MCI Conversion Prediction Using 3D Zernike Moments and the Improved Dynamic Particle Swarm Optimization Algorithm

Mild cognitive impairment (MCI) conversion prediction is a vital challenge in the area of Alzheimer’s disease (AD) as it could determine possible treatment pathways for AD patients. In this work, we presented robust MCI framework based on 3D-Zernike Moment (3D-ZM) method that generates statistical features (e.g., shape, texture, and symmetry information) from 3D-MRI scans improved dynamic particle swarm optimization (IDPSO) finds an informative sub-set Zernike prediction. We quantified efficiency proposed large sample patients including 105 progressive-MCI (pMCI) 121 stable-MCI (sMCI) at baseline ADNI dataset. Using framework, pMCI were distinguished sMCI with accuracy exceeding 75% (sensitivity, 83%, specificity, 68%), which well comparable state-of-the-art approaches. Experimental results indicate 3D-ZM can represent patterns IDPSO has great capability to find meaningful identifying who are risk stage.