Medical Imaging Analytics, Informatics and Machine Learning in a Global Health Application
published: Dec. 1, 2017, recorded: August 2017, views: 782
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Global health challenges arise from various shortages: lack of solutions in biomedicine, adverse social situations, lack of resources, and lack of expertise. While not all of these can be addressed by a data and informatics organization, such as the U.S. National Library of Medicine, it can address a critical need in this area – enabling access to high quality information to aid in diagnostics at the point of care. This can be achieved by extending its in-house research in biomedical image analytics, medical informatics, and machine learning, and adapting it to where it can be most useful. Diagnostics and screening applications utilize the same image analysis content understanding techniques used in multimodal information retrieval, except they need to be enhanced for use in a field-based system, made compatible with existing medical device communications and informatics standards, and made resilient for use in resource constrained regions. In this talk, I will describe the progress and challenges faced on a global health project for automated image analysis of chest x-ray images for use in screening for tuberculosis in a HIV prone rural region in sub-Saharan Africa. I will also describe challenges faced in extending the technology to other TB endemic regions and our ongoing efforts to improve its performance. The project demonstrates how a multidisciplinary approach through synergistic efforts of computational imaging scientists, radiologists, and engineers can be channeled to address a long standing global health challenge.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !