Object-oriented testure analysis and unsupervised segmentation for histopathological images

Abstract

The histopathological examination of tissue specimens is essential for cancer diagnosis and grading. However, this examination is subject to a considerable amount of observer variability as it mainly relies on visual interpretation of pathologists. To alleviate this problem, it is very important to develop computational quantitative tools, for which image segmentation constitutes the core step. The segmentation algorithms in literature commonly use pixel-level color/texture descriptors that they define on image pixels for quantizing a tissue. On the other hand, it is usually harder to express domain specific knowledge about tissues, such as the spatial organization of tissue components, using only the pixel-level descriptors. This may become even harder for tissue images, which typically consist of a considerable amount of variation and noise at their pixel-level, such as similar color distribution of different tissue components, distortion in cell alignments, and color contrast caused by too much stain in a particular region. The previous segmentation algorithms are more susceptible to these problems as they work on pixel-level descriptors. In order to successfully address these issues, in this thesis, we introduce three new texture descriptors, namely ObjSEG, GraphRLM, and ObjCooc textures, and implement algorithms that use these descriptors for segmenting histopathological tissue images. We extract these texture descriptors on tissue components that are approximately represented by circular objects. Since these objectoriented texture descriptors are defined on the tissue components, and hence domain specific knowledge, they represent the spatial organization of the components better than their previous counterparts. Thus, our algorithms based on these descriptors give more effective and robust segmentation results. Furthermore, since the descriptors are not directly defined on image pixels, they are effective to alleviate the pixel-level problems. In our experiments, we tested our algorithms that use the proposed objectoriented descriptors on a dataset of 200 colon tissue images. Our experiments demonstrated that our new object-oriented feature descriptors led to high segmentation accuracies, also providing a reasonable number of segmented regions. Compared with its previous counterparts, the experimental results also showed that our proposed algorithms are more effective in segmenting histopathological images.