Automated estimation of epithelial volume in breast cancer sections. A comparison with the image processing steps applied to gynecologic tumors

Quantifying local heterogeneity via morphologic scale: Distinguishing tumoral from stromal regions

INTRODUCTION

The notion of local scale was introduced to characterize varying levels of image detail so that localized image processing tasks could be performed while simultaneously yielding a globally optimal result. In this paper, we have presented the methodological framework for a novel locally adaptive scale definition, morphologic scale (MS), which is different from extant local scale definitions in that it attempts to characterize local heterogeneity as opposed to local homogeneity.

METHODS

At every point of interest, the MS is determined as a series of radial paths extending outward in the direction of least resistance, navigating around obstructions. Each pixel can then be directly compared to other points of interest via a rotationally invariant quantitative feature descriptor, determined by the application of Fourier descriptors to the collection of these paths.

RESULTS

OUR GOAL IS TO DISTINGUISH TUMOR AND STROMAL TISSUE CLASSES IN THE CONTEXT OF FOUR DIFFERENT DIGITIZED PATHOLOGY DATASETS: prostate tissue microarrays (TMAs) stained with hematoxylin and eosin (HE) (44 images) and TMAs stained with only hematoxylin (H) (44 images), slide mounts of ovarian H (60 images), and HE breast cancer (51 images) histology images. Classification performance over 50 cross-validation runs using a Bayesian classifier produced mean areas under the curve of 0.88 ± 0.01 (prostate HE), 0.87 ± 0.02 (prostate H), 0.88 ± 0.01 (ovarian H), and 0.80 ± 0.01 (breast HE).

CONCLUSION

For each dataset listed in Table 3, we randomly selected 100 points per image, and using the procedure described in Experiment 1, we attempted to separate them as belonging to stroma or epithelium.

Syntactic structure analysis in invasive breast cancer: analysis of reproducibility, biologic background, and prognostic value

The reproducibility, biologic background, and prognostic value of syntactic structure analysis were studied in a group of 94 patients with invasive primary breast cancer. Using an interactive digitizing video overlay system, the centers of malignant breast cancer nuclei were marked in the five (subjectively) most cellular fields of vision for each case at a final magnification of X1,200, and the corresponding minimum spanning tree was composed for each field. From each minimum spanning tree, 10 syntactic structure features were derived; subsequently, the mean, standard deviation, minimum, and maximum values of the five fields analyzed were calculated for further statistical analysis. Forty statistics thus were available for each case. The reproducibility of repeatedly measuring the same field (independent of nuclearity) and the same patient twice by the same or different observers was good for most of the syntactic structure features. When comparing the statistics of the syntactic structure features with other established prognosticators, correlations were found with (in this order) standard deviation and mean nuclear area (expressing nuclear differentiation), volume percentage epithelium (expressing architectural differentiation), and mitotic activity index. In univariate survival analysis several syntactic structure statistics yielded prognostic significance, the best being the maximum of the number of nuclei with two neighbors (P = .002; Mantel-Cox test, 12.4). Multivariate analysis revealed that syntactic structure features did not provide additional prognostic values with regard to each other. However, they did show additional prognostic values with regard to the multivariate prognostic index (currently one of the best prognosticators in breast cancer), which combines the mitotic activity index, lymph node status, and tumor size. Measurement of syntactic structure features could therefore contribute to an improved prediction of prognosis of breast cancer patients. In conclusion, syntactic structure analysis is a simple, fast, and highly reproducible technique that shows prognostic value in invasive breast cancer and also has important prognostic value with regard to the well-established and prognostically strong morphometric features. It seems to be a promising new method of analyzing tissue architecture in breast cancer and perhaps in many other tumors.