Deep Learning Models for Cystoscopic Recognition of Hunner Lesion in Interstitial Cystitis.

Background: Accurate cystoscopic recognition of Hunner lesions (HLs) is indispensable for better treatment prognosis in managing patients with Hunner-type interstitial cystitis (HIC), but frequently challenging due to its varying appearance. Objective: To develop a deep learning (DL) system for cystoscopic recognition of a HL using artificial intelligence (AI). Design setting and participants: A total of 626 cystoscopic images collected from January 8, 2019 to December 24, 2020, consisting of 360 images of HLs from 41 patients with HIC and 266 images of flat reddish mucosal lesions resembling HLs from 41 control patients including those with bladder cancer and other chronic cystitis, were used to create a dataset with an 8:2 ratio of training images and test images for transfer learning and external validation, respectively. AI-based five DL models were constructed, using a pretrained convolutional neural network model that was retrained to output 1 for a HL and 0 for control. A five-fold cross-validation method was applied for internal validation. Outcome measurements and statistical analysis: True- and false-positive rates were plotted as a receiver operating curve when the threshold changed from 0 to 1. Accuracy, sensitivity, and specificity were evaluated at a threshold of 0.5. Diagnostic performance of the models was compared with that of urologists as a reader study. Results and limitations: The mean area under the curve of the models reached 0.919, with mean sensitivity of 81.9% and specificity of 85.2% in the test dataset. In the reader study, the mean accuracy, sensitivity, and specificity were, respectively, 83.0%, 80.4%, and 85.6% for the models, and 62.4%, 79.6%, and 45.2% for expert urologists. Limitations include the diagnostic nature of a HL as warranted assertibility. Conclusions: We constructed the first DL system that recognizes HLs with accuracy exceeding that of humans. This AI-driven system assists physicians with proper cystoscopic recognition of a HL. Patient summary: In this diagnostic study, we developed a deep learning system for cystoscopic recognition of Hunner lesions in patients with interstitial cystitis. The mean area under the curve of the constructed system reached 0.919 with mean sensitivity of 81.9% and specificity of 85.2%, demonstrating diagnostic accuracy exceeding that of human expert urologists in detecting Hunner lesions. This deep learning system assists physicians with proper diagnosis of a Hunner lesion.

Low hemoglobin and PSA kinetics are prognostic factors of overall survival in metastatic castration-resistant prostate cancer patients.

The objective of this study was to identify the prognostic factors and to propose a new risk model in metastatic castration-resistant prostate cancer (mCRPC) patients. The clinical data were retrospectively obtained for 102 mCRPC patients who received cancer treatment between 2005 and 2018 at the University of Tokyo Hospital. We investigated clinical and pathological parameters, including prostate-specific antigen (PSA) kinetic profiles under androgen deprivation treatment, and identified predictors of overall survival (OS). The median age and PSA were 73 (Interquartile range [IQR], 68-79) years and 5.00 (IQR, 2.77-13.6) ng/ml. The median follow-up was 34 (IQR, 17-56) months. In univariate analysis, 'lymph node metastasis', 'Hemoglobin (Hb)', 'Time to nadir PSA (TNPSA)', 'PSA doubling time (PSADT)', 'Time to CRPC', and 'presence of pain' were prognostic factors. Multivariate analysis identified 'Hb < 11 g/dL', 'TNPSA < 7 months' and 'PSADT < 5 months' as independent prognostic factors of OS. The high-risk group (patients with two or three factors) demonstrated shorter OS (23 vs. 50 months) with an increased risk of death (HR = 2.997; 95% CI 1.632-5.506; P = 0.0004). The proposed risk stratification model may contribute to the prediction of survival and provide supportive information in treatment decision-making.

Prostate-specific antigen doubling time predicts the efficacy of site-directed therapy for oligoprogressive castration-resistant prostate cancer.

Background: In recent years, site-directed therapies (SDTs) targeting progressive lesions in patients with oligometastatic prostate cancer have attracted attention. However, whether they effectively treat oligoprogressive castration-resistant prostate cancer (CRPC) remains unclear. Here, we investigated the efficacy of SDT in patients with oligoprogressive CRPC and identified prognostic factors. Methods: We reviewed 59 patients with oligoprogressive CRPC who underwent SDT targeting prostate or metastatic lesions between April 2014 and March 2022. We evaluated the associations between several pretreatment clinical variables and treatment procedures and a >50% prostate-specific antigen (PSA) response, progression-free survival (PFS), and time to next treatment (TTNT). Results: A PSA response of >50% was observed in 66% of patients. The median PFS and TTNT were 8.3 months and 9.9 months, respectively. Patients with PSA doubling time ≥6 months showed a higher >50% PSA response rate (87% vs. 45%; P < 0.001), longer PFS (median, 15.0 vs. 5.0 months; P < 0.001), and longer TTNT (median, 16.3 vs. 5.9 months; P < 0.001) than patients with PSA doubling time <6 months. In multivariate analyses, a PSA doubling time of ≥6 months independently predicted a >50% PSA response, favorable PFS, and TTNT (P = 0.037, 0.025, and 0.017, respectively). Conclusion: PSA doubling time of ≥6 months may be a key indicator of the favorable efficacy of SDT for oligoprogressive CRPC.

Time to castration resistance is a novel prognostic factor of cancer-specific survival in patients with nonmetastatic castration-resistant prostate cancer.

We aimed to identify prognostic factors of cancer-specific survival (CSS) in non-metastatic castration-resistant prostate cancer (M0CRPC) patients. The final analysis of this retrospective cohort included 82 patients who were diagnosed as M0CRPC between 1998 and 2018 at the University of Tokyo Hospital. CRPC was defined as prostate-specific antigen (PSA) progression (increased PSA ≥ 25% and ≥ 2 ng/mL above the nadir or detection of a metastatic lesion). The median value of age and PSA at the time of CRPC were 76 (range 55-94) years and 2.84 (range 2.04-22.5) ng/mL, respectively. The median follow-up time from CRPC diagnosis was 38 (range 3-188) months. The prognostic factors of CSS were 'PSA doubling time (PSADT) ≤ 3 months', 'time to CRPC diagnosis from the start of androgen deprivation therapy (TTCRPC) ≤ 12 months', of which TTCRPC was a novel risk factor of CSS. In the multivariate analysis, 'PSADT ≤ 3 months' and TTCRPC ≤ 12 months' remained as statistically significant predictors of CSS. Novel risk stratification was developed based on the number of these risk factors. The high-risk group showed a hazard ratio of 4.416 (95% confidence interval 1.701-11.47, C-index = 0.727).

Safe administration of ipilimumab plus nivolumab to a dialysis patient with renal cell carcinoma.

INTRODUCTION: The combination of ipilimumab plus nivolumab has been used as first-line therapy for metastatic renal cell carcinoma. While it is well known that hemodialysis patients have a higher rate of renal cell carcinoma compared to the general population, no reports have described the safety of ipilimumab-nivolumab in metastatic renal cell carcinoma patients on hemodialysis. CASE PRESENTATION: A 73-year-old man with a 21-year history of dialysis was referred to our department in 2019 for bilateral renal tumors and multiple lung nodules. He had already been diagnosed with bilateral renal tumors in 2015, without undergoing surgery due to comorbidities. In May 2019, contrast-enhanced computed tomography revealed multiple lung metastases in addition to the existing renal tumors; consequently, he was treated with four doses of nivolumab-ipilimumab with no adverse events. CONCLUSION: The combination of ipilimumab plus nivolumab was safely used in a hemodialysis patient with metastatic renal cell carcinoma.

Spontaneous regression of a renal mass and multiple lung nodules after methotrexate cessation.

INTRODUCTION: Methotrexate has been reported to increase the risk of lymphoproliferative disorders. We report a rare case who was clinically diagnosed with methotrexate-associated lymphoproliferative disorders of the kidney. CASE PRESENTATION: A 77-year-old patient with rheumatoid arthritis had taken low-dose methotrexate for 13 years. The patient developed left renal mass 3 cm in size and multiple pulmonary nodules. Initially, renal malignant tumor with lung metastases was considered and the renal biopsy was planned. However, under possible diagnosis of methotrexate-related lymphoproliferative disorder, we withdrew methotrexate treatment at first and then observed spontaneous regression of the tumorous lesions of the kidney and lungs. CONCLUSION: Although methotrexate-related lymphoproliferative disorder in kidneys is very rare, our case advocates the importance of a relevant differential diagnosis of methotrexate-related lymphoproliferative disorder under the setting of long-term treatment of methotrexate for rheumatoid arthritis.