The recent developments in whole-slide digital scanners have spurred a revolution in imaging technology for histopathology. While these commercially available, high-throughput whole-slide scanners address data acquisition issues, the amount of data provided by them currently far exceeds the rate at which they can be analyzed efficiently. More importantly, the qualitative microscopic visual inspection of tissue slides by human readers (e.g., pathologists) is often subject to significant inter- and intra-reader variations. Using computerized image analysis, it is possible to extract more objective and precise quantitative diagnostic clues that will help improving the current evaluation of histopathological data.
The main goal of this dissertation is to understand and address the challenges associated with the development of image analysis techniques for the computer-aided interpretation of high-resolution histopathology imagery. We aim to design algorithms for key image analysis tasks such as robust and adaptive segmentation of cytological components for higher level processing, construction of biologically relevant and computationally tractable features and their mathematical representations in order to differentiate distinct tissue subtypes, detection of prognostically significant tissue structures, and spatial alignment of tissue sections prepared with different stains in order to incorporate complementary information.
We demonstrate the effectiveness of the proposed approaches on three important histopathology applications: analysis of whole-slide tissue sections for neuroblastoma prognosis, automated grading of follicular lymphoma and quantitative characterization of muscle fiber subtypes from serial transverse skeletal muscle tissue samples.
For computer-aided analysis of whole-slide neuroblastoma tissue sections, we develop a comprehensive, multi-resolution image analysis framework including the establishment of multi-resolution image hierarchy, image segmentation, feature construction and representation, feature extraction, classification and classification evaluation. Within the computer-aided follicular lymphoma grading work, we present a novel cell segmentation approach from the hematoxylin and eosin stained histopathology images with potential applications to other disease domains. We also present a model-based intermediate representation, which models the spatial distribution of cytological components and provides a rich set of features to classify image regions associated with distinct follicular lymphoma grades. In addition, we demonstrate a novel color texture analysis approach based on the non-linear color quantization using self-organizing maps. This approach may also be applicable to the analysis of other natural images with limited color spectrum (e.g., satellite imagery). Finally, we present a complete image analysis workflow including the segmentation of individual muscle fibers, the registration of successive tissue sections with different ATPase activity, and the classification of muscle fiber subtypes to quantitatively characterize the skeletal muscle histology. Each problem gives us an opportunity to explore different challenges associated with histopathological image analysis and propose novel solutions. Overall, proposed systems yield promising results and may provide new ways of characterizing and analyzing histopathology images.