DIFFERENTIATION OF LOW-GRADE NON-HODGKINS-LYMPHOMA BY DIGITAL IMAGE-PROCESSING

OBJECTIVE: To identify different types of low grade B-cell non-Hodgkin 's lymphoma (NHL) classified according to the Revised European America n Lymphoma and Kiel classification systems by means of digital image p rocessing. STUDY DESIGN: Seventy-four touch impl ants were scanned and analyzed. To compare common but intricate DNA stain with a routinely used panoptical dye, all lymphoma specimens had been stained by the Ro manowsky-Giemsa method and 48 touch imprints redyed with Feulgen-Azure A. In both cases 30 features derived from size, color and chromatin t exture of each nucleus were evaluated. RESULTS: Feulgen-stained touch imprints showed a 59% average probability of correct identification. T he division of mantle cell lymphoma and chronic lymphocytic leukemia w as difficult. In contrast, it was possible to distinguish all differen t types of lymphomas investigated if Romanowsky-Giemsa stain was used. Correct diagnoses were achieved for mantle cell lymphoma in 87.5%,fol licle center cell lymphoma in 78%, chronic lymphocytic leukemia in 78% , immunocytoma in 75% and marginal zone B-cell lymphoma in 80%. CONCLU SION: The application of texture analysis is feasible in the classific ation of NHL.