Introduction. Texture analysis was applied to MR images of peripheral nerves obtained with MR micro-neurography. Materials and Methods. Ankle tibial nerves were imaged at 3T in 10 patients affected with chronic inflammatory demyelinating neuropathy and 10 healthy subjects. Multiple subsets of textural features were compared, using different extraction methods and statistical analyses. The most discriminating features were selected and compared to the automatically extracted subsets. Results. Feature subset extracted from the whole pool of features performed better than the ones obtained by specific groups of features. Conclusion. Texture analysis may have a role in discriminating between pathologic and normal nerves.
This abstract and the presentation materials are available to members only; a login is required.