You are here

Image Processing & Visualization

Printer-friendly versionPrinter-friendly version

For use in biomedical education and the diagnosis and treatment of diseases, LHNCBC conducts R&D in the analysis, presentation, and retrieval of images and the creation of visualizations. Areas of active investigation include image compression, image enhancement, image recognition and understanding, image transmission, and user interface design. Our research has several objectives: build advanced imaging tools for biomedical research; create image-based tools for medical training and assessment; investigate design principles for, and develop multimedia image/text databases with particular focus on database organization, indexing and retrieval; develop Content-Based Image Retrieval (CBIR) techniques for automated indexing of medical images by image features.

Projects

  • Model of head of VHP male dataset.

    3D Printing, Visualization, and Immersive Display

    The 3D Printing, Visualization, and Immersive Display project is studying how to represent, display, and present biomedical information that is inherently more than two-dimensional, in order to maximize user understanding and retention of the underlying knowledge.

  • Illustration of intra-cellular organelles (mitochondria and endoplasmic reticulum) of a melanoma cancer cell.

    Biomedical Data Visualization

    Biomedical Data Visualization contributes to improving access to high quality biomedical imaging information. Our work includes research on the Visible Human imaging and visualization and producing video modules for Profiles in Science.

  • Detailed image of the camera and photographic stand including color reference cards for imaging pills, tablets, and capsules.

    C3PI: Computational Photography Project for Pill Identification

    The Computational Photography Project for Pill Identification (C3PI) is developing information infrastructure for identifying unknown oral solid dosage pharmaceuticals (pills) from digital photographs and is generating a comprehensive portfolio of digital images of those pills along with supplementary metadata for computer vision research.

  • chest x-ray image

    Computer-aided TB Screening on Chest X-rays

    We are collaborating with AMPATH (Academic Model Providing Access to Healthcare), an organization supported by USAID that runs the largest AIDS treatment program in the world. This project uses LHNCBC’s imaging research and system development to fulfill NIH global health policy objectives. Our objective is to leverage in-house expertise in image processing to screen HIV-positive patients in rural Kenya for evidence of pulmonary tuberculosis (TB) in chest x-rays.

  • Artist's conceptual image of how the 3D structures of glycoproteins are extracted from multiple 2D electron microscopy projections.

    High Resolution Electron Microscopy

    The 3D informatics for High Resolution Electron Microscopy project is analyzing the life sciences at nanometer scales. Using high performance computing on data from both transmission electron microscopy and ion-abrasion scanning electron microscopy, investigators are resolving previously unknown structures for use in cancer research and investigations of infectious diseases.

  • 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.

  • Logo of the Insight Toolkit (ITK).

    Insight Toolkit

    The Insight Toolkit (ITK) project is developing a public, open-source library of leading-edge algorithms for the segmentation (image partitioning) and registration (image alignment) of high-dimensional biomedical image data.

  • The Visible Human Project logo.

    Visible Human Project

    NLM/LHNCBC's Visible Human Project® (VHP) enables education, diagnosis, treatment planning, virtual reality, and virtual surgeries, through the use of its publicly-available Visible Man and Visible Woman reference data sets obtained from human cadavers.