PIs: Dr. Matthew Rosen and Dr. Juan Iglesias Gonzalez

Portable MR imaging of stroke

The goal is to develop machine learning techniques to improve image quality and extract morphometric measures from low-resolution, low-SNR brain MR images acquired with a portable scanner.
PIs: Dr. Bin Deng, Dr. Jayashree Kalpathy-Cramer, Dr. Stefan Carp and Dr. Christopher Bridge

DeepTOBIDx – Deep learning-enabled real-time diagnostic tomographic optical breast imaging

PI: Dr. Christian Farrar

Deep Learning Aided Magnetic Resonance Fingerprinting of Tumor Apoptosis

PI: Dr. Christian Farrar and Dr. Matthew Rosen

An AI-Based Framework for Automated Discovery of Rapid Magnetic Resonance Fingerprinting Acquisition Protocols for Molecular Imaging

PI: Dr. Kristina Simonyan

DystoniaNet: A Deep Learning Platform for Dystonia Diagnosis and Treatment

Yao D, O’Flynn LC, Simonyan K. DystoniaBoTXNet: Novel Neural Network Biomarker of Botulinum Toxin Efficacy in Isolated Dystonia. Ann Neurol. 2023 Mar;93(3):460-471. doi: 10.1002/ana.26558. Epub 2022 Dec 14. PMID: 36440757.
PI: Dr. Kristina Simonyan

Brain Computer Interfaces: Decision Making and Dystonia Treatment

Valeriani D, O’Flynn LC, Worthley A, Sichani AH, Simonyan K. Multimodal collaborative brain-computer interfaces aid human-machine team decision-making in a pandemic scenario. J Neural Eng. 2022 Oct 17;19(5). doi: 10.1088/1741-2552/ac96a5. PMID: 36179659.
Simonyan K, Ehrlich SK, Andersen R, Brumberg J, Guenther F, Hallett M, Howard MA, Millán JDR, Reilly RB, Schultz T, Valeriani D. Brain-Computer Interfaces for Treatment of Focal Dystonia. Mov Disord. 2022 Sep;37(9):1798-1802. doi: 10.1002/mds.29178. Epub 2022 Aug 10. PMID: 35947366; PMCID: PMC9474652.


PIs: Kristina Simonyan, MD, PhD, DrMed, Srikantan Nagarajan, PhD, Julie Barkmeier-Kraemer, PhD

Scientific Core

The Core is responsible for the development of comprehensive clinical and imaging data repositories of patients with laryngeal dystonia and voice tremor and the use of these data for the development and testing of machine-learning algorithms for differential diagnosis of these disorders and the assessment of treatment outcomes.
The Scientific Core pursues the following goals: (1) Comprehensive clinical phenotyping; (2) Research data repository, and (3) Predictive data analytics. The Core’s significance is in developing and implementation of standardized data collection and analytical tools for their availability to all projects and associated investigators. In addition, data analytics based on common data across different projects and Center sites facilitates the development of unified diagnostic and treatment biomarkers for each of these disorders.