Smart Colonoscopy Support

A medical technology startup partnered with AAEON to develop an innovative AI-assisted colonoscopy device using the BOXER-8641AI-PLUS. The objective was to increase the detection rate of subtle or ambiguous anomalies such as polyps, lesions, and adenomas during colonoscopies.

Key Platform Requirements

◆ Compliance with electromagnetic compatibility (EMC) standards

◆ Capable of delivering a continuous, high-speed stream of uncompressed image data

◆ Able to remotely update multiple systems at scale

◆ Sufficient AI performance to execute the customer's complex object detection and image classification algorithms

AI-Powered Fall Detection for Smarter Care

In a bid to leverage technological innovation to expedite the response times to falls and improve outcomes for care home residents that suffer falls, AI development company AIRUCA teamed up with AAEON and leading systems integrator Novalux to produce the AI-Behavia FD fall detection system using the BOXER-8621AI, a Compact Fanless Embedded AI System powered by the NVIDIA Jetson Orin Nano with Super Mode.

Key Platform Requirements

◆ Support continuous video streams from up to four network cameras without frame drops

◆ Provide a display interface through which video feeds could be output for local monitoring

◆ Communication protocols capable of triggering alarms or devices to alert staff that a fall had been detected

◆ Strong inferencing capabilities to provide accurate, latency-free analysis of multiple video feeds

Real-Time AI for Critical Care

A system integrator wanted to develop a real-time, AI-powered Intensive Care Unit (ICU) monitoring station capable of analyzing patient vitals signs, detecitng anomalies, and alerting medical staff to potential emergencies.

To do so, they used the MIX-Q670A1 equipped with a GPU powered by the Intel Arc A750E graphics platform.

Key Platform Requirements

◆ Capable of handling large volumes of patient data in real time

◆ Needed support for Wi-Fi and Bluetooth to connect medical IoT devices while ensuring secure data transmission with WPA3 encryption and TPM 2.0

◆ Extremely strong AI performance to detect trends and abnormalities in vital signs without adding excesive computational overhead

◆ Allow for upgrades in processing power, storage, and connectivity over time, ensuring long-term viability

Automating Medication Delivery

Noting the inefficiency of existing medication dispensation on hospital wards, a leading healthcare equipment provider developed an automated medication delivery cart.

To do so, the company employed AAEON's RICO-MX8P, a fanless Pico-ITX single-board computer powered by the NXP i.MX 8M Plus processor platform.

Key Platform Requirements

◆ The platform chosen would need to be installed within a larger robotic unit, so a small form factor was required, and fanless operation was a plus.

◆ The application would need both wired and wireless connectivity, as well as support for RFID card readers and QR code scanners.

◆ The medication delivery cart would require a custom user interface, so the software integration support the chosen embedded partner could offer was an important factor.