Eugene Shkolyar1, Xiao Jia2, Timothy C Chang1, Dharati Trivedi1, Kathleen E Mach1, Max Q-H Meng3, Lei Xing4, Joseph C Liao5. 1. Department of Urology, Stanford University School of Medicine, Stanford, CA, USA; Veterans Affairs Palo Alto Health Care System, Palo Alto, CA, USA. 2. Department of Radiation Oncology, Stanford University School of Medicine, Stanford, CA, USA; Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong. 3. Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong. 4. Department of Radiation Oncology, Stanford University School of Medicine, Stanford, CA, USA. Electronic address: lei@stanford.edu. 5. Department of Urology, Stanford University School of Medicine, Stanford, CA, USA; Veterans Affairs Palo Alto Health Care System, Palo Alto, CA, USA. Electronic address: jliao@stanford.edu.
Abstract
Adequate tumor detection is critical in complete transurethral resection of bladder tumor (TURBT) to reduce cancer recurrence, but up to 20% of bladder tumors are missed by standard white light cystoscopy. Deep learning augmented cystoscopy may improve tumor localization, intraoperative navigation, and surgical resection of bladder cancer. We aimed to develop a deep learning algorithm for augmented cystoscopic detection of bladder cancer. Patients undergoing cystoscopy/TURBT were recruited and white light videos were recorded. Video frames containing histologically confirmed papillary urothelial carcinoma were selected and manually annotated. We constructed CystoNet, an image analysis platform based on convolutional neural networks, for automated bladder tumor detection using a development dataset of 95 patients for algorithm training and five patients for testing. Diagnostic performance of CystoNet was validated prospectively in an additional 54 patients. In the validation dataset, per-frame sensitivity and specificity were 90.9% (95% confidence interval [CI], 90.3-91.6%) and 98.6% (95% CI, 98.5-98.8%), respectively. Per-tumor sensitivity was 90.9% (95% CI, 90.3-91.6%). CystoNet detected 39 of 41 papillary and three of three flat bladder cancers. With high sensitivity and specificity, CystoNet may improve the diagnostic yield of cystoscopy and efficacy of TURBT. PATIENT SUMMARY: Conventional cystoscopy has recognized shortcomings in bladder cancer detection, with implications for recurrence. Cystoscopy augmented with artificial intelligence may improve cancer detection and resection.
Adequate tumor detection is critical in complete transurethral resection of bladder tumor (TURBT) to reduce cancer recurrence, but up to 20% of bladder tumors are missed by standard white light cystoscopy. Deep learning augmented cystoscopy may improve tumor localization, intraoperative navigation, and surgical resection of bladder cancer. We aimed to develop a deep learning algorithm for augmented cystoscopic detection of bladder cancer. Patients undergoing cystoscopy/TURBT were recruited and white light videos were recorded. Video frames containing histologically confirmed papillary urothelial carcinoma were selected and manually annotated. We constructed CystoNet, an image analysis platform based on convolutional neural networks, for automated bladder tumor detection using a development dataset of 95 patients for algorithm training and five patients for testing. Diagnostic performance of CystoNet was validated prospectively in an additional 54 patients. In the validation dataset, per-frame sensitivity and specificity were 90.9% (95% confidence interval [CI], 90.3-91.6%) and 98.6% (95% CI, 98.5-98.8%), respectively. Per-tumor sensitivity was 90.9% (95% CI, 90.3-91.6%). CystoNet detected 39 of 41 papillary and three of three flat bladder cancers. With high sensitivity and specificity, CystoNet may improve the diagnostic yield of cystoscopy and efficacy of TURBT. PATIENT SUMMARY: Conventional cystoscopy has recognized shortcomings in bladder cancer detection, with implications for recurrence. Cystoscopy augmented with artificial intelligence may improve cancer detection and resection.
Authors: Martin E Gosnell; Dmitry M Polikarpov; Ewa M Goldys; Andrei V Zvyagin; David A Gillatt Journal: Urol Oncol Date: 2017-09-25 Impact factor: 3.498
Authors: Robert S Svatek; Brent K Hollenbeck; Sten Holmäng; Richard Lee; Simon P Kim; Arnulf Stenzl; Yair Lotan Journal: Eur Urol Date: 2014-01-21 Impact factor: 20.096
Authors: Maxim J McKibben; E Will Kirby; Joshua Langston; Mathew C Raynor; Matthew E Nielsen; Angela B Smith; Eric M Wallen; Michael E Woods; Raj S Pruthi Journal: Urology Date: 2016-08-01 Impact factor: 2.649
Authors: Francesco Greco; Jeffrey A Cadeddu; Inderbir S Gill; Jihad H Kaouk; Mesut Remzi; R Houston Thompson; Fijs W B van Leeuwen; Henk G van der Poel; Paolo Fornara; Jens Rassweiler Journal: Eur Urol Date: 2013-08-07 Impact factor: 20.096
Authors: Andreas Kleppe; Ole-Johan Skrede; Sepp De Raedt; Knut Liestøl; David J Kerr; Håvard E Danielsen Journal: Nat Rev Cancer Date: 2021-01-29 Impact factor: 60.716
Authors: M C Kriegmair; S Hein; D S Schoeb; H Zappe; R Suárez-Ibarrola; F Waldbillig; B Gruene; P-F Pohlmann; F Praus; K Wilhelm; C Gratzke; A Miernik; C Bolenz Journal: Urologe A Date: 2020-12-10 Impact factor: 0.639
Authors: Okyaz Eminaga; T Jessie Ge; Eugene Shkolyar; Mark A Laurie; Timothy J Lee; Lukas Hockman; Xiao Jia; Lei Xing; Joseph C Liao Journal: J Med Syst Date: 2022-10-03 Impact factor: 4.920
Authors: Andrew B Chen; Taseen Haque; Sidney Roberts; Sirisha Rambhatla; Giovanni Cacciamani; Prokar Dasgupta; Andrew J Hung Journal: Urol Clin North Am Date: 2021-10-23 Impact factor: 2.766