Summary: Interactive classification and content-based retrieval of tissue
Selim Aksoy, Giovanni Marchisio, Carsten Tusk, Krzysztof Koperski
Insightful Corporation, 1700 Westlake Ave. N., Seattle, WA, 98109
We describe a system for interactive classification and retrieval of microscopic tissue images. Our system models
tissues in pixel, region and image levels. Pixel level features are generated using unsupervised clustering of color
and texture values. Region level features include shape information and statistics of pixel level feature values.
Image level features include statistics and spatial relationships of regions. To reduce the gap between low-level
features and high-level expert knowledge, we define the concept of prototype regions. The system learns the
prototype regions in an image collection using model-based clustering and density estimation. Different tissue
types are modeled using spatial relationships of these regions. Spatial relationships are represented by fuzzy
membership functions. The system automatically selects significant relationships from training data and builds
models which can also be updated using user relevance feedback. A Bayesian framework is used to classify
tissues based on these models. Preliminary experiments show that the spatial relationship models we developed
provide a flexible and powerful framework for classification and retrieval of tissue images.
Keywords: Content-based image retrieval, image classification, spatial relationships, fuzzy logic, tissue images.
A challenging problem in medical imaging is automatic classification and retrieval in large image databases.
Most of the proposed approaches use low-level features like color histograms and texture features to index