Objectives: The aim of this study was to use deep learning (DL) of intraoperative images of urinary stones to predict the composition of urinary stones. In this way, the laser frequency and intensity can be adjusted in real time to reduce operation time and surgical trauma. Materials and methods: A total of 490 patients who underwent holmium laser surgery during the two-year period from March 2021 to March 2023 and had stone analysis results were collected by the stone laboratory. A total of 1658 intraoperative stone images were obtained. The eight stone categories with the highest number of stones were selected by sorting. Single component stones include calcium oxalate monohydrate (W1), calcium oxalate dihydrate (W2), magnesium ammonium phosphate hexahydrate, apatite carbonate (CH) and anhydrous uric acid (U). Mixed stones include W2 + U, W1 + W2 and W1 + CH. All stones have intraoperative videos. More than 20 intraoperative high-resolution images of the stones, including the surface and core of the stones, were available for each patient via FFmpeg command screenshots. The deep convolutional neural network (CNN) ResNet-101 (ResNet, Microsoft) was applied to each image as a multiclass classification model. Results: The composition prediction rates for each component were as follows: calcium oxalate monohydrate 99% (n = 142), calcium oxalate dihydrate 100% (n = 29), apatite carbonate 100% (n = 131), anhydrous uric acid 98% (n = 57), W1 + W2 100% (n = 82), W1 + CH 100% ( n = 20) and W2 + U 100% (n = 24). The overall weighted recall of the cellular neural network component analysis for the entire cohort was 99%. Conclusion: This preliminary study suggests that DL is a promising method for identifying urinary stone components from intraoperative endoscopic images. Compared to intraoperative identification of stone components by the human eye, DL can discriminate single and mixed stone components more accurately and quickly. At the same time, based on the training of stone images in vitro, it is closer to the clinical application of stone images in vivo. This technology can be used to identify the composition of stones in real time and to adjust the frequency and energy intensity of the holmium laser in time. The prediction of stone composition can significantly shorten the operation time, improve the efficiency of stone surgery and prevent the risk of postoperative infection.

A pan-cancer study of PD-1 and CTLA-4 as therapeutic targets Zongqiang Cai, Xiaojie Ang, Zekun Xu, Shiqing Li, Jianglei Zhang, Changsong Pei, Feng Zhou

Introduction: 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. Materials and 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. Conclusion: 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.

This retrospective study aims to examine the correlation between calcium oxalate (CaOx) stones and common clinical tests, as well as urine ionic composition. Additionally, we aim to develop and implement a personalized model to assess the accuracy and feasibility of using charts to predict calcium oxalate stones in patients with urinary tract stones. A retrospective analysis was conducted on data from 960 patients who underwent surgery for urinary stones at the First Affiliated Hospital of Soochow University from January 1, 2010, to December 31, 2022. Among these patients, 447 were selected for further analysis based on screening criteria. Multivariate logistic regression analysis was then performed to identify the best predictive features for calcium oxalate stones from the clinical data of the selected patients. A prediction model was developed using these features and presented in the form of a nomogram graph. The performance of the prediction model was assessed using the C-index, calibration curve, and decision curve, which evaluated its discriminative power, calibration, and clinical utility, respectively. The nomogram diagram prediction model developed in this study is effective in predicting calcium oxalate stones which is helpful in screening and early identification of high-risk patients with calcium oxalate urinary tract stones, and may be a guide for urologists in making clinical treatment decisions.

Background: Enhancer RNA (eRNA) is a non-coding RNA transcribed by enhancers and has a crucial role in controlling gene transcription. However, the potential functions of eRNA in prostate cancer (PCa) are still not fully understood. Methods: Clinical information and expression data of eRNAs and their target genes for PCa were downloaded from TCGA. Each eRNA in PCa samples was divided into high- and low-expression groups. The Kaplan–Meier method was used to identify the eRNAs significantly associated with the overall survival of PCa. Their correlations with age, prostate-specific antigen (PSA), and tumor stage were analyzed using Spearman coefficients. Finally, Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEEG) analyzes were used to predict the possible biological functions and pathways associated with eRNAs. Results: We identified 12 eRNAs associated with PCa survival, of which PARGP1 was the most clinically significant. It was associated with biochemical recurrence in PCa patients and was also a valuable complement to distinguish between PSA 0–4 ng/ml and 4–10 ng/ml. GO, and KEEG analysis showed that herpes simplex virus-1 infection was the most biologically significant enriched process. Conclusions: PARGP1 is associated with biochemical recurrence in prostate cancer and contributes to assessing the outcome.

Large cell neuroendocrine carcinoma of the prostate is an extremely rare malignant subgroup with limited reported cases. Little is known about its pathological characteristics, treatment options and long-term prognosis. In this case, we report a young patient presenting with painless gross hematuria for 3 months, accompanied with elevated serum total prostate-specific antigen (tPSA) level of 83.7 ng/ml. Magnetic resonance imaging (MRI) and 18F-FDG Positron Emission Tomography - Computed Tomography (¹⁸F-FDG PET/CT) indicated giant prostate mass, which metastasized to bilateral lungs, bones and lymph nodes. Prostate biopsy and transurethral resection of the prostate confirmed the diagnosis of adenocarcinoma with a Gleason score of 4 + 5. After receiving 12 months of goserelin acetate, rezvilutamide and six cycles of docetaxel, the patient further underwent laparoscopic radical prostatectomy (LRP). Immunohistochemical analysis (Syn+/CgA+/AR−) combined with treatment history revealed a histopathological diagnosis of treatment-related LCNEPC. Subsequently, the patient then received immunotherapy with serplulimab (300 mg) and the EP regimen (combining etoposide and cisplatin) chemotherapy. After six cycles of chemo-immunotherapy, further examination indicated reduction in size of multiple lymph nodes and lung metastases by March 2025. Here we reported a rare case of treatment-related LCNEPC, who had experienced systematic therapy with comprehensive care. These diagnostic and therapeutic approaches may improve the management capability and highlight the critical role of multimodal strategies in the subsequent cases.