Endoshare: A Publicly Available, Surgeons-Friendly Solution to De-Identify and Manage Surgical Videos

TL;DR

This paper tackles the barriers to surgical video sharing posed by heterogeneous recording formats and privacy concerns by introducing Endoshare, a publicly available, surgeon-friendly tool that merges, standardizes, and de-identifies endoscopic videos. Built with a three-layer architecture and an AI-assisted de-identification pipeline, Endoshare supports cross-platform deployment and configurable processing modes, validated through usability surveys and multi-hardware performance benchmarks. The study demonstrates high user acceptance, robust cross-platform performance, and an auditable, open codebase that facilitates training, multicenter research, and quality improvement while preserving patient privacy. Realizing its full impact will require broader interoperability validation and larger-scale usability studies, but Endoshare represents a significant step toward scalable, privacy-preserving surgical video data sharing and analysis.

Abstract

Video-based assessment and surgical data science can advance surgical training, research, and quality improvement, yet adoption remains limited by heterogeneous recording formats and privacy concerns linked to video sharing. This work develops, evaluates, and publicly releases Endoshare, a surgeon-friendly application that merges, standardizes, and de-identifies endoscopic videos. Development followed an iterative, user-centered software life cycle. In the analysis phase, an internal survey of four clinicians and four computer scientists, based on 10 usability heuristics, identified early requirements and guided a cross-platform, privacy-by-design architecture. Prototype testing reported high usability for clinicians (4.68 +/- 0.40 out of 5) and for computer scientists (4.03 +/- 0.51 out of 5), with the lowest score (4.00 +/- 0.93 out of 5) relating to label clarity, prompting interface refinement to streamline case selection, video merging, automated out-of-body removal, and filename pseudonymization. In the testing phase, ten surgeons completed an external survey combining the same heuristics with Technology Acceptance Model constructs, reporting high perceived usefulness (5.07 +/- 1.75 out of 7), ease of use (5.15 +/- 1.71 out of 7), heuristic usability (4.38 +/- 0.48 out of 5), and strong recommendation likelihood (9.20 +/- 0.79 out of 10). A performance assessment across different hardware and configurations showed that processing time increased proportionally with video duration and was consistently lower in fast mode. Endoshare is a publicly available solution to manage surgical videos, with potential to support training, research, and quality improvement. Compliance certification and broader interoperability validation are needed to establish it as a reliable tool for surgical video management. The software is available at https://camma-public.github.io/Endoshare

Figures (6)

• Figure 1: Endoshare architecture and interface.
• Figure 2: Overview of the Endoshare processing pipeline. A) Video merging and standardization combine disparate clips into a single, uniform file; B) File pseudonymization replaces patient identifiers with randomized tokens and strips all embedded metadata; C) AI-powered de-identification detects camera insertion frames, automatically blurs out-of-body scenes, and ensures any remaining identifiable content is masked.
• Figure 3: Distribution of user practices in surgical video workflows across four domains. A) preferred recording methods; B) long-term storage locations; C) intended video audiences; and D) reuse contexts for surgical videos.
• Figure 4: Radar chart summarizing usability evaluations across three domains: Perceived Usefulness (PU), Perceived Ease of Use (PEOU), and Heuristic Usability (Heur). Each axis represents a grouped construct—PU (Efficiency, Impact, Process Ease), PEOU (Learning, Usability, Adaptability), and Heur (Feedback, Control & Error, Efficiency)—with mean scores plotted (blue line) and annotated values.
• Figure 5: Benchmarking Endoshare performance. Processing speed of Endoshare across three hardware configurations (macOS laptop, Windows average desktop, Linux high-end desktop) for 1-, 30-, and 60-minute videos in both fast and advanced modes. Bars indicate geometric mean processing time relative to video duration.