Résumé : OBJECTIVE: To create an objective classification system to perform TNM classification of ampullary adenocarcinoma and cholangiocarcinoma using image cytometric data derived from Feulgen-stained tumor nuclei. STUDY DESIGN: Surgically resected cases of ampullary adenocarcinoma and cholangiocarcinoma with established TNM classifications were selected on the basis of available formalin-fixed, paraffin-embedded tissue. Fifteen numerical variables related to morphometric, densitometric and textural features of each tumor nucleus were recorded. We employed a methodology based on multivariate statistical tools to characterize the association of morphonuclear variables with TNM classification. The first step consisted of identifying and selecting representative nuclei of each T class. From this "purified" data set an objective classification system was created. The classification system was assessed using internal and external validation. RESULTS: Employing ANOVA, all 15 variables were significantly associated with T classification, 11 of 15 with N and 4 with M. Multivariate analysis was employed to distinguish between T1, T2 and T3 lesions. Our methodology correctly classified 76% of T1 nuclei, 47% of T2 nuclei and 84% of T3 nuclei. Heterogeneity within an individual tumor was defined in 61% of cases included in the training set. Complete concordance between pathologic classification and the classification system was observed in 71% of an independent validation.