Projects: Histopathology
Textons
Bonnie Hall is working on the automated analysis of tissue microarray specimens using a broad range of techniques from imaging, computer vision, and biology. Her research goals are to classify different staining patterns and tissue types, such as epithelium and stroma, using texture analysis. This will benefit not only the pathologist, but also the research community through the elimination of tedious manual scoring of microarray tissue disks.
Tissue Microarrays
The Help Defeat Cancer Project comprises a large-scale effort between CBII and researchers at IBM to analyze features in cancer tissue microarrays. The goal of this research is to discover a unique signature which characterizes cancer in the digitized pathological images.
Remote Microscopy
Recent advances in networking, robotics, and computer technology allow real-time diagnosis, consultation, and education by using images obtained through remote microscopy. CBII developed IGDS, the Image Guided Decision Support (IGDS) system, to integrate components for both remote microscope control and decision support. A physician can remotely command a robotic microscope, obtain high-quality images to be used in the diagnosis, and authorize other users to visualize the same images. The "Decision Support" component of the system locates, retrieves and displays cases which exhibit morphological profiles consistent to the case in question and suggests the most likely diagnosis based on majority logic. The IGDS system has a natural man-machine interface containing engines for speech recognition and voice feedback. (Excerpted from the abstract of Comaniciu et. al)
Segmentation
Yang et al. developed a robust segmentation model using snakes to segment imaged cells. The model was then used to distinguish between three types of leukemia/lymphomas.
