Background: Computational analysis of tissue structure reveals sub-visual differences in tissue functional states by\r\nextracting quantitative signature features that establish a diagnostic profile. Incomplete and/or inaccurate profiles\r\ncontribute to misdiagnosis.\r\nMethods: In order to create more complete tissue structure profiles, we adapted our cell-graph method for\r\nextracting quantitative features from histopathology images to now capture temporospatial traits of threedimensional\r\ncollagen hydrogel cell cultures. Cell-graphs were proposed to characterize the spatial organization\r\nbetween the cells in tissues by exploiting graph theory wherein the nuclei of the cells constitute the nodes and\r\nthe approximate adjacency of cells are represented with edges. We chose 11 different cell types representing\r\nnon-tumorigenic, pre-cancerous, and malignant states from multiple tissue origins.\r\nResults: We built cell-graphs from the cellular hydrogel images and computed a large set of features describing\r\nthe structural characteristics captured by the graphs over time. Using three-mode tensor analysis, we identified the\r\nfive most significant features (metrics) that capture the compactness, clustering, and spatial uniformity of the 3D\r\narchitectural changes for each cell type throughout the time course. Importantly, four of these metrics are also the\r\ndiscriminative features for our histopathology data from our previous studies.\r\nConclusions: Together, these descriptive metrics provide rigorous quantitative representations of image\r\ninformation that other image analysis methods do not. Examining the changes in these five metrics allowed us to\r\neasily discriminate between all 11 cell types, whereas differences from visual examination of the images are not as\r\napparent. These results demonstrate that application of the cell-graph technique to 3D image data yields\r\ndiscriminative metrics that have the potential to improve the accuracy of image-based tissue profiles, and thus\r\nimprove the detection and diagnosis of disease.
Loading....