Assessment of algorithms for mitosis detection in breast cancer histopathology images.

The proliferative activity of breast tumors, which is routinely estimated by counting of mitotic figures in hematoxylin and eosin stained histology sections, is considered to be one of the most important prognostic markers. However, mitosis counting is laborious, subjective and may suffer from low inter-observer agreement. With the wider acceptance of whole slide images in pathology labs, automatic image analysis has been proposed as a potential solution for these issues. In this paper, the results from the Assessment of Mitosis Detection Algorithms 2013 (AMIDA13) challenge are described. The challenge was based on a data set consisting of 12 training and 11 testing subjects, with more than one thousand annotated mitotic figures by multiple observers. Short descriptions and results from the evaluation of eleven methods are presented. The top performing method has an error rate that is comparable to the inter-observer agreement among pathologists.

Cell words: modelling the visual appearance of cells in histopathology images.

Detection and classification of cells in histological images is a challenging task because of the large intra-class variation in the visual appearance of various types of biological cells. In this paper, we propose a discriminative dictionary learning paradigm, termed as Cell Words, for modelling the visual appearance of cells which includes colour, shape, texture and context in a unified manner. The proposed framework is capable of distinguishing mitotic cells from non-mitotic cells (apoptotic, necrotic, epithelial) in breast histology images with high accuracy.

DiSWOP: a novel measure for cell-level protein network analysis in localized proteomics image data.

MOTIVATION: New bioimaging techniques have recently been proposed to visualize the colocation or interaction of several proteins within individual cells, displaying the heterogeneity of neighbouring cells within the same tissue specimen. Such techniques could hold the key to understanding complex biological systems such as the protein interactions involved in cancer. However, there is a need for new algorithmic approaches that analyze the large amounts of multi-tag bioimage data from cancerous and normal tissue specimens to begin to infer protein networks and unravel the cellular heterogeneity at a molecular level. RESULTS: The proposed approach analyzes cell phenotypes in normal and cancerous colon tissue imaged using the robotically controlled Toponome Imaging System microscope. It involves segmenting the 4',6-diamidino-2-phenylindole-labelled image into cells and determining the cell phenotypes according to their protein-protein dependence profile. These were analyzed using two new measures, Difference in Sums of Weighted cO-dependence/Anti-co-dependence profiles (DiSWOP and DiSWAP) for overall co-expression and anti-co-expression, respectively. These novel quantities were extracted using 11 Toponome Imaging System image stacks from either cancerous or normal human colorectal specimens. This approach enables one to easily identify protein pairs that have significantly higher/lower co-expression levels in cancerous tissue samples when compared with normal colon tissue. AVAILABILITY AND IMPLEMENTATION: http://www2.warwick.ac.uk/fac/sci/dcs/research/combi/research/bic/diswop.

On generating cell exemplars for detection of mitotic cells in breast cancer histopathology images.

Mitotic activity is one of the main criteria that pathologists use to decide the grade of the cancer. Computerised mitotic cell detection promises to bring efficiency and accuracy into the grading process. However, detection and classification of mitotic cells in breast cancer histopathology images is a challenging task because of the large intra-class variation in the visual appearance of mitotic cells in various stages of cell division life cycle. In this paper, we test the hypothesis that cells in histopathology images can be effectively represented using cell exemplars derived from sub-images of various kinds of cells in an image for the purposes of mitotic cell classification. We compare three methods for generating exemplar cells. The methods have been evaluated in terms of classification performance on the MITOS dataset. The experimental results demonstrate that eigencells combined with support vector machines produce reasonably high detection accuracy among all the methods.

HyMaP: A hybrid magnitude-phase approach to unsupervised segmentation of tumor areas in breast cancer histology images.

BACKGROUND: Segmentation of areas containing tumor cells in standard H&E histopathology images of breast (and several other tissues) is a key task for computer-assisted assessment and grading of histopathology slides. Good segmentation of tumor regions is also vital for automated scoring of immunohistochemical stained slides to restrict the scoring or analysis to areas containing tumor cells only and avoid potentially misleading results from analysis of stromal regions. Furthermore, detection of mitotic cells is critical for calculating key measures such as mitotic index; a key criteria for grading several types of cancers including breast cancer. We show that tumor segmentation can allow detection and quantification of mitotic cells from the standard H&E slides with a high degree of accuracy without need for special stains, in turn making the whole process more cost-effective. METHOD: BASED ON THE TISSUE MORPHOLOGY, BREAST HISTOLOGY IMAGE CONTENTS CAN BE DIVIDED INTO FOUR REGIONS: Tumor, Hypocellular Stroma (HypoCS), Hypercellular Stroma (HyperCS), and tissue fat (Background). Background is removed during the preprocessing stage on the basis of color thresholding, while HypoCS and HyperCS regions are segmented by calculating features using magnitude and phase spectra in the frequency domain, respectively, and performing unsupervised segmentation on these features. RESULTS: All images in the database were hand segmented by two expert pathologists. The algorithms considered here are evaluated on three pixel-wise accuracy measures: precision, recall, and F1-Score. The segmentation results obtained by combining HypoCS and HyperCS yield high F1-Score of 0.86 and 0.89 with re-spect to the ground truth. CONCLUSIONS: In this paper, we show that segmentation of breast histopathology image into hypocellular stroma and hypercellular stroma can be achieved using magnitude and phase spectra in the frequency domain. The segmentation leads to demarcation of tumor margins leading to improved accuracy of mitotic cell detection.