This study aims to explore the possibility and bottleneck of clinical translation for an artificial intelligence (AI) diagnosis system for bladder cancer based on cystoscopy.We retrospectively collected videos of 101 bladder cancer patients from January to November 2023, at Sun Yat-sen Memorial Hospital, Sun Yat-sen University. Among these patients, with a median age of 63 years and 81.0% were male. The bladder cancer AI diagnosis system was utilized for diagnosis, and the accuracy of diagnoses from the videos was assessed. Additionally, a surgical evaluation scale was formulated to evaluate the quality of the videos, simulating clinical usage.The final test results showed a system sensitivity of 97.8%, a positive predictive value of 81.7%, specificity of 54.2%, and a negative predictive value of 92.3%. Furthermore, the surgical evaluation scale scores ranged from 3.96 to 4.69, indicating the feasibility of clinical application for this system.This study further quantitatively validated the accuracy of an artificial intelligence system using cystoscopy videos and assessed the potential for clinical application.
本研究主要探讨基于膀胱镜的膀胱癌人工智能诊断系统（CAIDS）临床转化的可能性及瓶颈问题。回顾性收集2023年1~11月中山大学孙逸仙纪念医院的101例膀胱癌患者膀胱镜视频，患者年龄中位数为63岁，其中男性占比81.0%（82/101）。使用CAIDS进行诊断，并对视频的诊断准确性进行评估。同时制定手术评价量表，基于量表对视频质量进行评估，以模拟临床使用。使用膀胱镜视频来定量验证人工智能系统的准确性。最终测试结果系统灵敏度为97.8%，阳性预测值为81.7%，特异度54.2%，阴性预测值为92.3%。此外，手术评价量表评分在3.96~4.69，表明该系统具有临床推广的可行性。.

BACKGROUND: The forgotten ureteral stents (FUS) is one of the late complications of stent placement. This systematic review summarized different aspects of FUS and focused on the problems and solutions related to FUS.
METHODS: This systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) statement. PubMed® and Embase® were searched from inception until October 1st, 2022. Eligible studies were those defining FUS as a stent unintentionally left in situ longer than at least 2 months.
RESULTS: Total 147 studies with 1292 patients were finally included. The mean indwelling time of FUS was 33.5 months (range from 3 months to 32 years). The most common initial cause for stent placement was adjunct treatment to urolithiasis (79.2%). The major forgetting reasons were patient-related (83.9%), which included poor compliance, lapse in memory, and misconceptions about the necessity of timely removal. Primary presenting complaints were flank pain (37.3%), lower urinary tract symptoms (33.3%), and hematuria (22.8%). Encrustation (80.8%) and urinary tract infections (40.2%) were the most common complications detected in patients with FUS. Computed tomography evolving as a preferred imaging test (76.1%) was indispensable for evaluating encrustation, migration, fracture and other complicated situations in patients with FUS. Besides, evaluation of kidney function and infection status was also of great importance. Multiple and multimodal procedures (59.0%) were often necessitated to achieve the stent-free status, and were mostly endoscopic procedures. Cystoscope was most commonly used (64.8%). Retrograde ureteroscopy (43.4%) and antegrade stent removal (31.6%) were often used when dealing with more complicated situations. Extracorporeal shockwave lithotripsy (30.4%) was often used as adjunctive to other endoscopic procedures, but it sometimes failed. The decision regarding the choice of treatment is based on the volume and site of encrustation, the direction of migration, the site of fracture, kidney function and other urinary comorbidities.
CONCLUSIONS: FUS not only pose hazard to patients\' health, but also impose a huge economic burden on medical care. Thorough preoperative evaluation is fundamental to developing the treatment strategy. The management of FUS should be individualized using different treatment modalities with their advantages to minimize patients\' morbidities. Prevention is better than cure. Strengthening health education and setting a tracking program are of great importance to the prevention of FUS.

In 2022, American Urological Association updated the guideline for the diagnosis and treatment of interstitial cystitis/bladder pain syndrome (IC/BPS). A significant change has been made in treatment recommendations. The updated guideline no longer divided treatments into first-line through sixth-line tiers. Instead, treatment is categorized into behavioral/non-pharmacologic, oral medicines, bladder instillations, procedures, and major surgery. This change emphasizes the heterogeneity of IC/BPS patients and the importance of individualized treatment, overturns traditional unreasonable ideas about hierarchical and progressive treatment, and encourages patients and physicians to make treatment decisions together. At the same time, the panel emphasized the importance of early implementation of cystoscopy in patients suspected of Hunner lesions and warned against the possibility of pentosan polysulfate causing a unique retinal pigmentary maculopathy. Urinary reconstruction surgery was considered to only be used as a last resort for the treatment of IC/BPS, and there is uncertainty about the overall balance between benefits and risks/burdens. The updated guideline provides a new understanding and decision-making basis for the diagnosis and treatment of IC/BPS. However, it should be noted that the clinical characteristics of Chinese patients should be considered in practice and the application of the guideline should be localized.
2022年美国泌尿外科学会更新了间质性膀胱炎/膀胱疼痛综合征（IC/BPS）的诊断和治疗指南，本次更新在治疗推荐方面做了大幅改动，不再推荐一线至六线治疗，而将目前已有的治疗方案分为五大类，包括行为和非药物治疗、口服药物、膀胱药物灌注、经尿道手术和骶神经调节，以及尿路重建手术。这种改变强调了IC/BPS患者的异质性及个体化治疗的重要性，打破了长期以来层级递进式的治疗观念，并且鼓励患者参与治疗方案的决策。同时，专家委员会强调了IC/BPS病程早期进行膀胱镜检查的重要性，也指出应用戊聚糖多硫酸盐导致视网膜色素性黄斑病的风险，并且认为尿路重建手术仅作为治疗IC/BPS的最后手段，且收益风险比不明确。更新后的指南就IC/BPS的诊断和治疗为医师提供了新的认识和决策依据，但需要注意的是，实践中需考虑中国患者的临床特征，做到指南应用本土化。.

BACKGROUND: Bladder cancer (BC) is a major health concern that poses a significant threat to the population, with an increasing incidence rate and a high risk of recurrence and progression. The primary clinical method for diagnosing BC is cystoscopy, but due to the limitations of traditional white light cystoscopy and inadequate clinical experience among junior physicians, its detection rate for bladder tumor, especially small and flat lesions, is relatively low. However, recent years have seen remarkable advancements in the application of artificial intelligence (AI) technology in the field of medicine. This has led to the development of numerous AI algorithms that have been successfully integrated into medical practices, providing valuable assistance to clinicians. The purpose of this study is to develop a cystoscopy algorithm that is real time, cost effective, high performing, and accurate, with the aim of enhancing the detection rate of bladder tumors during cystoscopy.
METHODS: For this study, a dataset of 3,500 cystoscopic images obtained from 100 patients diagnosed with BC was collected, and a deep learning model was developed utilizing the U-Net algorithm within a convolutional neural network for training purposes.
RESULTS: This study randomly divided 3,500 images from 100 BC patients into training and validation groups, and each patient\'s pathology result was confirmed. In the validation group, the accuracy of tumor recognition by the U-Net algorithm reached 98% compared to primary urologists, with greater accuracy and faster detection speed.
CONCLUSIONS: This study highlights the potential of U-Net-based deep learning techniques in the detection of bladder tumors. The establishment and optimization of the U-Net model is a significant breakthrough and it provides a valuable reference for future research in the field of medical image processing.

The vascular and morphological features of tumors are important predictors of the nature, grade, and stage of various cancers. However, this association has not been tested in bladder cancer. The aim of our study was to investigate the correlation between the morphological characteristics of tumor vessels and the nature, stage and grade of bladder cancer. Between November 2021 and March 2023, we prospectively collated clinical information and cystoscopy information from a series of patients with bladder cancer. Univariate and multivariate logistic regression analysis were used to identify independent risk factors for the nature, grade and stage of bladder cancer. Our analysis showed that cauliflower-like tumors, dotted vessels, and circumferential vessels were independent risk factors for bladder cancer. Reticular vessels were an independent risk factor for high-grade bladder cancer. Thick branching vessels in bladder tumors, along with a wide base, were independent risk factors for the invasion of bladder cancer into the lamina propria. Primary diagnosis, lesion location (beside the left ureteral orifice) and obscure lesion boundaries were all identified as independent risk factors for muscle invasive bladder cancer.

The present study reports the clinical data of a patient with renal venous malformation misdiagnosed as carcinoma. CT revealed hematocele in the left renal pelvis and ureter. CTU: the left renal pelvis and calyces showed a slightly high density shadow, a size of about 2.6 cm*1.5 cm, and mild-to-moderate enhancement was found at the edge of the lesion. Enhanced MR showed that irregular mass abnormal signal was observed in the lower calyx of the left kidney and the lesions were cast, with short T1 and slightly long T2 signals. The secondary bleeding or mucus of low-grade malignant tumor became suspicious. The patient underwent cystoscopy and left ureteroscopy under general anesthesia on December 3, 2021. Bloody urine can be seen on the left side, and multiple blood clots in the left renal pelvis can be detected. After washing, dark red bloody necrotic substances can be seen. Pathology suggests that renal venous malformation, accompanied by bleeding and thrombosis, is located in the renal medulla, involving the renal calyx, rupture and bleeding of the renal calyx, and obvious local bleeding of surrounding renal tissue. Follow-up for more than 1 year showed that the patient\'s condition was stable. When patients have renal colic with hematuria, enhanced CT suggests that renal mass is mild-to-moderate continuous enhancement, enhanced MRI suggests short T1 and long T2, considering that the mass may be accompanied by bleeding, and ureteroscopy suggests that dark red bloody necrotic substances should be considered in the diagnosis of renal venous malformation.

OBJECTIVE: Hospital management and medical treatment changed during the coronavirus disease 2019 (COVID-19) pandemic. This study investigated the impact of the COVID-19 pandemic on patients with bladder cancer.
METHODS: In this multicenter retrospective study, we collected information from the electronic medical records of outpatients who underwent cystoscopy and inpatients with confirmed bladder cancer in three hospitals in Nanjing (two province-level and one county-level hospitals) in 2019 and 2020. Patients\' home addresses, treatment methods, length of stay, and pathology were compared between the periods.
RESULTS: In total, 4048 outpatients and 1242 inpatients were included. The average number of cystoscopies decreased significantly during the lockdown. In province-level hospitals, the number of cystoscopies increased gradually as the pandemic was brought under control but remained lower than that in 2019, whereas the number grew in 2020 in county-level hospitals. The rates of recurrence and radical cystectomy were higher in 2020 than in 2019. No significant difference in the pathological grade was observed. More patients who underwent radical cystectomy were diagnosed with muscle-invasive bladder cancer during the 2020 lockdown.
CONCLUSIONS: The pandemic severely affected patients with bladder cancer, mainly in their choice of institution and treatment.

Currently, the clinical strategy for diagnosis of non-muscle invasive bladder cancer (NMIBC) such as cystoscopy and cytology are invasive and/or with limited accuracy. OncoUrine, a urinary assay for mutation and methylation biomarkers, have showed a high accuracy in the detection of upper tract urinary carcinoma (UTUC) patients with hematuria. The aim of this study is to evaluate the performance of OncoUrine in diagnosis of NMIBC patients.
In this multicenter prospective study, a total of 203 patients were enrolled, including 60 patients present with hematuria and 143 NMIBC patients under recurrence surveillance. Urine samples were collected before cystoscopy to undergo OncoUrine test. OncoUrine performance was calculated compared to clinical standard methods in hematuria cohort and recurrence surveillance cohort, respectively. Furthermore, NMIBC patients were followed up with a median time of 20.5 months (range 0.03 to 24.03 months) to assess the predictive value of OncoUrine during recurrence monitoring.
For bladder cancer diagnosis, OncoUrine tested 47 samples and achieved a sensitivity/specificity/positive predictive value (PPV)/negative predictive value (NPV) of 80% (95% CI 44.2-96.5)/91.9% (95% CI 77.0-97.9)/72.7% (95% CI 39.3-92.7)/94.4% (95% CI 80.0-99.0) (kappa value 69.4%, 95% CI 44.4-94.3), indicating 72.3% of unnecessary cystoscopy. For recurrence diagnosis, OncoUrine tested 93 samples, and the sensitivity/specificity/PPV/NPV was 100% (95% CI 59.8-100.0)/68.2% (95% CI 57.1-77.7)/22.9% (95% CI 11.0-40.6)/100% (95% CI 92.3-100.0) (kappa value 27.0%, 95% CI 11.1-42.8), indicating 62.4% of spared cystoscopy. What is more, OncoUrine correctly predicted 80% (20/25) of final recurrence with 12/25 (48%) patients who were OncoUrine positive, but cystoscopy negative was followed with recurrence during follow-up. The test result of OncoUrine was also found significantly correlated with recurrence free survival (RFS) of NMIBC patients (median 34.4-month vs unreached; HR 6.0, 95% CI 2.7-13.5, P < 0.0001).
OncoUrine showed potential value to reduce the frequency of unnecessary cystoscopy and the healthcare cost of bladder cancer patients. Patients with positive test results represented a population who were at high risk of recurrence and thus should be subject to frequent surveillance to ensure timely detection of any potential recurrence. This study has been registered in ClinicalTrials.gov with the number NCT04994197 posted on August 2021.

OBJECTIVE: At present, the prediction of bladder tumor nature during cystoscopy is partially dependent on the clinician\'s own experience. Subjective factors may lead to excessive biopsy or delayed treatment. The purpose of our study is to establish a reliable model for predicting the nature of bladder tumors using narrow band imaging.
METHODS: From November 2021 to November 2022, the clinical data of 231 patients who required a cystoscopy were prospectively collected at our center. Cystoscopy was performed in 219 eligible patients, in which both tumor and vascular morphology characteristics were recorded. Pathological results were used as the diagnostic standard. A logistic regression analysis was used to screen out factors related to tumor pathology. Bootstrap resampling was used for internal validation. A total of 71 patients from four other centers served as an external validation cohort.
RESULTS: The following diagnostic factors were identified: tumor morphology (cauliflower-like or algae-like lesions), vascular morphology (dotted or circumferential vessels), tumor boundary (clear or unclear), and patients\' symptoms (gross hematuria) and were included in the prediction model. The internal validation results showed that the area under the curve was 0.94 (95% CI 0.92-0.97), and the P value from the goodness-of-fit test was 0.97. After external validation, the results showed the area under the curve was 0.89 (95% CI 0.82-0.97) and the P value of the goodness-of-fit test was 0.24.
CONCLUSIONS: A diagnostic prediction nomogram was established for bladder cancer. The verification results showed that the prediction model has good prediction performance.

BACKGROUND: Urinary bladder cancer (UBC) is the most common malignancy affecting the urinary system. This study aimed to investigate the diagnostic value of combining DAPK methylation in urinary sediment and B ultrasound in the detection of recurrent UBC.
METHODS: A total of 1021 cases with primary UBC who underwent electrocision of bladder tumor through urethra were included in this study and followed up. Various parameters including B ultrasound, DAPK methylation in urinary sediment, examination of exfoliated cells in the urine, and cystoscopy were performed. The data collected was analyzed using the Kappa test, and receiver operating characteristic (ROC) curve was constructed to assess the diagnostic role in recurrent UBC.
RESULTS: Among the 1021 patients, 115 patients experienced recurrence confirmed by cystoscopy and biopsy within two years and were excluded from the study, resulting in an effective sample size of 906 primary UBC cases. The results of cystoscopy showed agreement with B ultrasound (Kappa = 0.785, P < 0.05), as well as with DAPK methylation in urinary sediment, and the combination of B ultrasound and DAPK methylation (Kappa = 0.517, P < 0.05, Kappa = 0.593, P < 0.05). The combination of B ultrasound with DAPK methylation yielded an area under the curve of 0.922, with a sensitivity of 92.86%, specificity of 91.63%, and a negative predictive value of 99.4%, suggesting that a negative result indicates a low risk of recurrence.
CONCLUSIONS: The combination of DAPK methylation in urinary sediment with B ultrasound demonstrates high diagnostic performance for recurrent UBC.