The increased detection of ductal carcinoma in situ (DCIS) by mammographic screening and the more widespread use of breast-conserving surgery have led to a search for histological features associated with the risk of recurrence. In a case control study of 141 patients with long follow-up, we compared the ability of five morphological classifications to predict recurrence after local excision. A significant correlation was not found between recurrence and growth pattern when a traditional classification based on architecture was used nor with necrosis when a scheme based principally on this feature was employed. A correlation was, however, found between recurrence and "differentiation" as defined by nuclear features and cell polarization in a classification recently formulated by the European Pathologists Working Group (EPWG), but this failed to reach statistical significance at the 5% level. A stronger and statistically significant correlation was found between nuclear grade as defined by the EPWG and recurrence when cell polarization was disregarded, using the classification currently employed by the UK National Health Service and European Commission-funded Breast Screening Programmes. This was attributable to a small number of recurring cases being downgraded as a consequence of exhibiting polarized cells. A significant correlation between histology and recurrence was also observed using the Van Nuys classification, which is based on nuclear grade and necrosis. Whether the tumor recurred as in situ or invasive carcinoma was unrelated to histological classification, as was the time course over which it occurred. These findings strongly support the use of nuclear grade to identify cases of DCIS at high risk of recurrence after local excision, but further work is necessary to determine whether nuclear grade or necrosis is more appropriate to subdivide the non-high-grade cases.