Entity

Time filter

Source Type

Sun City Center, United States

McCann M.T.,Carnegie Mellon University | Ozolek J.A.,University of Pittsburgh | Parvin B.,Lawrence Berkeley National Laboratory | Parvin B.,University of Nevada, Reno | Kovacevic J.,Center for Bioimage Informatics
IEEE Signal Processing Magazine | Year: 2015

Histology is the microscopic inspection of plant or animal tissue. It is a critical component in diagnostic medicine and a tool for studying the pathogenesis and biology of processes such as cancer and embryogenesis. Tissue processing for histology has become increasingly automated, drastically increasing the speed at which histology labs can produce tissue slides for viewing. Another trend is the digitization of these slides, allowing them to be viewed on a computer rather than through a microscope. Despite these changes, much of the routine analysis of tissue sections remains a painstaking, manual task that can only be completed by highly trained pathologists at a high cost per hour. There is, therefore, a niche for image analysis methods that can automate some aspects of this analysis. These methods could also automate tasks that are prohibitively time-consuming for humans, e.g., discovering new disease markers from hundreds of whole-slide images (WSIs) or precisely quantifying tissues within a tumor. ©2015IEEE. Source


Wang W.,Center for Bioimage Informatics | Chen C.,Center for Bioimage Informatics | Peng T.,Center for Bioimage Informatics | Slepcev D.,Carnegie Mellon University | And 2 more authors.
2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings | Year: 2010

We propose a novel method for detecting characteristic informative phenotype patterns from biomedical images. By building a metric space quantifying the difference between images, we learn the distributions of different classes, and then detect the characteristic regions using graph partition. We show that the detected regions are statistically significant. Our approach can also be used for designing differentiating features for specific data set. We apply our method to a digital pathology problem and successfully detect two characteristic phenotypes pertaining to normal liver and hepatoblastoma nuclei. In addition to digital pathology, our method can be applied to other biomedical problems for detecting characteristic phenotypes (e.g. location proteomics, genetic screens, cell mechanics, etc.). ©2010 IEEE. Source


McCann M.T.,Center for Bioimage Informatics | Majumdar J.,Center for Bioimage Informatics | Peng C.,University of Pittsburgh | Castro C.A.,Carnegie Mellon University | Kovacevic J.,Center for Bioimage Informatics
2014 IEEE International Conference on Image Processing, ICIP 2014 | Year: 2014

In this work, we present a new algorithm and benchmark dataset for stain separation in histology images. Histology is a critical and ubiquitous task in medical practice and research, serving as a gold standard of diagnosis for many diseases. Automating routine histology analysis tasks could reduce health care costs and improve diagnostic accuracy. One challenge in automation is that histology slides vary in their stain intensity and color; we therefore seek a digital method to normalize the appearance of histology images. As histology slides often have multiple stains on them that must be normalized independently, stain separation must occur before normalization. We propose a new digital stain separation method for the universally-used hematoxylin and eosin stain; this method improves on the state-of-the-art by adjusting the contrast of its eosin-only estimate and including a notion of stain interaction. To validate this method, we have collected a new benchmark dataset via chemical destaining containing ground truth images for stain separation, which we release publicly. Our experiments show that our method achieves more accurate stain separation than two comparison methods and that this improvement in separation accuracy leads to improved normalization. © 2014 IEEE. Source


Chen S.,Center for Bioimage Informatics | Lederman G.,Carnegie Mellon University | Wang Z.,Carnegie Mellon University | Rizzo P.,University of Pittsburgh | And 3 more authors.
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings | Year: 2014

We propose a novel recovery algorithm for signals with complex, irregular structure that is commonly represented by graphs. Our approach is a generalization of the signal inpainting technique from classical signal processing. We formulate corresponding minimization problems and demonstrate that in many cases they have closed-form solutions. We discuss a relation of the proposed approach to regression, provide an upper bound on the error for our algorithm and compare the proposed technique with other existing algorithms on real-world datasets. © 2014 IEEE. Source


Kolouri S.,Center for Bioimage Informatics | Basu S.,Center for Bioimage Informatics | Basu S.,IBM | Rohde G.K.,Center for Bioimage Informatics | Rohde G.K.,Carnegie Mellon University
2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 | Year: 2014

Multichannel microscopy has emerged as a technique for imaging multiple targets (molecules, protein distributions, etc.) simultaneously. Discovering the relative changes in these targets (i.e. distribution of different proteins) is fundamental for understanding cell structure and function. We describe a new method for quantifying and visualizing relationships between multiple targets, from a set of segmented multichannel cells. The method is based on combining the canonical correlation analysis technique with a framework for analyzing images based on the concept of optimal mass transportation. We apply the method towards understanding chromatin distribution in cancer nuclei as a function of nuclear envelope shape. We also show that sub cellular distribution of mitochondria can be used to predict the sub cellular localization of actin fibers in yeast cells. Finally, we also describe the application of the method towards understanding relationships between nuclear and cellular shapes in 2D HeLa cells. We believe that the method could serve as a general tool for mining relationships between different sub cellular protein/molecule distributions as well as organelle shapes. © 2014 IEEE. Source

Discover hidden collaborations