The research goals of Dr. Wu’s group are to improve the diagnosis, prognosis and management of patients with brain injury by quantifying and monitoring injury or recovery on an individual patient basis. The group focuses particularly on stroke, cardiac arrest and traumatic brain injury. Predicting a patient’s response to different treatment strategies prior to therapeutic intervention can aid clinical decision-making and thereby improve patient outcome. Her research concentrates on the development of machine-learning algorithms which combine multiple MRI modalities and clinical data to assess tissue injury and recovery and ultimately patient-centered outcomes. In addition to algorithm development, her research involves the refinement of advanced MRI data acquisition and analysis and development and validation of quantitative imaging biomarkers.

Education

PhD in Electrical Engineering, Massachusetts Institute of Technology (MIT)

Select Publications

1. Wu O, Koroshetz WJ, Ostergaard L, Buonanno FS, Copen WA, Gonzalez RG, Rordorf G, Rosen BR, Schwamm LH, Weisskoff RM, Sorensen AG. Predicting tissue outcome in acute human cerebral ischemia using combined diffusion- and perfusion-weighted MR imaging. Stroke. 2001 Apr;32(4):933-42.

2. Wu O, Østergaard L, Weisskoff RM, Benner T, Rosen BR, Sorensen AG. Tracer arrival timing-insensitive technique for estimating flow in MR perfusion weighted imaging using singular value decomposition with a block-circulant deconvolution matrix. Magn Reson Med. 2003 Jul;50(1):164-74.

3. Wu O, Sorensen AG, Benner T, Singhal AB, Furie KL, Greer DM. Comatose patients with cardiac arrest: predicting clinical outcome with diffusion-weighted MR imaging. Radiology. 2009 Jul;252(1):173-81.

4. Wu O, Winzeck S, Giese AK, Hancock BL, Etherton MR, Bouts MJRJ, Donahue K, Schirmer MD, Irie RE, Mocking SJT, McIntosh EC, Bezerra R, Kamnitsas K, Frid P, Wasselius J, Cole JW, Xu H, Holmegaard L, Jiménez-Conde J, Lemmens R, Lorentzen E, McArdle PF, Meschia JF, Roquer J, Rundek T, Sacco RL, Schmidt R, Sharma P, Slowik A, Stanne TM, Thijs V, Vagal A, Woo D, Bevan S, Kittner SJ, Mitchell BD, Rosand J, Worrall BB, Jern C, Lindgren AG, Maguire J, Rost NS. Big Data Approaches to Phenotyping Acute Ischemic Stroke Using Automated Lesion Segmentation of Multi-Center Magnetic Resonance Imaging Data. Stroke. 2019 Jul;50(7):1734-1741.

5. Winzeck S, Mocking SJT, Bezerra R, Bouts MJRJ, McIntosh EC, Diwan I, Garg P, Chutinet A, Kimberly WT, Copen WA, Schaefer PW, Ay H, Singhal AB, Kamnitsas K, Glocker B, Sorensen AG, Wu O. Ensemble of Convolutional Neural Networks Improves  Automated Segmentation of Acute Ischemic Lesions Using Multiparametric Diffusion-Weighted MRI. AJNR Am J Neuroradiol. 2019 Jun;40(6):938-945.

Highlights

Martinos Investigator invited to AHA 2019 Research Leadership Academy

AJNR Paper: Ensemble of Convolutional Neural Networks Improves Automated Segmentation of Acute Ischemic Lesions Using Multiparametric Diffusion-Weighted MRI

MGH Advances in Motion Article: Deep Learning Automated Algorithms Accurately Segment Stroke Lesions

MGH News Release: Imaging may allow safe tPA treatment of patients with unwitnessed strokes

Website

Clinical Computational Neuroimaging Group