University of Michigan software deemed successful

Pattern recognition software from the University of Michigan has proven just how useful it can be in interpreting digitized tissue slides. The program, called Invariant Vector Quantization, was successful in separating malignancy from background tissue in digital slides of cancerous tissue. A group of pathologists graded the system by comparing the software results to human results to ensure accuracy. Though the technology is accurate, it is not meant to -- nor will it -- replace the traditional methods of human pathologists. Since the computer-aided analysis might contribute to patient care, the group is making all of their primary data freely available to other doctors and researchers at U-M’s online digital imaging repository, www.WSIrepository.org.