Background and Purpose-Initial clinical assessment or conventional diffusion tensor imaging parameters alone do not reliably predict poststroke recovery of motor function. Recently, local diffusion homogeneity (LDH) has been proposed to represent the local coherence of water molecule diffusion and can serve as a complementary marker for investigating white matter alterations of the brain. We aimed to determine whether a combination of initial clinical assessment and LDH could predict motor recovery after acute subcortical infarction. Methods-Standard upper extremity Fugl-Meyer assessment and diffusion tensor imaging were performed 1, 4, and 12 weeks after onset in 50 patients with subcortical infarction. Proportional recovery model residuals were used to assign patients to proportional recovery and poor recovery groups. Tract-based spatial statistics analysis was used to compare diffusion differences between proportional and poor recovery outcomes. Multivariate logistic regression model was used to identify the predictors of motor improvement within 12 weeks after stroke. Results-The poor recovery group had lower LDH than the proportional recovery group, mainly in the ipsilesional corticospinal tract in the superior corona radiate and posterior limb of internal capsule 1 week after stroke (P<0.005; family-wise error corrected). Multivariate logistic regression analysis indicated that both initial Fugl-Meyer assessment and LDH in the ipsilesional corticospinal tract in the superior corona radiate and posterior limb of internal capsule were predictors of motor improvement within 12 weeks after stroke (G=47.22; P<0.001). Leave-one-out cross-validation confirmed a positive predictive value of 0.818, a negative predictive value of 0.833, and an accuracy of 0.824 (P<0.00001; permutation test). Conclusions-These results suggest that a combination of clinical assessment and LDH in the ipsilesional corticospinal tract in the acute phase can accurately predict resolution of upper limb impairment within 12 weeks after subcortical infarction.