BRAIN Lab

---

Research Laboratory of Andreas Rauschecker, MD, PhD

Dr. Andreas Rauschecker is a neuroradiologist and a neuroscientist by training.  He is interested in better understanding brain function and dysfunction through the use of magnetic resonance imaging, and specially through the use of advanced image analytics and artificial intelligence applied to brain imaging data.  Dr. Rauschecker completed his undergraduate education in Biology and Psychology at Georgetown University and a Master's in Neuroscience at Oxford University.  He obtained his MD and PhD (Neuroscience) degrees at Stanford University.  He then completed his residency training in diagnostic radiology at the University of Pennsylvania and his neuroradiology fellowship at UCSF.  In addition to directing his laboratory, Dr. Rauschecker is attending neuroradiologist at UCSF and Benioff Children's Hospital, Associate Program Director of UCSF's Neuroradiology Fellowship Program, co-Executive Director of UCSF's Center for Intelligent Imaging (ci²), and co-chair of UCSF's Research Data Science Council.  In his spare time, Dr. Rauschecker loves exploring the outdoors, eating great food, and traveling to new places, especially with his family.

Neel is a fourth-year undergraduate at Georgetown University majoring in Neurobiology. His research interests include mapping white matter abnormalities in pediatric brain cancer survivors. In his free time, Neel enjoys playing the guitar and mountain biking. 

Gunvant is a fourth-year MD student at UCSF applying into Diagnostic Radiology residency. His research interests include developing explainable machine learning-based tools to aid radiologists in interpreting imaging and generating radiology reports. Outside of work, Gunvant enjoys rooting for the Warriors and playing piano.

Aditya is a junior at UC Berkeley majoring in Bioengineering. As of now, he's currently working on classifying radiology protocols using free clinical text as input. In the future, he hopes to develops computational tools which integrate seamlessly within the clinical environment and aid in providing accurate and effective diagnoses and treatment options. When he's not on his computer, he enjoys reading science fiction and getting flyered on Sproul.

Julien is a third-year French engineering student at Ecole polytechnique, majoring in Applied Mathematics. His research is centered around computational methods for brain tractography.

Mike is a radiology resident with a background in deep learning, statistical modeling, and image processing. He did his PhD in Computational Neuroscience at Boston University where he used calcium imaging to study the striatum in mice, and then moved from mice to humans in whom he worked to forecast disease progression in Alzheimer's dementia using structural MRI and survival modeling. He is interested in using imaging and machine learning to inform one another. In his free time, he enjoys reading and meditating.

Yannan Yu is a first year diagnostic radiology resident at UCSF. Her research focused on neuroimaging especially stroke imaging, including MR/CT perfusion, diffusion weighted imaging, vessel wall imaging. She has specific interest in artificial intelligence to improve diagnosis on medical imaging as well as improving prognostication and clinical workflow. Outside work, she enjoys painting, board game, forest/coastal foraging, and video gaming.

Erik is a graduate student of Data Science at University of Erlangen–Nuremberg studying machine learning and artificial intelligence (AI). He obtained his BS from the University of Applied Sciences Mittweida. His research is focused on MRI segmentation using transformer architectures. In his spare time he likes to play the guitar or go hiking.

Maxence Pajot is a Masters student at Ecole Normale Supérieure and Ecole Polytechnique, where he studies Applied Mathematics and Cognitive Science. His research pertains to reading, and the impact it has on white matter. For this, he studies MRI data from the ABCD dataset.

Soo is a second-year MD student at the Geisel School of Medicine at Dartmouth. He's interested in leveraging artificial intelligence and neuroimaging to better understand human cognition and develop prognostic tools for neurological and psychiatric disorders. When he's not looking at brain images, he enjoys watching movies, going on hikes, and jamming with friends.

Dr. Jeffrey Rudie completed his MD PhD at UCLA in neuroscience, followed by radiology residency at U Penn and Neuroradiology fellowship at UCSF. He is an emergency/neuroradiologist at Scripps Clinic in San Diego and an adjunct assistant professor of Radiology at UCSD. He is actively involved in both academic research and industry projects focused on developing artificial intelligence tools that can be integrated into the clinical workflow to improve the accuracy and efficiency of neuroradiology. This includes tools for automated segmentation and longitudinal assessment of intracranial metastases and diffuse gliomas.