Deep learning based cell segmentation in histopathological images

Abstract

In digital pathology, cell imaging systems allow us to comprehend histopathological events at the cellular level. The first step in these systems is generally cell segmentation, which substantially affects the subsequent steps for an effective and reliable analysis of histopathological images. On the other hand, cell segmentation is a challenging task in histopathological images where there are cells with different pixel intensities and morphological characteristics. The approaches that integrate both pixel intensity and morphological characteristics of cells are likely to achieve successful segmentation results. This thesis proposes a deep learning based approach for a reliable segmentation of cells in the images of histopathological tissue samples stained with the routinely used hematoxylin and eosin technique. This approach introduces two stage convolutional neural networks that employ pixel intensities in the first stage and morphological cell features in the second stage. The proposed TwoStageCNN method is based on extracting cell features, related to cell morphology, from the class labels and posteriors generated in the first stage and uses the morphological cell features in the second stage for the final segmentation. We evaluate the proposed approach on 3428 cells and the experimental results show that our approach yields better segmentation results compared to different segmentation techniques.