Sina Farsiu

Associate Professor in the Department of Biomedical Engineering

Paul Ruffin Scarborough Distinguished Associate Professor of Engineering

Associate Professor in the Department of Ophthalmology

Associate Professor in the Department of Electrical and Computer Engineering

Associate Professor of Computer Science

Faculty Network Member of the Duke Institute for Brain Sciences

Campus mail: Box 3802 Med Ctr, Durham, NC 27710

Phone: (919) 684-6642

I am the director of the Vision and Image Processing (VIP) Laboratory. Along with my colleagues, we investigate how to improve early diagnostic methods and find new imaging biomarkers of ocular and neurological diseases in adults (e.g. age-related macular degeneration, diabetic retinopathy, Glaucoma, Alzheimer) and children (e.g. retinopathy or prematurity). We also develop automatic artificial intelligence machine learning and deep learning algorithms to detect/segment/quantify anatomical/pathological structures seen on medical images.

On another front, we study efficient signal processing based methods to overcome the theoretical and practical limitations that constrain the achievable resolution of any imaging device. Our approach, which is based on adaptive extraction and robust fusion of relevant information from the expensive and sophisticated as well as simple and cheap sensors, has found wide applications in improving the quality of imaging systems such as ophthalmic SD-OCT, digital X-ray mammography, electronic and optical microscopes, and commercial digital camcorders. We are also interested in pursuing statistical signal processing based projects, including super-resolution, demosaicing, deblurring, denoising, motion estimation, compressive sensing/adaptive sampling, and sensor fusion.

Education and Training

University of California at Los Angeles, Research Assistant, Electrical Engineering
University of California at Los Angeles, Postdoctoral Scholar, Electrical Engineering

Selected Grants and Awards

Publications

MimickNet, Mimicking Clinical Image Post- Processing Under Black-Box Constraints.

Image post-processing is used in clinical-grade ultrasound scanners to improve image quality (e.g., reduce speckle noise and enhance contrast).

Baseline Visual Field Findings in the RUSH2A Study: Associated Factors and Correlation with Other Measures of Disease Severity.

PURPOSE: Baseline visual fields to monitor the Rate of Progression in USH2A-related Retinal Degeneration (RUSH2A) study. DESIGN: Cross-sectional study within a natural history study.

Multimodal Coherent Imaging of Retinal Biomarkers of Alzheimer's Disease in a Mouse Model.

We acquired depth-resolved light scattering measurements from the retinas of triple transgenic Alzheimer's Disease (3xTg-AD) mice and wild type (WT) age-matched controls using co-registered angle-resolved low-coherence interferometry (a/LCI) and o

Spectroscopic optical coherence refraction tomography.

In optical coherence tomography (OCT), the axial resolution is often superior to the lateral resolution, which is sacrificed for long imaging depths.

Retinal cavitations in macular telangiectasia type 2 (MacTel): longitudinal structure-function correlations.

BACKGROUND/AIMS: To quantify retinal cavitation size over time in macular telangiectasia type 2 (MacTel) and to correlate changes with visual acuity and area of ellipsoid zone loss.

Assessing Ganglion Cell Layer Topography in Human Albinism Using Optical Coherence Tomography.

Purpose:To test whether ganglion cell layer (GCL) and inner plexiform layer (IPL) topography is altered in albinism. Methods:Optical coherence tomography scans were analyzed in 30 participants with albinism and 25 control participants.

Deep learning-based single-shot prediction of differential effects of anti-VEGF treatment in patients with diabetic macular edema.

Anti-vascular endothelial growth factor (VEGF) agents are widely regarded as the first line of therapy for diabetic macular edema (DME) but are not universally effective.