Objectives To evaluate the feasibility of proximal nerve MR neurography with diffusion tensor imaging (DTI) for differentiating Charcot-Marie-Tooth (CMT) 1A, CMT2, and healthy controls. Methods The diameters, fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD) of L4-L5 nerve roots, femoral nerve (FN), and sciatic nerve (SN) were compared. Receiver operating characteristic (ROC) curve analyses were conducted to evaluate the diagnostic performance. DeLong's tests were applied to compare multiple ROC curves. Intraclass correlation coefficients were calculated for interobserver agreement assessment. Results The diameters of the L4 nerve root, L5 nerve root, and SN of CMT1A patients were significantly larger than those of CMT2 patients and healthy controls. The FA values of all measured proximal nerves were significantly higher in controls (0.46 +/- 0.09, 0.46 +/- 0.08, 0.45 +/- 0.07, and 0.48 +/- 0.08) than in CMT1A patients (0.30 +/- 0.09, 0.29 +/- 0.06, 0.35 +/- 0.08, and 0.29 +/- 0.09). The FA values of the L5 nerve root, FN, and SN were significantly higher in controls (0.46 +/- 0.08, 0.45 +/- 0.07, and 0.48 +/- 0.08) than in CMT2 patients (0.36 +/- 0.06, 0.34 +/- 0.07, and 0.34 +/- 0.10). The MD and RD values of the L5 nerve root in CMT1A patients (1.59 +/- 0.21 and 1.37 +/- 0.21) were higher than those in CMT2 patients (1.31 +/- 0.17 and 1.05 +/- 0.14). The AUCs of the above parameters ranged from 0.780 to 1.000. For the measurements of nerve diameters, the ICC ranged from 0.91 to 0.97. For the measurements of DTI metrics, the ICC ranged from 0.87 to 0.97. Conclusions MR neurography with DTI is able to differentiate CMT1A patients, CMT2 patients, and healthy controls.