OBJECTIVE: To investigate the potential correlation between estrogen receptor (ER) texture and histologic grade in breast carcinomas. STUDY DESIGN: Clinical material comprised 96 biopsies of infiltrative ductal carcinomas that were hematoxylin-eosin (H-E) and immunohistochemically (IHC) stained. H-E-stained specimens were used for tumor grading, and IHC-stained specimens were analyzed for ER-status estimation. Spearman's correlation test was used to estimate the relation between histologic grade and both the physician's ER-status assessment and a computer system's ER-status evaluation. Moreover, a pattern recognition system was developed that takes as input textural features extracted from ER-expressed nuclei and outputs the grade of the tumor. The system was evaluated using an external cross-validation procedure in order to assess its generalization to new cases. RESULTS: Spearman's correlation revealed that the histologic grading was inversely related to both the physician's ER-status assessment and to the computer system's ER-status evaluation. The pattern recognition system was able to predict histologic grade with 95.2% accuracy. Important textural nuclear features were proven--the skewness, the angular second moment and the sum of entropy. CONCLUSION: ER-expressed nuclei texture was found to contain important information related to histologic grade.
OBJECTIVE: To investigate the potential correlation between estrogen receptor (ER) texture and histologic grade in breast carcinomas. STUDY DESIGN: Clinical material comprised 96 biopsies of infiltrative ductal carcinomas that were hematoxylin-eosin (H-E) and immunohistochemically (IHC) stained. H-E-stained specimens were used for tumor grading, and IHC-stained specimens were analyzed for ER-status estimation. Spearman's correlation test was used to estimate the relation between histologic grade and both the physician's ER-status assessment and a computer system's ER-status evaluation. Moreover, a pattern recognition system was developed that takes as input textural features extracted from ER-expressed nuclei and outputs the grade of the tumor. The system was evaluated using an external cross-validation procedure in order to assess its generalization to new cases. RESULTS: Spearman's correlation revealed that the histologic grading was inversely related to both the physician's ER-status assessment and to the computer system's ER-status evaluation. The pattern recognition system was able to predict histologic grade with 95.2% accuracy. Important textural nuclear features were proven--the skewness, the angular second moment and the sum of entropy. CONCLUSION:ER-expressed nuclei texture was found to contain important information related to histologic grade.