A collaborative team of researchers has developed an innovative method of generating high-quality chest X-ray images that can be used to diagnose COVID-19 more accurately than current methods.
Yelena Yesha, PhD, IDSC Innovation Officer, and Dr. Michael Morris, IDSC Affiliate Member (pictured at left), are involved in the research, which is being led by Sumeet Menon (pictured at right), a doctoral student in computer science at University of Maryland, Baltimore County (UMBC).
The team’s findings were published* in the prestigious Proceedings of the IEEE International Conference on Big Data (aka IEEE Big Data 2020) held virtually in December 2020. The researchers used Generative Adversarial Networks (GANs) in order to increase the limited volume of public datasets for COVID19 x-ray images, and empower machine-learning algorithms. Their analysis showed these generated images were visually comparable to real X-rays.
In a separate project, Dr. Yesha is leading a team building an AI-based program that is able to diagnose lung cancer from radiographic images. “We are not trying to replace radiologists, but we are trying to build the AI-based tools that can assist radiologists to do the proper diagnosis,” she said. “Now, we are working with the FDA to see if these tools can be adopted as a part of a digital diagnostic solution.”
Another current project is a collaboration with RAD-AID lab, a nonprofit institute focused on bringing radiology services into underrepresented countries. In locations where trained radiologists are not available, AI and machine learning technologies can enhance the current level of care, she said.
About RAD-AID International
Radiology is vital medical imaging (x-ray, CT, ultrasound, MRI, etc.) essential for healthcare. Over half the world lacks radiology, impacting diagnosis and treatment of cancer, heart disease, infections, trauma, maternal-infant complications, and much more. RAD-AID brings radiology to low-resource areas by delivering education, equipment, infrastructure, and support. RAD-AID works in over 30 countries to improve and optimize access to medical imaging and radiology in low resource regions of the world for increasing radiology’s contribution to global public health initiatives and patient care. Find out how RAD-AID delivers radiology globally.
*S. Menon, J. Galita, D. Chapman, A. Gangopadhyay, J. Mangalagiri, P. Nguyen, Y. Yesha, Y. Yesha, B. Saboury, M. Morris., “Generating Realistic COVID19 X-rays with a Mean Teacher + Transfer Learning GAN,” 2020, https://arxiv.org/pdf/2009.12478.pdf
Tags: AI tools, COVID-19, Generative Adversarial Networks, IEEE Big Data 2020, image classification, machine learning algorithms, Mean Teacher, medical imaging, Michael Morris, RAD-AID Lab, radiology, Sumeet Menon, UMBC, University of Maryland Baltimore County, X-ray, Yelena Yesha
