Treatment of medium- to large-sized renal stones is safe and highly effective by both UMP and fURS. Moreover, both treatments yield comparable postsurgical analgesic requirements and high patient satisfaction scores. Patient-related factors (anatomical and stone related) and availability of technical equipment and surgical expertise appear to be the most important determining factors in treatment planning.
UMP and fURS are both safe and effective in the treatment of medium-size urinary stones. Costs for endoscopes and disposable materials are significantly lower in UMP.
Background
Optimal detection and surveillance of bladder cancer (BCa) rely primarily on the cystoscopic visualization of bladder lesions. AI-assisted cystoscopy may improve image recognition and accelerate data acquisition.
Objective
To provide a comprehensive review of machine learning (ML), deep learning (DL) and convolutional neural network (CNN) applications in cystoscopic image recognition.
Evidence acquisition
A detailed search of original articles was performed using the PubMed-MEDLINE database to identify recent English literature relevant to ML, DL and CNN applications in cystoscopic image recognition.
Evidence synthesis
In total, two articles and one conference abstract were identified addressing the application of AI methods in cystoscopic image recognition. These investigations showed accuracies exceeding 90% for tumor detection; however, future work is necessary to incorporate these methods into AI-aided cystoscopy and compared to other tumor visualization tools. Furthermore, we present results from the RaVeNNA-4pi consortium initiative which has extracted 4200 frames from 62 videos, analyzed them with the U-Net network and achieved an average dice score of 0.67. Improvements in its precision can be achieved by augmenting the video/frame database.
Conclusion
AI-aided cystoscopy has the potential to outperform urologists at recognizing and classifying bladder lesions. To ensure their real-life implementation, however, these algorithms require external validation to generalize their results across other data sets.
Ho:YAG laser lithotripsy might be safe provided that there is sufficient irrigation. However, high power and low irrigation resulted in potentially tissue-damaging temperatures. Laser devices should, therefore, always be applied in conjunction with continuous, closely monitored irrigation whenever performing Ho:YAG laser lithotripsy.
Background
Cost-effective methods to facilitate practical medical education are in high demand and the “mixed-reality” (MR) technology seems suitable to provide students with instructions when learning a new practical task. To evaluate a step-by-step mixed reality (MR) guidance system for instructing a practical medical procedure, we conducted a randomized, single-blinded prospective trial on medical students learning bladder catheter placement.
Methods
We enrolled 164 medical students. Students were randomized into 2 groups and received instructions on how to perform bladder catheter placement on a male catheterization training model. One group (107 students) were given their instructions by an instructor, while the other group (57 students) were instructed via an MR guidance system using a Microsoft HoloLens. Both groups did hands on training. A standardized questionnaire covering previous knowledge, interest in modern technologies and a self-evaluation was filled out. In addition, students were asked to evaluate the system’s usability. We assessed both groups’s learning outcome via a standardized OSCE (objective structured clinical examination).
Results
Our evaluation of the learning outcome revealed an average point value of 19.96 ± 2,42 for the control group and 21.49 ± 2.27 for the MR group - the MR group’s result was significantly better (p = 0.00). The self-evaluations revealed no difference between groups, however, the control group gave higher ratings when evaluating the quality of instructions. The MR system’s assessment showed less usability, with a cumulative SUS (system usability scale) score of 56.6 (lower half) as well as a cumulative score of 24.2 ± 7.3 (n = 52) out of 100 in the NASA task load index.
Conclusions
MR is a promising tool for instructing practical skills, and has the potential to enable superior learning outcomes. Advances in MR technology are necessary to improve the usability of current systems.
Trial registration
German Clinical Trial Register ID: DRKS00013186
Objectives: Due to the increasing fragility of the instruments and rising concerns about the sterility of reprocessable scopes, several single-use devices for flexible ureteroscopy have been introduced. In this study, we compare currently available disposable digital and fiberoptic flexible ureteroscopes with a contemporary reusable fiberoptic device. Materials and Methods: LithoVueÔ, Pusen Uscope Ò (UE3011, UE3022), Flexor Ò VueÔ, and a reusable fiber optic flexible ureteroscope (BOA vision Ò) were tested in kidney models. The setup included (1) visualization of all calices (correct assignment of colored pearls) and (2) the extraction of human calculi with a standard disposable extraction device (NGage Ò). We documented the effective visualization, stone extraction, and times to completion. In addition, the surgeons' workload and performance were determined using the National Aeronautics and Space Administration-Task Load Index. Results: In visualizing and identifying calices, the LithoVue and both generations of the Uscope performed similarly, but time to completion was significantly longer for all single-use devices in comparison with the Boa Vision. LithoVue retracted stones almost as well as the reusable scope (97% vs 95%/82%/96% stone clearance), while accessibility was impeded using Uscope UE3011, as reflected by the retrieval time per stone (73 vs 102 seconds/stone). This disadvantage has, however, been overcome with the new Uscope Generation UE3022, showing a retrieval time of only 65 seconds per stone, excelling over the reusable scope in this category. The Uscope UE3022 image quality was also rated best, but showed no significant difference. Conclusions: In comparison with disposable ureteroscopes available, LithoVue offers performance and characteristics similar to a reusable device, while the FlexorVu's performance does not yet yield satisfactory results for clinical use. The first generation of Uscope exhibits potential, but requires further technical improvements to match the performance of a reusable device. With the new-generation UE3022, Pusen has made significant improvement and offers a quality comparable with the LithoVue's.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.