Magnetic resonance imaging of peripheral nerve sheath tumors. Assessment by numerical visual fuzzy cluster analysis

A retrospective, nonblinded review of ten nerve sheath tumors (four malignant) selected for pathologic proof and complete magnetic resonance (MR) evaluation was performed to assess the primary tumor location, signal pattern, and extent of reactive zone. A modification of visual fuzzy cluster analysis (VFCA) that emphasized the number of visual fuzzy clusters in each mass was developed to assess the neural tumors. The MR findings were correlated with the findings at surgery and histopathology. There were six men and four women, aged 19 to 62 years (mean, 43). Nine tumors involved the lower extremity. In all tumors, MRI correctly identified the nerve trunk of origin. Tumor dimensions were generally overestimated by MRI. Three internal signal patterns were observed: homogeneous (1/1 benign), finitely inhomogeneous (5/5 benign), and hectically inhomogeneous (4/4 malignant). The number of visual fuzzy clusters (VFCRs) for each sequence did not allow reliable separation of benign and malignant entities, but when considered in aggregate, benign and malignant lesions segregated in different clusters. This implies that the likelihood of malignancy increases as the number of MR-identifiable tissue types per lesion increase. Three types of reaction (edema) were observed best on long repetition time/echo time (TR/TE) sequences, confined to immediate peritumoral region, intracompartmental, and extracompartmental. The first two patterns correlated well with clinicopathologic findings; however, the third pattern did not. Separation of indolent (benign) cellular masses from aggressive (malignant) ones by MR characteristics is difficult but VFCA shows promise for aiding this differentiation and deserves further investigation in larger study populations.