Hardware Integration Testing for Smart Video-based Medical Device Prototypes.

Area of Science:

• Biomedical Engineering
• Medical Imaging
• Embedded Systems

Background:

• Intelligent, camera-based in-body medical devices require rigorous verification.
• Video Capsule Endoscopy (VCE) is a key technology in gastrointestinal diagnostics.
• Existing verification methods may not adequately address real-time performance and error detection for complex devices.

Purpose of the Study:

• To present a novel hardware-in-the-loop (HIL) verification system for intelligent, camera-based in-body medical devices.
• To demonstrate the system's efficacy using a Video Capsule Endoscopy (VCE) prototype.
• To validate the system's capability for real-time performance and automatic error identification.

Main Methods:

• Development of a field-programmable gate array (FPGA)-based HIL verification system.
• Simulation of gastrointestinal (GI) tract traversal by injecting pre-recorded VCE images.
• Integration and testing with a VCE prototype to assess real-time requirements and error detection.

Main Results:

• The HIL system successfully met the real-time operational requirements of the VCE prototype.
• The system demonstrated the capability for automatic identification of errors during simulated use.
• The FPGA-based approach proved effective in simulating complex in-body device scenarios.

Conclusions:

• The developed HIL system provides a robust platform for verifying camera-based in-body medical devices.
• This verification approach facilitates the integration of machine learning (ML) hardware accelerators in medical devices.
• The system enables pre-clinical testing and validation, enhancing device reliability and safety.