APPLICATION OF ATTRIBUTED GRAPHS IN DIAGNOSTIC PATHOLOGY

OBJECTIVE: To compute attributed graphs based upon calculation of the minimum spanning tree (MST) for various applications in diagnostic lun g pathology. STUDY DESIGN: The study design included assistance in his tologic diagnosis, confirmation of the diagnosis in single cases, meas urement of texture alterations after induction chemotherapy, estimatio n of prognosis of operated-on lung cancer patients and analysis of lun g cancer cells in association with differentiation markers. The histol ogic slides were Feulgen stained, and features of the integrated optic al density (IOD) were associated with the nodes of the MST. The same p rocedure was applied to immunohistochemically and ligand histochemical ly stained slides by calculation of the mean staining intensity of the cytoplasm of tumor cells. A measure for structural entropy was introd uced by computing the relative differences in distance and IOD between neighboring tumor cells in a 1/r(2) field of force. In addition, the current of entropy was computed. RESULTS: Structural entropy reflects alterations in regular textures; the current of entropy is an especial ly good prognostic parameter in lung cancer. In immuno-chemistry and l igand histochemistry, construction of the attributed MST permits detai led insight into locally different staining behavior of tumor cells an d immunocompetent cells. CONCLUSION Attributed graphs contain importan t information that can be used for the estimation of survival or for c onfirmation of diagnostic entities, such as tumor cell types.