NEW METHOD OF NUCLEAR GRADING OF TISSUE-SECTIONS BY MEANS OF DIGITAL IMAGE-ANALYSIS WITH PROGNOSTIC-SIGNIFICANCE FOR NODE-NEGATIVE BREAST-CANCER PATIENTS

To optimize treatment of the individual patient with node-negative bre ast cancer, objective, reproducible, and standardized prognostic crite ria are required, A number of factors have been studied in recent year s, but until now it has been possible to obtain information about the risk of recurrence only for some patients belonging to subgroups with special characteristics. We report the establishment of an image analy sis method for nuclear grading as an attempt to solve this problem, fn a retrospective analysis, we used routine hematoxylin and eosin-stain ed paraffin sections from 54 node-negative patients with surgery betwe en 1980 and 1985. Cell scenes of primary tumors were scanned in a ligh t microscope in successive focus positions to obtain three-dimensional information, After automatic image segmentation, nuclear features wer e calculated as input for a first binary classification tree to differ entiate between tumor and nontumor cells, Tumor nuclei from patients w ith or without relapse were defined as high-risk or low-risk nuclei, r espectively, and were separated with a second tree, Feature values of the measured tumor nuclei from each patient were examined with this se cond tree to analyze whether the majority of nuclei for each patient w ere classified as high-risk or low-risk nuclei, Correct classification rates in the two binary cell classification trees were 88.0% and 83.8 %, respectively. In the learning sample of our study, all patients wit h a relapse had the majority of nuclei in the high-risk group, most wi th more than 80%. Therefore, it seems to be possible to develop an ima ge analytical risk profile system for nuclear grading to provide infor mation on individual prognosis. (C) 1996 Wiley-Liss, Inc.