Farshad Falahati

I hold a PhD in Neuroscience and have a technical background in biomedical engineering. My expertise centers around medical imaging, with a strong focus on imaging techniques such as MRI and PET. Over the past 12 years, I’ve been working extensively with advanced MRI methods to study structural and functional patterns in the brain. Additionally, I have substantial experience in data analytics and machine learning, applying these tools to streamline processing workflows and uncover complex patterns in neuroimaging data. I am passionate about bridging science and technology, from understanding the physics behind imaging techniques to leveraging machine learning solutions for more efficient and insightful data analysis.

My primary research interest lies in understanding how the brain’s function and structure evolve during normal aging and in neurodegenerative disorders such as Alzheimer’s disease. I am particularly focused on leveraging state-of-the-art neuroimaging and machine learning techniques to analyze neuroimaging data, aiming to uncover patterns and extract meaningful insights.

I apply advanced neuroimaging techniques, including MRI and PET, alongside machine learning, to develop automated methods for segmentation and quantification of brain structures. A key aspect of my work is utilizing deep learning for automated midbrain segmentation using quantitative susceptibility mapping, which advances our understanding of iron accumulation in midbrain nuclei as we age.

Additionally, I developed a novel machine learning-based disease severity index for the early detection and monitoring of Alzheimer’s disease, with promising potential for identifying subtypes of the disease.

I am involved in several collaborative projects at ARC, including:

• The IronAge study (PI: Grégoria Kalpouzos), which investigates the effects of brain iron on neural activity and cognitive function in aging
• The Dynamic study (PI: Alireza Salami), which explores neurocognitive mechanisms of healthy aging using multimodal brain mapping techniques
• The ElastAge study (PI: Grégoria Kalpouzos), which investigate the biomechanical properties of the brain tissue in normal aging and preclinical AD using Magnetic Resonance Elastography
• The StoneAge study (PI: Goran Papenberg), which extends the IronAge study by linking iron accumulation with neuroinflammation
• The Long-Covid project (PI: Erika Jonsson Laukka), which is focused on the cognitive and olfactory deficits in post-COVID-19 syndrome
• The SNAC-K project (PI: Laura Fratiglioni), which examines aging and cognitive decline in a large, population-based cohort

Through these projects, our collaborative efforts aim to deepen our understanding of the mechanisms underlying brain aging, while my primary focus is on developing and applying advanced neuroimaging techniques to more accurately assess brain structures and functions.

• MRI Physics and Instrumentation, Introduction to Brain Imaging in Neuroscience (Master's course), 2021 – present
• Machine Learning: Applications in Aging Research, Integration of neuroimaging and cognition in normal aging and dementia (PhD course), 2023
• Structural and Functional MRI Workshop, Integration of neuroimaging and cognition in normal aging and dementia (PhD course), 2023
• Neuroimaging Workshop, Frontiers in Translation Medicine (Master's course), 2015 – 2017
• Neuroimaging Workshop, Molecular brain imaging techniques in neurodegenerative disorders (PhD course), 2016