Large-scale computations on histology images reveal grade-differentiating parameters for breast cancer

BACKGROUND

Tumor classification is inexact and largely dependent on the qualitative pathological examination of the images of the tumor tissue slides. In this study, our aim was to develop an automated computational method to classify Hematoxylin and Eosin (H&E) stained tissue sections based on cancer tissue texture features.

METHODS

Image processing of histology slide images was used to detect and identify adipose tissue, extracellular matrix, morphologically distinct cell nuclei types, and the tubular architecture. The texture parameters derived from image analysis were then applied to classify images in a supervised classification scheme using histologic grade of a testing set as guidance.

RESULTS

The histologic grade assigned by pathologists to invasive breast carcinoma images strongly correlated with both the presence and extent of cell nuclei with dispersed chromatin and the architecture, specifically the extent of presence of tubular cross sections. The two parameters that differentiated tumor grade found in this study were (1) the number density of cell nuclei with dispersed chromatin and (2) the number density of tubular cross sections identified through image processing as white blobs that were surrounded by a continuous string of cell nuclei. Classification based on subdivisions of a whole slide image containing a high concentration of cancer cell nuclei consistently agreed with the grade classification of the entire slide.

CONCLUSION

The automated image analysis and classification presented in this study demonstrate the feasibility of developing clinically relevant classification of histology images based on micro- texture. This method provides pathologists an invaluable quantitative tool for evaluation of the components of the Nottingham system for breast tumor grading and avoid intra-observer variability thus increasing the consistency of the decision-making process.

Analysis of a sampling technique applied to biological images

This correspondence examines the classification potential of two techniques based on spiral sampling of binary images of zooplankton. Image pixels are rearranged into a one-dimensional sequence by selecting samples in a spiral manner starting from the edge of the image and proceeding toward the center. The properties of this sample sequence are examined by Fourier transform and correlation techniques, using images from six major zooplankton categories of varying orientation and size. The ability of features extracted from spiral sequences to classify zooplankton samples, and their classification accuracy are investigated.