Ulysses Balis. M.D., (left) and Jason Hipp, M.D., Ph.D., (right) developed an algorithm that accurately identifies abnormalities in cell and tissue samples.
U-M led team makes computer-aided tissue analysis better, faster and simpler
issue 14 | winter 2012
Ulysses Balis, M.D., clicks on a helicopter in a digital satellite photo of Baghdad, Iraq. With another click, an algorithm that he and his team designed identifies three more choppers in the image without highlighting any of the buildings, streets, trees or cars.
Balis isn't playing war games. The director of the Division of Pathology Informatics at the U-M Medical School is demonstrating the extreme flexibility of a software tool aimed at making the detection of abnormalities in cell and tissue samples faster, more accurate and more consistent.
SIVQ to the rescue
In a medical setting, instead of helicopters, 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's algorithm can be applied to other images, such as this photo identifying helicopters in a satellite image of Baghdad
SIVQ isn't limited to any particular area of medicine. It can readily 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 Pathology Informatics.
"The fact that the algorithm operates effortlessly across domains and length scales, while requiring minimal user training, sets it apart from conventional approaches to image analysis," Balis says.
The technology — developed 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.
"That's good because in pathology, images of cells and tissue do not have a particular orientation," Balis says.
The pathology of pixels
In SIVQ, a search starts with the selection of a small area of pixels, known as a vector. The algorithm then compares this circular vector to every part of the image. And at every location, the ring rotates through millions of possibilities in an attempt to find a match in every possible degree of rotation. The program then creates a heat map, shading the image based on the quality of match at every point.
At left, in a digital slide of a bone marrow aspirate, a single ring vector is selected for high specificity for immature PMNs (bands). At right, SIVQ has identified additional affected cells.
Pathology informatics fellow Jason Hipp, M.D., Ph.D., believes the technology has the potential to be a "game changer" for the field by opening myriad new possibilities for deeper image analysis.
"It's going to allow us to think about things differently," says Hipp, also a clinical lecturer in the Department of Pathology. "We're starting to bridge the gap between the qualitative analysis carried out by trained expert pathologists and the quantitative approaches made possible by advances in imaging technology."
Still, pathologists shouldn't be worried that SIVQ will put them out of a job.
"No one is talking about replacing pathologists," Balis says. "But working in tandem with this technology, the hope is that they will be able to achieve a higher overall level of performance." U-M has been seeking licensing partners for the technology.