Micro C Medical Imaging System, M01

The Micro C Medical Imaging System, M01 is a handheld X-ray device designed for point-of-care diagnostic imaging of adult and pediatric extremities, utilizing a three-component system (emitter, cassette, control unit) and computer vision for positioning. This version introduces AiLARA, a static AI-based software algorithm that automatically recommends exposure settings to optimize image quality and radiation dose, validated through non-clinical phantom studies and usability evaluations.

The Micro C Medical Imaging System, M01 is a handheld, mobile X-ray system designed for point-of-care diagnostic imaging of distal extremities in both adult and pediatric patients. It comprises three main components: an Emitter (containing the X-ray tube, operator controls, and a computer vision camera for positioning), a Cassette (housing the X-ray detector and positioning aids), and a Control Unit (with the high-voltage generator and computing hardware). The system facilitates static and serial radiographic exposures, allowing clinicians to select technique factors or utilize its new AI-driven modes. It interfaces with external displays and input devices and supports image viewing, adjustment, and transfer to PACS or flash drives. The primary update in this iteration of the Micro C system is the integration of AiLARA (Artificial Intelligence Low As Reasonably Achievable) software, featuring "Single AiLARA" and "Serial AiLARA" modes. This static AI-based algorithm automatically determines and recommends X-ray power settings and exposure times without requiring manual user input, aiming to optimize image acquisition, ensure clinically relevant images, and reduce overexposures or retakes. Non-clinical performance data validated the AiLARA software: algorithm verification confirmed its learning from a dataset, software verification showed it met requirements, image quality studies using phantoms demonstrated diagnostic relevance across various anatomies and configurations, and radiation dose testing confirmed outputs were below diagnostic reference levels and comparable to manual modes, including for small/pediatric anatomies. Usability evaluations with licensed professionals also confirmed the system's effectiveness with the new AiLARA modes.

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. How does the AiLARA algorithm's performance in determining exposure parameters compare to experienced radiographers' manual selections across a diverse range of patient sizes and anatomical variations beyond the tested phantoms?; What is the learning curve for clinicians transitioning from manual X-ray systems to the AiLARA-assisted modes, particularly regarding trust in the AI's recommendations and override frequency?; Beyond dose reduction and image consistency, are there measurable improvements in diagnostic accuracy or workflow efficiency (e.g., time to diagnosis, reduced retake rates in clinical practice) with the AiLARA system?; How robust is the computer vision positioning system in accurately aligning the emitter and cassette in challenging clinical environments or with uncooperative patients?; What are the specific failure modes of the AiLARA algorithm, and what safeguards are in place if the AI suggests a clinically inappropriate exposure, especially for sensitive populations like pediatric patients?