You are here

Image Processing

Printer-friendly versionPrinter-friendly version

Toward meeting the goals outlined in the Strategic Plan of the National Library of Medicine – Building a Platform for Biomedical Discovery and Data-powered Health, the Lister Hill National Center for Biomedical Communications (LHNCBC) conducts research and development (R&D) in advancing machine learning and artificial intelligence (ML/AI) techniques on image and video data toward diagnostics, informatics, and data science applications in biomedicine. Our research has several objectives: advance ML/AI techniques for biomedical data; develop techniques to explain decision-making in machine intelligence algorithms; study algorithm reliability and impact of ML/AI decisions in the practice of biomedicine; advance image informatics, image and signal analytics, and information retrieval; research in data visualization; and, develop tools in support of data science activities related to these interests. These goals are achieved through R&D projects in specific areas of biomedicine in close partnership and collaboration with other NIH institutes and centers, other Government agencies, academic institutions, and the private industry.

Projects

chest x-ray image

Chest X-ray Analysis using Machine Intelligence Research for HIV/TB Screening

Research in machine learning and artificial intelligence (ML/AI) algorithms aims to improve computer-aided disease detection, accuracy and reliability. We develop novel computational solutions to analyze chest x-rays (CXR) and screen for cardiopulmonary diseases with a special interest in pulmonary TB in HIV+ population.

Screenshot of the Boundary Marking Tool created for cancer research.

Imaging Tools for Cancer Research

The goal of our work in Biomedical Imaging is two-fold: One, to develop advanced imaging tools for biomedical research in partnership with the National Cancer Institute and other organizations. Secondly, to conduct research in Content Based Image Retrieval (CBIR) to index and retrieve medical images by image features (e.g., shape, color and texture), augmented by textual features as well.

malaria screener thumbnail

Malaria Screener

To improve malaria diagnostics, we are developing a fully-automated system for parasite detection and counting in blood films in collaboration with NIH’s National Institute of Allergy and Infectious Diseases (NIAID) and Mahidol-Oxford University.