Alzheimer’s Disease Prediction

Open Project: Alzheimer’s Disease Prediction

Type: Master Thesis

Contact Person: Sebastian Pölsterl, Christian Wachinger

Alzheimer’s disease (AD) is a neurodegenerative disorder and the most common form of dementia diagnosed in people over 65 years of age. Initially, patients suffer from short memory loss, until progressive deterioration eventually requires patients to be completely dependent upon caregivers due to severe impairment of cognitive and motor abilities. AD not only has a significant impact on a patient’s quality of life, but also comes with great economic costs associated with patient care.

For early diagnosis of AD and identifying patients that are at an increased risk for rapid progression to dementia, a variety of data is collected, including clinical, genetic, and imaging data. Magnetic resonance images (MRI) can be used to measure atrophy of the brain, as shown in the image below. In addition, levels of protein deposits (amyloid-beta) in the brain can be obtained from cerebrospinal fluid (CSF) or positron emission tomography (PET). In addition, genetic alterations can increase the risk for developing AD.

In this project, we will use multi-modal data for studying Alzheimer’s disease with a focus on MRI. The goal of this thesis is to develop machine learning techniques for AD prediction that fully integrate multi-modal data.

    - Good programming skills in Python.
    - Experience in machine learning and statistics.
    - Experience in deep learning (PyTorch, TensorFlow, etc.) is desirable.
    - Experience in working with medical data is desirable.