Spatially-Invariant Vector Quantization for Image Analysis
- Created on Tuesday, 01 November 2011
A new software tool aims to make computer-aided tissue analysis faster, more accurate, and more consistent.
Researchers at the University of Michigan Health System and their colleagues have developed a software tool that aims to make the detection of abnormalities in cell and tissue samples faster, more accurate, and more consistent. The technique, known as Spatially-Invariant Vector Quantization (SIVQ), can pinpoint cancer cells and other critical features from digital images made from tissue slides.
SIVQ can separate calcifications from
malignancies in breast tissue samples,
search for and count particular cell types
in a bone marrow slide, or quickly identify
the cherry red nucleoli of cells associated
with Hodgkin’s disease, according
to findings published in the Journal of
The technology — developed by a team led by Ulysses Balis, M.D., director of the Division of Pathology Informatics at the U-M Medical School working in conjunction with researchers at Massachusetts General Hospital and Harvard Medical School — differs from conventional pattern recognition software by basing its core search on a series of concentric, pattern-matching rings, rather than the more typical rectangular or square blocks. This approach takes advantage of the rings’ continuous symmetry, allowing for the recognition of features no matter how they’re rotated or whether they’re reversed, like in a mirror.
In SIVQ, a search starts with the user selecting a small area of pixels, known as a vector, which he or she wants to try to match elsewhere in the image. The vector can also come from a stored library of images.
The algorithm compares this circular vector to every part of the image. At every location, the ring rotates through millions of possibilities in an attempt to find a match in every possible degree of rotation. Smaller rings within the main ring can provide an even more refined search.
The program then creates a heat map, shading the image based on the quality of match at every point. This technique would not work with a square or rectangular- shaped search structure because those shapes don’t remain symmetrical as they rotate.
The technology has the potential open a myriad of new possibilities for deeper image analysis. For example, the most common way to look at tissue samples is still a staining technique that dates back to the 1800s. Reading these complex slides and rendering a diagnosis is part of the art of pathology.
SIVQ, however, can assist pathologists by pre-screening an image and identifying potentially problematic areas, including subtle features that may not be readily apparent to the eye.
SIVQ’s efficiency in pre-identifying potential problems becomes apparent when one considers that a pathologist may review more than 100 slides in a single day.
Vectors can also be pooled to create shared libraries, a catalog of reference images upon which the computer can search, which could help pathologists to quickly identify rare anomalies.
Balis and his colleagues have a number of of additional research projects involving SIVQ nearing completion. These demonstrate the technology’s potential usefulness in a number of basic science and clinical applications. These efforts involve collaborations with researchers at the National Institutes of Health, Mayo Clinic, Rutgers University, Harvard Medical School, and Massachusetts General Hospital.
This technology was done by University of Michigan Health System, Ann Arbor, MI. U-M is seeking licensing partners to bring this technology to market. For more information and to watch videos of the technology in action, visit http://www.uofmhealth.org/News/sivq_pathology_0200.