Identifying urethral strictures using machine learning: a proof-of-concept evaluation of convolutional neural network model.

Autor: Kim JK; Division of Urology, Department of Surgery, University of Toronto, Toronto, ON, Canada. jjk.kim@mail.utoronto.ca.; Division of Urology, Hospital for Sick Children, 555 University Ave, Toronto, ON, M5G 1X8, Canada. jjk.kim@mail.utoronto.ca., McCammon K; Department of Urology, Eastern Virginia Medical School, Norfolk, VA, USA., Robey C; Department of Urology, Eastern Virginia Medical School, Norfolk, VA, USA., Castillo M; Institute of Urology, St. Luke's Medical Centre, Quezon City, Philippines., Gomez O; Section of Pediatric Imaging, Institute of Radiology, St. Luke's Medical Centre, Quezon City, Philippines., Pua PJL; Section of Pediatric Imaging, Institute of Radiology, St. Luke's Medical Centre, Quezon City, Philippines., Pile F; Institute of Urology, St. Luke's Medical Centre, Quezon City, Philippines., See M 4th; Institute of Urology, St. Luke's Medical Centre, Quezon City, Philippines., Rickard M; Division of Urology, Hospital for Sick Children, 555 University Ave, Toronto, ON, M5G 1X8, Canada., Lorenzo AJ; Division of Urology, Department of Surgery, University of Toronto, Toronto, ON, Canada.; Division of Urology, Hospital for Sick Children, 555 University Ave, Toronto, ON, M5G 1X8, Canada., Chua ME; Division of Urology, Department of Surgery, University of Toronto, Toronto, ON, Canada.; Division of Urology, Hospital for Sick Children, 555 University Ave, Toronto, ON, M5G 1X8, Canada.; Institute of Urology, St. Luke's Medical Centre, Quezon City, Philippines.
Jazyk: angličtina
Zdroj: World journal of urology [World J Urol] 2022 Dec; Vol. 40 (12), pp. 3107-3111. Date of Electronic Publication: 2022 Nov 09.
DOI: 10.1007/s00345-022-04199-6
Abstrakt: Introduction: To evaluate urethral strictures and to determine appropriate surgical reconstructive options, retrograde urethrograms (RUG) are used. Herein, we develop a convolutional neural network (CNN)-based machine learning algorithm to characterize RUG images between those with urethral strictures and those without urethral strictures.
Methods: Following approval from institutional REB from participating institutions (The Hospital for Sick Children [Toronto, Canada], St. Luke's Medical Centre [Quezon City, Philippines], East Virginia Medical School [Norfolk, United States of America]), retrograde urethrogram images were collected and anonymized. Additional RUG images were downloaded online using web scraping method through Selenium and Python 3.8.2. A CNN with three convolutional layers and three pooling layers were built (Fig. 1). Data augmentation was applied with zoom, contrast, horizontal flip, and translation. The data were split into 90% training and 10% testing set. The model was trained with one hundred epochs.
Results: A total of 242 RUG images were identified. 196 were identified as strictures and 46 as normal. Following training, our model achieved accuracy of up to 92.2% with its training data set in characterizing RUG images to stricture and normal images. The validation accuracy using our testing set images showed that it was able to characterize 88.5% of the images correctly.
Conclusion: It is feasible to use a machine learning algorithm to accurately differentiate between a stricture and normal RUG. Further development of the model with additional RUGs may allow characterization of stricture location and length to suggest optimal operative approach for repair.
(© 2022. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)
Databáze: MEDLINE
Externí odkaz: