Recognition of Postoperative Cystography Features by Artificial Intelligence to Predict Recovery from Postprostatectomy Urinary Incontinence: A Rapid and Easy Way to Predict Functional Outcome

I-Hung Shao; Hung-Cheng Kan; Hung-Yi Chen; Ying-Hsu Chang; Liang-Kang Huang; Yuan-Cheng Chu; Po-Hung Lin; Kai-Jie Yu; Cheng-Keng Chuang; See-Tong Pang; Chun-Te Wu

doi:10.3390/jpm13010126

Recognition of Postoperative Cystography Features by Artificial Intelligence to Predict Recovery from Postprostatectomy Urinary Incontinence: A Rapid and Easy Way to Predict Functional Outcome

J Pers Med. 2023 Jan 8;13(1):126. doi: 10.3390/jpm13010126.

Authors

I-Hung Shao^{1

2

3}, Hung-Cheng Kan^{1

2}, Hung-Yi Chen⁴, Ying-Hsu Chang^{2

5}, Liang-Kang Huang^{1

2}, Yuan-Cheng Chu^{1

2}, Po-Hung Lin^{1

2}, Kai-Jie Yu^{1

2}, Cheng-Keng Chuang^{1

2}, See-Tong Pang^{1

2}, Chun-Te Wu^{1

2}

Affiliations

¹ Division of Urology, Department of Surgery, Linkou Chang Gung Memorial Hospital, Taoyuan 333005, Taiwan.
² College of Medicine, Chang Gung University, Taoyuan 333323, Taiwan.
³ Graduate Institute of Clinical Medical Sciences, College of Medicine, Chang Gung University, Taoyuan 333323, Taiwan.
⁴ Department of Urology, Chang Gung Memorial Hospital at Keelung, Keelung 204201, Taiwan.
⁵ Division of Urology, Department of Surgery, New Taipei Municipal TuCheng Hospital, Chang Gung Memorial Hospital, New Taipei 236017, Taiwan.

Abstract

Purpose: Post-operative cystography has been used to predict the recovery of postprostatectomy urinary incontinence (PPI) in patients with localized prostate cancer. This study aimed to validate the predictive value of cystography for PPI and utilize a deep learning model to identify favorable and unfavorable features. Methods: Medical records and cystography images of patients who underwent robotic-assisted radical prostatectomy for localized prostate cancer were retrospectively reviewed. Specific cystography features, including anastomosis leakage, a downward bladder neck (BN), and the bladder neck angle, were analyzed for the prediction of PPI recovery. Favorable and unfavorable patterns were categorized based on the three cystography features. The deep learning model used for transfer learning was ResNet 50 and weights were trained on ImageNet. We used 5-fold cross-validation to reduce bias. After each fold, we used a test set to confirm the model’s performance. Result: A total of 170 consecutive patients were included; 31.2% experienced immediate urinary continence after surgery, while 93.5% achieved a pad-free status and 6.5% were still incontinent in the 24 weeks after surgery. We divided patients into a fast recovery group (≤4 weeks) and a slow recovery group (>4 weeks). Compared with the slow recovery group, the fast recovery group had a significantly lower anastomosis leakage rate, less of a downward bladder neck, and a larger bladder neck angle. Test data used to evaluate the model’s performance demonstrated an average 5-fold accuracy, sensitivity, and specificity of 93.75%, 87.5%, and 100%, respectively. Conclusions: Postoperative cystography features can predict PPI recovery in patients with localized prostate cancer. A deep-learning model can facilitate the identification process. Further validation and exploration are required for the future development of artificial intelligence (AI) in this field.

Keywords: artificial intelligence; cystography; deep learning; postprostatectomy incontinence; radical prostatectomy; urinary incontinence.

Grants and funding

This research received no external funding.