model outputs were correlated with clinical variables. Results: The CNN achieved an accuracy of 95.2% in the training set and 90.1% in validation. Model-derived probabilities were significantly associated with tumor grade, lesion size, and muscle invasion. Logistic regression demonstrated a strong association with invasive disease (OR = 0.07, p = 0.017). Conclusion: CNN-based analysis of MTS-stained bladder biopsies images enables accurate prediction of muscle invasion, with potential to improve diagnostic precision.