Artificial intelligence and neural networks in urology: current clinical applications

Checcucci, Enrico; Autorino, Riccardo; Cacciamani, Giovanni; Amparore, Daniele; Cillis, Sabrina De; Piana, Alberto; Piazzolla, Pietro; Vezzetti, Enrico; Fiori, Cristian; Veneziano, Domenico; Tewari, Ash; Dasgupta, Prokar; Hung, Andrew J.; Gill, Inderbir S.; Porpiglia, Francesco; Uro-technology,

doi:10.23736/s0393-2249.19.03613-0

Cited by 117 publications

(75 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Nevertheless, it should be noted that the rate of PSMs reported in the present study is still more than acceptable for a learning curve series. New imaging technologies and tools for image‐guided surgical navigation are promising and will allow real‐time understanding of surgical anatomy, which will probably help in lowering the PSM rates during the learning curve process [22].…”

Section: Discussionmentioning

confidence: 99%

Retzius‐sparing robot‐assisted radical prostatectomy: early learning curve experience in three continents

et al. 2020

View full text Add to dashboard Cite

Objective To assess the effect of surgical experience on peri‐operative, functional and oncological outcomes during the first 50 Retzius‐sparing robot‐assisted radical prostatectomy (RsRARP) cases performed by surgeons naïve to this novel approach. Materials and Methods We retrospectively evaluated the initial cases operated by 14 surgeons in 12 different international centres. Pre‐, peri‐ and postoperative features of the first 50 patients operated by each surgeon in all the participating centres were collected. The effect of surgical experience on peri‐operative, functional and oncological outcomes was firstly evaluated after stratification by level of surgical experience (initial [≤25 cases] and expert [>25 cases]) and after using locally weighted scatterplot smoothing to graphically explore the relationship between surgical experience and the outcomes of interest. Results We evaluated 626 patients. The median follow‐up was 13 months in the initial group and 9 months in the expert group (P = 0.002). Preoperative features overlapped between the two groups. Shorter console time (140 vs 120 min; P = 0.001) and a trend towards lower complications rates (13 vs 5.5%; P = 0.038) were observed in the expert group. The relationship between surgical experience and console time, immediate urinary continence recovery and Clavien–Dindo grade ≥2 complications was linear, without reaching a plateau, after 50 cases. Conversely, a non‐linear relationship was observed between surgical experience and positive surgical margins (PSMs). Conclusions In this first report of a multicentre experience of RsRARP during the learning curve, we found that console time, immediate urinary continence recovery and postoperative complications are optimal from the beginning and further quickly improve during the learning process, while PSM rates did not clearly improve over the first 50 cases.

show abstract

Section: Discussionmentioning

confidence: 99%

Retzius‐sparing robot‐assisted radical prostatectomy: early learning curve experience in three continents

et al. 2020

View full text Add to dashboard Cite

show abstract

“…AI has an increasing potential role in urology diagnostics. [8][9][10] In our previous studies on endourology, we performed anomaly detection based on the transfer learning technique of deep learning. We demonstrated that features…”

Section: Discussionmentioning

confidence: 99%

Cystoscopic Imaging for Bladder Cancer Detection Based on Stepwise Organic Transfer Learning with a Pretrained Convolutional Neural Network

Ikeda

Nosato

Kochi

et al. 2021

Journal of Endourology

View full text Add to dashboard Cite

Background: Nonmuscle-invasive bladder cancer is diagnosed, treated, and monitored using cystoscopy. Artificial intelligence (AI) is increasingly used to augment tumor detection, but its performance is hindered by the limited availability of cystoscopic images required to form a large training data set. This study aimed to determine whether stepwise transfer learning with general images followed by gastroscopic images can improve the accuracy of bladder tumor detection on cystoscopic imaging. Materials and Methods: We trained a convolutional neural network with 1.2 million general images, followed by 8728 gastroscopic images. In the final step of the transfer learning process, the model was additionally trained with 2102 cystoscopic images of normal bladder tissue and bladder tumors collected at the University of Tsukuba Hospital. The diagnostic accuracy was evaluated using a receiver operating characteristic curve. The diagnostic performance of the models trained with cystoscopic images with or without stepwise organic transfer learning was compared with that of medical students and urologists with varying levels of experience. Results: The model developed by stepwise organic transfer learning had 95.4% sensitivity and 97.6% specificity. This performance was better than that of the other models and comparable with that of expert urologists. Notably, it showed superior diagnostic accuracy when tumors occupied >10% of the image. Conclusions: Our findings demonstrate the value of stepwise organic transfer learning in applications with limited data sets for training and further confirm the value of AI in medical diagnostics. Here, we applied deep learning to develop a tool to detect bladder tumors with an accuracy comparable with that of a urologist. To address the limitation that few bladder tumor images are available to train the model, we demonstrate that pretraining with general and gastroscopic images yields superior results.

show abstract

“…These results provide an opportunity to solve the problem for researchers in other medical fields. For example, in previous studies of urology, AI algorithms have been applied for the prediction of prostate biopsy results and the recurrence-free probability of bladder cancer [35]. In addition, the in-hospital and long-term mortalities of patients with cardiovascular diseases have been predicted using AI algorithms in several previous studies.…”

Section: Discussionmentioning

confidence: 99%

Artificial intelligence algorithm to predict the need for critical care in prehospital emergency medical services

Kang

Cho²,

Kwon³

et al. 2020

Scand J Trauma Resusc Emerg Med

View full text Add to dashboard Cite

Background: In emergency medical services (EMSs), accurately predicting the severity of a patient's medical condition is important for the early identification of those who are vulnerable and at high-risk. In this study, we developed and validated an artificial intelligence (AI) algorithm based on deep learning to predict the need for critical care during EMS. Methods: We conducted a retrospective observation cohort study. The algorithm was established using development data from the Korean national emergency department information system, which were collected during visits in real time from 151 emergency departments (EDs). We validated the algorithm using EMS run sheets from two EDs. The study subjects comprised adult patients who visited EDs. The endpoint was critical care, and we used age, sex, chief complaint, symptom onset to arrival time, trauma, and initial vital signs as the predicted variables. Results: The number of patients in the development data was 8,981,181, and the validation data comprised 2604 EMS run sheets from two hospitals. The area under the receiver operating characteristic curve of the algorithm to predict the critical care was 0.867 (95% confidence interval, [0.864-0.871]). This result outperformed the Emergency Severity Index (0.839 [0.831-0.846]), Korean Triage and Acuity System (0.824 [0.815-0.832]), National Early Warning Score (0.741 [0.734-0.748]), and Modified Early Warning Score (0.696 [0.691-0.699]). Conclusions: The AI algorithm accurately predicted the need for the critical care of patients using information during EMS and outperformed the conventional triage tools and early warning scores.

show abstract

Artificial intelligence and neural networks in urology: current clinical applications

Cited by 117 publications

References 49 publications

Retzius‐sparing robot‐assisted radical prostatectomy: early learning curve experience in three continents

Retzius‐sparing robot‐assisted radical prostatectomy: early learning curve experience in three continents

Cystoscopic Imaging for Bladder Cancer Detection Based on Stepwise Organic Transfer Learning with a Pretrained Convolutional Neural Network

Artificial intelligence algorithm to predict the need for critical care in prehospital emergency medical services

Contact Info

Product

Resources

About