LEUKO: a Computer Decision Support System for Leukemia Diagnosis
May 15, 2007
Counting different types of leukocytes as part of leukemia diagnosis is often assigned to expert humans: this is a time-consuming process which is typically done by limiting the analysis to a reduced number of samples. Automation would allow inspection of many more cells with wide statistical information about each blood smear slide. Medical doctors can describe the nucleus and the cytoplasm in terms of the shape, size, color and texture. This project attempts to imitate the experts, translating the qualitative descriptions into feature vectors and developing softwares with user-friendly interfaces for both pattern recognition and feature selection. Our pattern recognition system is built to recognize the 5 types of normal leukocytes and lymphoid leukemias as chronic lymphocitic, prolymphocitic and Hairy cells with 92% average accuracy performance
Downloads
About NERSC and Berkeley Lab
The National Energy Research Scientific Computing Center (NERSC) is the primary high-performance computing facility for scientific research sponsored by the U.S. Department of Energy's Office of Science. Located at Lawrence Berkeley National Laboratory, the NERSC Center serves more than 4,000 scientists at national laboratories and universities researching a wide range of problems in combustion, climate modeling, fusion energy, materials science, physics, chemistry, computational biology, and other disciplines. Berkeley Lab is a U.S. Department of Energy national laboratory located in Berkeley, California. It conducts unclassified scientific research and is managed by the University of California for the U.S. DOE Office of Science. For more information about computing sciences at Berkeley Lab, please visit www.lbl.gov/cs.
