Intel and GE Healthcare Develops A New AI Imaging Solution to Accelerate Critical Patient Diagnoses

Artificial Intelligence News

Intel_and_GE_Health_Develops_a_New_AI_Imagin_Solution_to_Accelerate_Critical_Patient_Diagnoses Intel and GE Healthcare Develops A New AI Imaging Solution to Accelerate Critical Patient DiagnosesSemiconductor manufacturing firm Intel and GE Healthcare have partnered to deploy deep learning AI to lessen the time between medical imaging, diagnoses, and beginning treatment.  The companies’ collaborated project is promising to provide physicians with automated diagnostic alerts for some circumstances within seconds of medical imaging being completed. It encompasses the Intel Distribution of OpenVINO toolkits, working on Intel processor-based X-ray systems to assist prioritize and streamline patient care.

David Ryan, Intel Internet of Things Group Health and Life Sciences Sector General Manager stated that the AI imaging models are optimized for inference and deployment utilizing the model optimizer component of OpenVINO. The optimized models are then incorporated into the GE application with the OpenVINO inference engine APIs. As X-ray images are acquired by the machine, the inference engine operates them for clinical diagnosis. As per said by Keith Bigelow, GE Healthcare Senior Vice-President of Edison Portfolio Strategy, medical imaging is the largest and fastest-growing data source in the healthcare industry. But, even though it accounts for 90 percent of all healthcare data, over 97 percent of it goes unanalyzed or unused. Bigelow further said that processing this huge volume of medical imaging data could escort to longer times from image acquisition to diagnosis to care. However, the patient’s health could refuse while they wait for the diagnosis. Particularly, when it comes to crucial circumstances, quick analysis and escalation are indispensable to speed up treatment.

In future applications, Ryan noted that deep learning models can be utilized to recognize incidental findings, in addition, to assist radiologists to administer their workload, improve quality of scans, and diminish retakes that can cause a redundant revelation to radiation. He also added that deep learning is also indicating promising outputs in image reform from the imaging modalities. Deep learning’s future applications can extend beyond imaging data to comprise EHR (Electronic Health Records), pathology, cellular microscopy data, and so on, to assist develop targeted drugs and attain accuracy in medication.