Plenary: Next Frontier, Sunday, Afternoon Session
Presentation Authors: Eugene Shkolyar*, Xiao Jia, Lei Xing, Joseph Liao, Stanford, CA
Introduction: Over 1 million cystoscopies are performed annually in the United States for detection and surveillance of bladder cancer. Adequate identification of suspicious lesions is critical to minimizing recurrence and progression rates, however standard cystoscopy misses up to 20% of bladder cancer. Access to adjunct imaging technology may be limited by cost and availability of experienced personnel. Machine learning holds the potential to enhance medical decision-making in cancer detection and imaging. We aimed to develop a deep-learning algorithm for augmented detection of bladder cancer during standard cystoscopy.
Methods: With IRB approval, videos of office-based cystoscopy and transurethral resection of bladder tumor from 100 subjects (141 videos) were prospectively collected and annotated. For algorithm development, video frames (n=611) containing histologically confirmed papillary bladder cancer were selected and tumor outlined (green line, Figure). Bladder neck, ureteral orifices, and air bubble were labeled for exclusion learning. “TUMNet”, an image analysis platform based on convolutional neural networks, was developed to evaluate videos in two stages: 1) recognition of frames containing abnormal areas and 2) segmentation of regions within the frame occupied by tumor. A training set was constructed based on 95 subjects (417 cancer and 2,335 normal frames). A validation set was constructed based on 5 subjects (211 cancer, 1,002 normal frames). An ongoing prospective study is underway to evaluate TUMNet performance.
Results: In the validation set, TUMNet per-frame sensitivity was 88% (186/211) and per-tumor sensitivity was 90% (9/10) with a per-frame specificity of 99% (992/1002). TUMNet accurately detected all 16 tumors that were resected in the ongoing prospective test cohort (n=9; 15 cancer, 1 benign).
Conclusions: We have created a deep-learning algorithm that accurately detects papillary bladder cancers. Computer augmented cystoscopy may aid in diagnostic decision-making to improve diagnostic yield and standardize performance across providers.
Source of Funding: None