My research objectives are focused on the development of artificial intelligence technologies for neurology research. My graduate training revolved around medical engineering and offered me a multidisciplinary advanced education in computer science, physics, mathematics, biology, and chemistry. As I was progressing towards the start of my PhD, I decided to develop my expertise in machine learning— a type of artificial intelligence—and neurology, working for example on the automatic classification of fMRI signals of the auditory cortex under the supervision of Dr. Takerkart during my studies in Centrale Marseille, France. In Germany, I strengthened my expertise in machine learning in Prof. Navab's chair and developed and published an automated method for the segmentation of medical images based on Markov Chain Monte Carlo. During my PhD in the Netherlands, I focused on deep learning and neurology and developed methods for weakly supervised learning, regression neural networks, and brain lesion detection and quantification from MRI. One of my major contribution is my work on the automated quantification and detection of enlarged perivascular spaces—a type of brain lesion related to cerebral small vessel disease. During my PhD, I visited Prof. Rost group at MGH, Harvard Medical School, to strengthen my expertise in neurology research, and developed and published deep learning registration methods for clinical brain MRI. I am now doing my postdoctoral training in Prof. Daniel Rubin's group at Stanford with the additional supervision of the neurologist Prof. Lee-Messer. I am developing deep learning methods to detect and predict seizures from EEG and video recordings of epileptic patients.

Stanford Advisors