Endoshare: a publicly available, surgeons-friendly solution to de-identify and manage surgical videos

Video-based assessment and surgical data science can advance surgical training, research, and quality improvement. However, widespread use of surgical videos is limited by heterogeneous recording formats and privacy concerns associated with sharing potentially sensitive data. The work presents the development, implementation, evaluation, and public release of Endoshare, a surgeon-friendly application that merges, standardizes, and de-identifies endoscopic videos.

Development followed the first four phases of the software development life cycle (analysis, design, implementation, testing), using iterative user-centered evaluations to guide system refinement. In the initial analysis phase, an internal survey of clinicians and computer scientists, using 10 usability heuristics, identified early requirements. These findings guided design and implementation toward a cross-platform, privacy-by-design architecture. In the final testing phase, an external clinician survey combined the same heuristics with Technology Acceptance Model constructs to evaluate usability and adoption, complemented by a performance assessment across different hardware and configurations. Statistical evaluation used standard descriptive and inferential methods.

In the analysis phase, four clinicians and four computer scientists tested a prototype, reporting high usability (4.68 ± 0.40/5 and 4.03 ± 0.51/5). The lowest score (4.00 ± 0.93/5) concerned the clarity of labels, indicating a need to make functions easier to recognize. The application's user experience was refined to ensure minimal effort for case selection, video merging, automated out-of-body detection and removal, and filename pseudonymization. In the testing phase, 10 surgeons reported high perceived usefulness (5.07 ± 1.75/7), ease of use (5.15 ± 1.71/7), heuristic usability (4.38 ± 0.48/5), and recommended the system (9.20 ± 0.79/10). Benchmarking showed that processing time increased proportionally with video duration and was consistently lower in fast mode (≈ 79% faster).

Endoshare is a publicly available surgeon-friendly solution to manage, standardize, and de-identify surgical videos. Endoshare could facilitate the use and sharing of valuable surgical video data for surgical training, research, and quality improvement. Compliance certification and broader interoperability validation are needed to establish it as a reliable tool.