Abstract Purpose In the current clinical standard of care, cystoscopic video is not routinely saved because it cumbersome to review. Instead, clinicians rely on brief procedure notes and still frames manage bladder pathology. Preserving discarded data via 3D reconstructions, which are convenient review, has potential improve patient care. However, many videos collected by fiberscopes, lower cost but induce a pattern that inhibits reconstruction. The aim this study remove honeycomb-like...

Cystoscopic video can be cumbersome to review; however, preservation of data in the form 3D bladder reconstructions has potential improve patient care. Unfortunately, not all cystoscopy videos produce viable reconstructions, because their underlying frames contain artifacts such as motion blur and debris, which consequently make them unusable for reconstructions. Here, we develop a real-time pipeline, termed Assessment Feedback Pipeline (AFP), that alerts clinicians when are detected...

Specular reflections (SRs) are highlight artifacts commonly found in endoscopy videos that can severely disrupt a surgeon's observation and judgment. Despite numerous attempts to restore SR, existing methods inefficient time consuming lead false clinical interpretations. Therefore, we propose the first complete deep-learning solution, SpecReFlow, detect SR regions from video with spatial temporal coherence.

In the current clinical standard of care, cystoscopic video is not routinely saved because it cumbersome to review. Instead, clinicians rely on brief procedure notes and still frames manage bladder pathology. Preserving discarded data via 3D reconstructions, which are convenient review, has potential improve patient care. However, many videos collected by fiberscopes, lower cost but induce a pattern that inhibit reconstruction. The aim our study remove honeycomb-like present in...

Objective: 3D reconstruction of the shape and texture hollow organs captured by endoscopy is important for diagnosis surveillance early recurrent cancers. Better evaluation pipelines developed such applications requires easy access to extensive datasets associated ground truths, cost-efficient scalable simulations a range possible clinical scenarios, more reliable insightful metrics assess performance. Methods: We present computer-aided simulation platform cost-effective synthesis monocular...

Cystoscopic data can be used to improve bladder cancer care, but cystoscopic videos are cumbersome review. Alternatively, video preserved in the form of a 3D reconstruction, which is both informative and convenient Developing algorithms for reconstruction an iterative process often requires access clinical data. Unfortunately, time constraints urology workflow inhibit this technical development. In manuscript, we present virtual cystoscopy simulator enable creation realistic customizable...

Specular reflections (SR) commonly found in endoscopy videos can severely disrupt a surgeon's observation and judgment, but existing methods to inpaint SR regions result false clinical interpretations. Therefore, we propose an end-to-end pipeline termed SpecFlow detect restore from videos. Our proposed consists of two phases: detection using reduced U-net model novel restoration method optical flow-guided color propagation. achieves competitive 82.8% Dice score with only 14ms computational...