Frozen sections of 202 consecutive breast tumour cases were analyzed by morphometric quantitation of nuclear features. Nuclei were selected at random. Conventional light microscope examination of the paraffin-embedded specimens revealed 144 cases of cancer and 56 benign tumours. Using multivariate discriminant analysis of morphometric features, all but two of the benign cases and 79% of the malignant tumours were correctly classified. When a morphometrically based dynamic filter set to exclude 'non-diagnostic' nuclei was used, the correctly classified malignant cases rose to 86% Morphometry is a fast, reproducible and efficient method that can be used in conjunction with the histomorphological diagnosis of mammary frozen sections. The combination of systematic sampling and an objective dynamic filter may be a powerful approach to quantitative analyses of tumours from other sites. However, it is also likely that efficiency can be improved by combining nuclear morphometric features with structural, histochemical and molecular biological data. The combination of traditional histomorphological examination with quantitative information may well increase the diagnostic accuracy in individual patients.