Ongoing Investigations

ADNI data is made available to researchers around the world. As such, there are many active research projects accessing and applying the shared ADNI data. To further encourage Alzheimer’s disease research collaboration, and to help prevent duplicate efforts, the list below shows the specific research focus of the active ADNI investigations. This information is requested annually as a requirement for data access.

Principal Investigator  
Principal Investigator's Name: Nidhal Abdulaziz
Institution: UOWD
Department: Faculty of Engineering and Information Sciences
Country:
Proposed Analysis: The proposed method constitutes for optimum accuracy through the application of two methods of feature extraction, fed separately to a chosen classification method, the Ada-SVM, in order to allow for accurate result confirmation. For the first feature extraction method, regional measures of the Magnetic Resonance Image are extracted via the Freesurfer method, focusing on the cortical volume and cortical thickness. The second method, on the other hand, pays emphasis on skull stripping via structure tensor. The sub regions recorded will then form a matrix to configure for a feature vector in each sample, which would be further classified via Ada-SVM, a method that would combine the diversity offered by Adaboost with the accuracy of Support Vector Machines (SVM) through the decreasing variation of the kernel width. This is done in order to abolish the effect of imbalanced data. Similarly, the probability-ranked measures from the Freesurfer are also fed to the Ada-SVM classifier for result verification. Effectiveness of the proposed method is then measured via four factors, namely: accuracy, sensitivity, specificity, and precision.
Additional Investigators  
Investigator's Name: Abigail Copaico
Proposed Analysis: The proposed method constitutes for optimum accuracy through the application of two methods of feature extraction, fed separately to a chosen classification method, the Ada-SVM, in order to allow for accurate result confirmation.