1. Home »
  2. Supervisor: Dr. Syed Muhammad Usman
Supervisor: Dr. Syed Muhammad Usman

 

Alzheimer’s disease prediction using Multimodal Signals

 

Supervisor: Dr. Syed Muhammad Usman, Sr. Asst. Professor

Campus/School/Dept: BUIC H-11/BSEAS/CS

Supervisory Record:  

  • PhD Produced: Nil
  • PhD Enrolled: 02
  • MS/MPhil Produced: 08
  • MS/MPhil Enrolled: 01

 

Topic Brief Description:

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder and a leading cause of dementia, characterized by cognitive decline and memory impairment. Early and accurate prediction is critical for timely intervention and management. This research focuses on developing an advanced machine learning framework for Alzheimer’s disease detection using multimodal signals such as electroencephalography (EEG), magnetic resonance imaging (MRI), and functional MRI (fMRI). The integration of multimodal data allows for a comprehensive understanding of neural and structural changes associated with the disease, overcoming the limitations of single-modality analysis. The proposed approach will utilize deep learning and multimodal fusion techniques to analyze structural, functional, and electrophysiological patterns in the brain. By combining imaging data (MRI, fMRI) with temporal and spectral features from EEG signals, the model aims to identify disease biomarkers with higher accuracy and robustness.

 

Research Objectives/Deliverables:

  1. Develop a system that accurately predicts early signs of Alzheimer’s disease using multimodal data.
  2. Combine EEG, MRI, and fMRI signals to provide a comprehensive understanding of brain changes associated with Alzheimer’s.
  3. Extract meaningful structural, functional, and temporal features from each modality to enhance diagnostic accuracy.
  4. Ensure transparency in the model’s decisions by identifying critical biomarkers and making the results interpretable for clinicians.

 

Research Questions: 

  1. How can a machine learning-based system be designed to accurately detect early signs of Alzheimer’s disease using multimodal data?
  2. What techniques are most effective for integrating EEG, MRI, and fMRI data to provide a comprehensive understanding of brain changes associated with Alzheimer’s disease?
  3. How can structural, functional, and temporal features be effectively extracted from EEG, MRI, and fMRI data to improve diagnostic accuracy?
  4. What explainable AI methods can be employed to ensure transparency in model decisions and help identify critical biomarkers for clinical interpretation?

 

Candidate’s Eligibility Profile:

  1. The applicant must have an MS/MPhil/Equivalent degree in electrical engineering with CGPA >0. Besides, applicants must have a strong background in mathematics, programming, optimization theory and related fields.
  2. Experience with programming languages such as MATLAB, or Python is advantageous. Candidates should thrive in an international environment and have excellent communication skills to actively contribute to team research efforts.
  3. Proficiency in spoken and written English is essential. We value independence and responsibility while promoting teamwork and collaboration among colleagues.