Toward objective prognostic grading of prostatic carcinoma using image analysis

Abstract

At present there is no generally accepted histopathologic grading system for prostatic carcinoma that would be reproducible, and it is still unclear which system provides the most reliable individual prognosis. The objective of this study was to evaluate the relationship between morphometric features and prognosis in patients with clinical stage B prostatic carcinoma using computerized image analysis. Standardized histologic, Feulgen-stained slides from 23 patients operated on for clinical stage B prostatic carcinoma were studied. Dimension-, form- and texture-related nuclear features, both classic and fractal, were computed for at least 100 nuclei per slide. Patients were divided into low-risk and high-risk groups, using as criteria the absence or presence of metastases, respectively, three years after the operation. A discriminant function based on five chromatin texture-related features allowed complete separation between groups with a good or poor prognosis. These preliminary results, however, need to be confirmed on a larger set of patients.