Background/Objectives: Cystoscopy is necessary for diagnosing bladder cancer, but it has limitations in identifying ambiguous lesions, such as carcinoma in situ (CIS), which leads to a high recurrence rate of bladder cancer. With the significant advancements in deep learning in the medical field, several studies have explored its application in cystoscopy. This study aimed to utilize the VGG19 and Deeplab v3+ deep learning models to classify and segment cystoscope images, respectively. Methods: We classified cystoscope images obtained from 772 patients based on morphology (normal, papillary, flat, mixed) and biopsy results (normal, Ta, T1, T2, CIS, etc.). Experienced urologists annotated and labeled the lesion areas and image categories. The classification model for bladder cancer lesion, annotated with pathological results, was developed using VGG19 with an additional fully connected layer, utilizing sparse categorical cross-entropy as the loss function. The Deeplab v3+ model was used for segmenting each morphological type of bladder cancer in the cystoscope images, employing the dice coefficient loss function. The classification model was evaluated using validation accuracy and correlation with biopsy results, while the segmentation model was assessed using the Intersection over Union (IoU) combined with binary accuracy. Results: The dataset was split into training and validation sets with a 4:1 ratio. The VGG19 classification model achieved an accuracy score of 0.912. The Deeplab v3+ segmentation model achieved an IoU of 0.833 and a binary accuracy of 0.951. Visual analysis revealed a high similarity between the lesions identified by Deeplab v3+ and those labeled by experts. Conclusions: In this study, we applied two deep learning models using well-annotated datasets of cystoscopic images. Both VGG19 and Deeplab v3+ demonstrated high performance in classification and segmentation, respectively. These models can serve as valuable tools for bladder cancer research and may aid in the diagnosis of bladder cancer.

A prostatic urethral lift (PUL) can be performed under local anesthesia in patients normally at high risk for general anesthesia due to multiple comorbidities. However, the clinical efficacy of PULs in patients with multiple comorbidities remains unknown. Therefore, in this this study, we aimed to evaluate the clinical efficacy of the PUL in patients with a high number of comorbidities by comparing its clinical efficacy in these patients with that in healthy individuals. We performed a retrospective observational cohort study, in which patients who underwent a PUL between December 2016 and January 2019 at a single tertiary care center were categorized into two groups: healthy individuals who wanted to preserve sexual function (Group 1) and patients with a high number of comorbidities who were at high risk for general anesthesia, based on an American Society of Anesthesiologists (ASA) score of ≥3 (Group 2). The International Prostate Symptom Score (IPSS), maximum urinary flow rate (Qmax), and post-void residual urine (PVR) were obtained preoperatively and compared throughout the 2-year follow-up. A total of 66 patients were enrolled, of whom 36 patients were included in Group 1 and 30 in Group 2. In Group 1, IPSS, IPSS quality of life (QoL), and Qmax significantly improved and were then maintained during follow-up, whereas, in Group 2, improvements in these parameters were not maintained during follow-up, except for IPSS QoL. Eleven patients (36%) in Group 2 required additional treatment for the recurrence of lower urinary tract symptoms. In conclusion, patients with a high number of comorbidities had a low therapeutic effect after PUL, suggesting a high rate of treatment failure. Therefore, comorbidity status should be considered when evaluating the potential benefits of the PUL procedure during preoperative counseling.