SonoGif

SonoGif de-identifies ultrasound clips by removing protected health information from both metadata and image content to facilitate safe sharing for medical education and research.

Key Features:

• Browser-based processing: JavaScript runs entirely within the web browser, ensuring ultrasound clips remain on the user's device during initial processing.
• DICOM parsing: DICOM files are parsed using the open-source dicomParser library.
• Video rendering: Standard video formats are rendered with native HTML5 Canvas APIs.
• Manual PHI annotation: Users can manually annotate images to obscure on-screen protected health information.
• Server-side compilation: De-identified frames are transmitted to a secure server where FFmpeg compiles them into shareable video formats.

Scientific Applications:

• Point-of-care ultrasound education: Enables de-identification and sharing of ultrasound clips for online medical education in point-of-care ultrasound.
• Clinical research: Facilitates sharing of ultrasound media for research while maintaining compliance with HIPAA standards.
• Global medical education: Supports ultrasound education in diverse clinical environments including low-resource settings.

Methodology:

SonoGif uses JavaScript for browser-based processing, the dicomParser library for DICOM file parsing, native HTML5 Canvas APIs for video rendering, manual user annotation for on-screen PHI obscuration, and FFmpeg on a secure server for compiling de-identified frames into shareable video formats.