SPIDAL Communities

Remote Sensing -- Kansas

The images below display Kansas radar images measuring glacier beds with results of new machine learning algorithms identifying the top (red) and bottom (green) of the glaciers. Results of earlier work are labelled as [11]. Ground Truth is human generated analysis.

  • Research paper here.
  • Research paper here.
Glacier Readings

Pathology Informatics – Stony Brook University

Digital pathology images or whole slide images are generated through scanning human tissue specimens with high resolution microscope scanners. Examination of high resolution whole slide images enables more effective diagnosis, prognosis and prediction of cancer and other important diseases. Recently, 3D examinations of tissues at microscopic resolution have become possible, with significant potential to enhance the study of normal and disease processes through 3D spatial analytics. Pathology image analysis segments massive spatial objects such as nuclei and blood vessels, represented with their boundaries, along with many extracted image features from these objects. The spatially derived information is used for complex queries and analytics to support biomedical research. Scalable methods for pathology image analytics will be essential to realize the potential power of pathology imaging. We will provide a generic parallel image processing pipeline that supports different image analysis algorithms with HPC-ABDS.