AI Assisted Radiology Image Quality Assessment

Continuous quality control (QC) in the diagnostic imaging workflow is vital to maintain a high quality radiology department. Effective QC efforts often require time consuming, laborious work by medical physicists as they collect and analyze hundreds of images from multiple imaging systems. An example of an inefficiency that can be addressed with deep learning (DL) is in the detection of repeated and rejected x-ray images. DL algorithms were developed to perform automatic QC checks on chest x-ray images to minimize the effort and improve the accuracy of QC programs, enabling the delivery of efficient and quality care to patients.

Hye Sun Na, Digital Product Manager, AI at GE Healthcare

Hye Sun Na is an AI product manager at GE Healthcare driving the development of a platform for creating deep learning models. She works closely with device product teams to define the AI strategy and integrate deep learning into GEHC’s portfolio of imaging and clinical monitoring systems. Prior to joining the AI team, Hye Sun was a senior engineer on the CT physics team, leading feature development for GE’s Revolution CT system. She has over 10 years of engineering experience in diagnostic imaging including X-ray, MR, and CT. Hye Sun holds a Biomedical Engineering degree from the University of Texas at Austin and is a member of the American Association of Physicists in Medicine.

Cookies help us deliver our services. By using our services, you agree to our use of cookies. Learn more