The neurofibromatoses, including NF1, NF2, and schwannomatosis, are hereditary tumor predisposition syndromes caused by germline mutations in the NF1, NF2, and SMARCB1 tumor-suppressor genes, respectively.[1]–[4] Biallelic inactivation of these tumor-suppressor genes in susceptible cells leads to dysregulation of key cellular machinery, including activation of the Ras pathway (NF1), loss of contact-dependent inhibition of the EGFR pathway (NF2), and perturbation of the SWI-SNF chromatin remodeling complex (schwannomatosis).

These related syndromes have overlapping clinical features and for years, clinicians struggled to differentiate the types of neurofibromatosis. Clinical criteria were established for NF1 and NF2 in 1987 and for schwannomatosis in 2005.[5], [6] These patients share a predisposition to developing benign nerve sheath tumors, including neurofibromas and schwannomas, that are derived from neoplastic Schwann cells. Despite the benign histology of neurofibromas and schwannomas, neurofibromatosis patients have increased mortality due to malignant peripheral nerve sheath tumor (MPNST), glioma, cardiovascular disease, and organ compression by neurofibromas.[7], [8] For NF1 patients, the median age at death is 59 years, compared with 74 years for the general population.[9] For NF2 patients, actuarial survival after diagnosis is 85% at 5 years, 67% at 10 years, and 38% at 20 years.[10] Mortality figures for schwannomatosis have not been reported.

The spectrum of tumor involvement of these disorders is highly variable. In practice, clinicians carefully select the body region to image based on the presence of symptoms and knowledge of disease phenotype (e.g., cranial MRI for vestibular schwannomas in NF2 patients). Imaging of the entire body using traditional regional scans is not possible due to the cost (in time and money) of MRI. For this reason, data regarding the prevalence of whole-body disease patterns from large, multicenter cohorts are lacking.

Whole-body MRI (WBMRI) can evaluate the entire body in a relatively short time without the use of ionizing radiation. We performed an international multicenter study of WBMRI to assess tumor burden of internal nerve sheath tumors in NF1, NF2, and schwannomatosis. Our goal was to identify phenotypic similarities among these related neurogenetic disorders, to identify patterns of tumor involvement, and to relate tumor burden to demographic factors and cutaneous disease manifestations.

In this study, we used WBMRI to examine internal tumor burden in three closely related tumor-suppressor syndromes. Our findings corroborate that WBMRI can detect internal tumors in a far higher percentage of patients than conventional, regional imaging methods.[21] For example, the prevalence of plexiform or spinal nerve sheath tumors on regional MRI or CT scan ranges from 16%–39% in NF1 patients.[17], [22]–[25] Using WBMRI, we found that 60% of such patients have internal nerve sheath tumors. As expected, patients without a known history of internal tumor had high rates of lesions on WBMRI, indicating that asymptomatic tumors are common in this population [25].

Because WBMRI can detect even relatively small or asymptomatic tumors in all body regions, it provides a more comprehensive picture of tumor burden in patients and, for the first time, allows for analysis of tumor distribution across body parts. We used novel approaches to describe this distribution, including Gini coefficient to measure the regionality of tumor burden and clustering analysis to sort patients into groups based on tumor predilection. Our results show that internal nerve sheath tumors, like dermal neurofibromas, are not randomly or evenly distributed across body parts (see www.wholebodymri.org). Instead, particular body regions appear to be preferentially affected, while other body regions are relatively spared.

There are multiple processes that might explain why the pelvis and head/neck are particularly affected by internal tumors or why younger patients have a greater proportion of internal tumor volume in the pelvis and legs. Genetic mosaicism is well documented in neurofibromatosis and may be diagnosed when patients display disease features that are restricted to portions of the body (e.g., segmental findings).[26], [27] Alternatively, there may be tissue-specific biological factors in the affected regions that are permissive for tumor formation. It is increasingly clear that neurofibroma formation requires a microenvironment containing bone marrow-derived cells that are heterozygous at Nf1.[28] These biological factors could be important during development (e.g., for congenital lesions like plexiform neurofibromas) or post-natally (e.g., for non-congenital lesions like vestibular schwannomas). Genetically engineered mouse (GEM) models of NF1 and NF2 develop nerve sheath tumors in restricted locations that differ from humans.[29]–[31] Subsequent investigations of molecular biomarkers in both GEM and human tissue may help identify biological factors involved in these unique disease manifestations.

Overall, tumor burden and patterns of regionality were similar for the three tumor-suppressor syndromes. We observed a high prevalence of nerve sheath tumors in schwannomatosis patients (71%), NF1 patients (60%), and NF2 patients (42%). There was no difference in the median number of tumors but there was greater median tumor volume in NF1 patients than in NF2 or schwannomatosis patients. This difference was due to the increased prevalence of larger plexiform tumors in this population. The overall similarity in tumor burden among these conditions is striking given the diverse functions of the NF1, NF2, and SMARCB1 tumor-suppressor genes. Inactivation of NF1 leads to upregulation of RAS signaling [32]; inactivation of NF2 leads to dysregulation of cell surface receptors and intercellular signaling, and to disinhibition of the E3 ubiquitin ligase CRL4(DCAF1)[33], [34]; and inactivation of SMARCB1 leads to dysregulation of the SWI-SNF chromatin remodeling complex [35]. Current laboratory models do not explain the precise interaction between these pathways, but can be used to explore whether these separate pathways converge upon a final common pathway in Schwann cells.

Having an accurate phenotype of patients not only provides a basis for future research investigations, but has important implications for clinical management of NF patients. Our data identifies clinical risk factors for internal nerve sheath tumors in the neurofibromatoses; this information builds upon established genetic factors that influence tumor burden, such as NF1 gene microdeletions (increased tumor burden) [36] and mosaicism for the NF2 gene (decreased tumor burden).[27] In NF1 patients, decreasing number of cafe-au-lait macules correlated with the presence, but not volume, of internal neurofibromas (Figure 3). This finding, which was reported recently,[14] was not explained by increasing age since this variable was included in the multivariate model. An inverse relationship between the presence of neurofibromas and café-au-lait macules – the two cardinal features of NF1 – has been reported in rare variants of NF1. Patients with spinal neurofibromatosis have multiple spinal neurofibromas without café-au-lait macules whereas patients with a 3-bp inframe deletion in exon 17 of the NF1 gene have café-au-lait macules without neurofibromas.[37] Our data suggests that this inverse relationship may apply to a broader subset of patients than previously recognized. Further research should examine differential effects of germline NF1 mutations on melanocytes and Schwann cells since both are derived from neural crest cells.

Increasing numbers of subcutaneous tumors correlated with increasing neurofibroma volume in NF1 patients, corroborating previous reports [38] and presumably reflecting their shared biologic underpinnings with internal tumors. We also found that women with NF1 have greater tumor burden, on average, than men. Although the biological basis for this finding is not known, some studies have suggested that sex hormones may stimulate tumor growth. For example, tumor number and size increase in women during pregnancy,[17], [39] and in women using contraception with high doses of synthetic progesterone.[40] In addition, laboratory studies have implicated progesterone in neurofibroma progression.[41] Additional studies on the effect of sex hormones on tumor formation and growth are warranted to clarify this finding.

Our data identify scoliosis and decreasing numbers of cutaneous schwannomas as risk factors for internal schwannomas in NF2. While the presence of internal schwannomas correlated with scoliosis, it did not correlate with established markers of disease severity such as spinal tumors or meningiomas.[15], [16] For this reason, we suspect that scoliosis may result from spinal tumors rather than being a predisposing factor. Unexpectedly, whole-body tumor volume in NF2 patients was inversely correlated with the number of cutaneous schwannomas.[15] If this finding is confirmed, it further highlights the importance of different microenviroments in tumor formation. In schwannomatosis patients, no risk factors were identified for the presence of internal schwannomas although increasing age correlated with whole-body tumor volume. This finding may explain, in part, the late age at onset of symptoms compared to NF1 and NF2 [5].

The limitations of our study include the use of a sample of convenience at two large referral centers and the lack of children in the study population. For this reason, our study population does not represent all patients with neurofibromatosis or schwannomatosis. Additionally, coverage of the legs and arms by WBMRI may be incomplete in individuals who are tall or heavy. Our study did not include serial WBMRI scans of individual patients and therefore cannot determine the rate by which tumor count or volume changed with time. Future longitudinal studies of WBMRI in NF patients should quantify changes in tumor burden over time to better understand tumor progression.

In conclusion, in this large prospective international study, we found high rates of internal nerve sheath tumors in neurofibromatosis patients and showed that tumors were non-randomly distributed across body parts. These results provide valuable information about risk factors for internal nerve sheath tumors and raise new biological questions for future research. The addition of WBMRI to careful phenotyping represents a powerful approach to studying hereditary tumor predisposition syndromes and other complex genetic syndromes in humans.