Publication Date

Spring 2020

Degree Type

Master's Project

Degree Name

Master of Science (MS)


Computer Science

First Advisor

Leonard Wesley

Second Advisor

Allyson Rosen

Third Advisor

Yulia Newton


Mild Cognitive Impairment, Computer Vision, Diffusion Compartmental Imaging, NODDI, Alzheimer's Disease


The result of applying the Neurite Orientation Density and Dispersion Index (NODDI) algorithm to improve the prediction accuracy for patients diagnosed with MCI is reported. Calculations were carried out using a collection of 68 patients (34 control and 34 with MCI) gathered from the Alzheimer’s Disease Neuroimaging Initiative database (ADNI). Patient data includes the use of high-resolution Magnetic Resonance Images as with as Diffusion Tensor Imaging. A Linear Regression accuracy of 83% was observed using the added NODDI summary statistic: Orientation Dispersion Index (ODI). A statistically significant difference in groups was found between control patients and patients with MCI with a power 0.96. In order to confirm performance, comparison of accuracy of prediction without the use and with the use of the ODI values is also presented. The impact of this increase in accuracy on the early detection of MCI is also presented. Results show a 4.68% increase in prediction accuracy through the inclusion of the ODI values. Future work includes the use of tractography to better locate the specific area of interest. Increasing the cohort would also add validity to the results in this paper. Expanding the number of tracts utilized in this study would also validate the use of the NODDI algorithm to detect neurological deterioration in tracts associated with memory. The inclusion of more complex prediction models would also add possible increases in performance in modeling patients with MCI.