Hemosiderin laden macrophages and hemosiderin within follicular cells distinguish benign follicular lesions from follicular neoplasms

Background: Published criteria to distinguish benign colloid nodules from follicular neoplasms emphasize only three interdependent features: size of follicles, amount of colloid, and cellularity. There is a need for the validation of other independent criteria. Methods: This study quantified the significance of cystic change, defined as presence of macrophages, and the presence of hemosiderin in either the macrophages or follicular cells. The cohort consisted of 165 patients with fine needle aspiration (FNA) and histologic follow-up of either goiter (101), follicular adenoma (47), or follicular carcinoma (17). Papillary thyroid carcinomas and Hrthle cell neoplasms were excluded from the cohort, because these categories are known to show cystic change and hemosiderin. FNAs were reviewed blindly with the most cellular slide scored for the presence of macrophages and/or hemosiderin. Results: Hemosiderin within macrophages were seen in 67 (68 of 101) of the goiters and only 6 (four of 64) of follicular neoplasms ( P .0001). All four follicular neoplasms with hemosiderin in macrophages were adenomas. Three of these four had equivocal features of a benign colloid nodule histologically. None of the 17 follicular carcinomas had hemosiderin in macrophages ( P .12). Macrophages without hemosiderin also strongly distinguished goiters from neoplasms (83 vs 17) but appears less useful as a criterion since macrophages were present within 3 of 17 follicular carcinomas. Hemosiderin within follicular epithelial cells was present in 18 (18 of 101) of goiters, whereas none of the 64 follicular neoplasms had intraepithelial hemosiderin ( P .0003). Conclusions: If papillary thyroid carcinoma and Hrthle cell neoplasm are ruled out, our findings indicate that the presence of hemosiderin virtually excludes a clinically significant follicular neoplasm.