Thalamus segmentation using multi-modal feature classification: Validation and pilot study of an age-matched cohort

Jeffrey Glaister, Aaron Carass, Tziona NessAiver, Joshua V. Stough, Shiv Saidha, Peter A. Calabresi, Jerry L. Prince

Abstract: Highlights•A Random Forest Thalamus Segmentation (RAFTS) algorithm is proposed using T1-w MRI, T2-w MRI, and DTI.•RAFTS achieves a higher mean Dice score compared to four state-of-art methods.•A pilot study exploring the difference in the thalamus fraction of multiple sclerosis and healthy patients is carried out.