Name
Abstract | ||
|---|---|---|
We present biologically-driven cell-graphs for the computer-aided grading of cancer in 3D breast tissue slides. Cell-graphs were previously proposed to capture structure-function relationships within tissues by representing the tissues with undirected and unweighted graphs wherein the cell nuclei constitute the graph nodes and the approximate adjacencies of the nuclei are represented with edges. Using advanced immunohistochemistry staining, levels of interactions between the cells can be captured via the expressions of particular proteins that yield more biological attributes for constructing the graph edges. With this motivation, we fluorescently labeled proteins that participate in cell-to-cell communications and analyze the structural organization of the cells in three grades of breast cancer using biologically-driven cell-graphs. Using the features extracted from the graphs in a supervised machine learning setting, computer-aided grading is achieved. Biologically-driven cell-graphs achieve 98.5% accuracy in grading the cancer into non-malignant, non-invasive, and invasive grades that significantly outperforms the conventional proximity-based cell-graphs and a Delaunay triangulation based method by 9.0% and 13.5%, respectively. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/ISBI.2013.6556431 | Biomedical Imaging |
Keywords | Field | DocType |
cancer,cellular biophysics,computer aided analysis,edge detection,feature extraction,fluorescence,graph theory,image representation,learning (artificial intelligence),medical image processing,molecular biophysics,proteins,3D breast tissue slide,Delaunay triangulation based method,advanced immunohistochemistry staining,biological attribute,biologically-driven cell-graph,breast tissue grading,cell interaction,cell nuclei,cell structural organization,cell-to-cell communication,computer-aided cancer grading,conventional proximity-based cell-graph,fluorescently labeled protein,graph edge representation,graph feature extraction,graph node,noninvasive grade,nonmalignant grade,protein expression,structure-function relationship,supervised machine learning setting,tissue representation,undirected graph,unweighted graph,Breast cancer,Cell-graphs,Digital pathology | Graph theory,Computer vision,Breast cancer,Pattern recognition,Grading (education),Expression (mathematics),Edge detection,Computer science,Feature extraction,Artificial intelligence,Cancer,Delaunay triangulation | Conference |
ISSN | ISBN | Citations |
1945-7928 | 978-1-4673-6456-0 | 3 |
PageRank | References | Authors |
0.46 | 7 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Basak Oztan | 1 | 64 | 10.31 |
| Katherine R. Shubert | 2 | 3 | 0.46 |
| Chris S. Bjornsson | 3 | 3 | 0.46 |
| George E. Plopper | 4 | 38 | 3.57 |
| Bülent Yener | 5 | 1075 | 94.51 |