IEI group provides total solution for AI healthcare application, from big data management (NAS) , AI training (AI training platform, training machine and accelerator card) to AI inference (web based platform, inference machine both stand alone and embedded system)
Because colon cancer could occur everywhere in the large intestine, the medical personnel need to be very cautious when doing colonoscopy. This application assists the doctor to pay more attention when inflammation, infections, ulcers, polyps or any other abnormal tissues are detected in a gastrointestinal tract inspection. We try to reduce the human error resulting from fatigue or distraction in the daily clinical work
Age-related macular degeneration is a leading cause of vision loss. It destroys the macular, the part of the eye that provides sharp, central vision needed for seeing objects clearly.
The HTB-100, a high-performance and reliable medical grade embedded system developed by IEI, can be used as a device for AI inference in brain tumor diagnosis by adding a VPU & GPU accelerator card, benefiting from its flexible expansion feature.
In brain tumor treatment, cyberknife is one of the common methods currently used. It is equipped with a linear accelerator on a robotic arm with two X-ray cameras to precisely position and delivers radiation beams to destroy tumor cells.
In traditional process, to create a brain tumor treatment plan, at least two doctors have to manually mark and shape the brain tumor in every picture. It usually takes a whole day to get only one case done due to its complex and sophisticated process. After using the AI inference application, identifying brain tumor becomes automatic, taking only a few seconds to analyze. It is more time saving and more precise while reducing workload of doctors and avoiding errors.
Intel® Distribution of OpenVINO™ toolkit is based on convolutional neural networks (CNN), the toolkit extends workloads across multiple types of Intel® platforms and maximizes performance.
It can optimize pre-trained deep learning models such as Caffe, MXNET, and ONNX Tensorflow. The tool suite includes more than 20 pre-trained models, and supports 100+ public and custom models (includes Caffe, MXNet, TensorFlow, ONNX, Kaldi) for easier deployments across Intel® silicon products (CPU, GPU/Intel® Processor Graphics, FPGA, VPU).