ECM-Aware Cell-Graph Mining for Bone Tissue Modeling and Classification

Abstract

Pathological examination of a biopsy is the most reliable and widely used technique to diagnose bone cancer. However, it suffers from both inter- and intra- observer subjectivity. Techniques for automated tissue modeling and classification can reduce this subjectivity and increases the accuracy of bone cancer diagnosis. This paper presents a graph theoretical method, called extracellular matrix (ECM)-aware cell-graph mining, that combines the ECM formation with the distribution of cells in hematoxylin and eosin (H&E) stained histopathological images of bone tissues samples. This method can identify different types of cells that coexist in the same tissue as a result of its functional state. Thus, it models the structure-function relationships more precisely and classifies bone tissue samples accurately for cancer diagnosis. The tissue images are segmented, using the eigenvalues of the Hessian matrix, to compute spatial coordinates of cell nuclei as the nodes of corresponding cell-graph. Upon segmentation a color code is assigned to each node based on the composition of its surrounding ECM. An edge is hypothesized (and established) between a pair of nodes if the corresponding cell membranes are in physical contact and if they share the same color. Hence, multiple colored-cell-graphs coexist in a tissue each modeling a different cell-type organization. Both topological and spectral features of ECM-aware cell-graphs are computed to quantify the structural properties of tissue samples and classify their different functional states as healthy, fractured, or cancerous using support vector machines. Classification accuracy comparison to related work shows that ECM-aware cell-graph approach yields 90.0% whereas Delaunay triangulation and simple cell-graph approach achieves 75.0% and 81.1% accuracy, respectively.

Fig. 1

Microscopic images of tissue samples surgically removed from human bone tissues and stained with hematoxylin and eosin.

Fig. 2

A fractured bone tissue example is shown in 2(a). Note the fracture cells in the middle of the original image. The simple-cell-graph representation, the Voronoi diagram and the Delaunay triangulation for this sample tissue are depicted in 2(b), 2(c) and 2(d) respectively. The corresponding ECM-aware cell-graph is drawn in 2(e). The interactions between fracture cells are drawn with blue and the red cells with red color. Delaunay triangulation represents the tissue as a single connected component and does not allow crossing of edges. Simple-cell-graphs relaxes these restrictions and allows the tissue to be non-planar and disconnected. Likewise, ECM-aware cell-graphs do not put such restrictions on the tissue and moreover it can also capture the structural organization of different cells in a tissue. Furthermore, ECM-aware cell-graphs can be adjusted with different linking thresholds whereas Delaunay triangulations are fixed representations.

Fig. 3

Receiver operator characteristics curves are given for the fracture vs cancerous and healthy vs fracture in 3(a) and 3(b) respectively. The area under curve (AUC) for ECM-aware colored cell-graphs is 0.97 and 1 whereas for Delaunay this value is 0.66 and 0.92 respectively. Thus, ECM-aware cell-graphs perform better than Delaunay graphs.