Dr. Shepherd has a 30-year background in quantitative imaging. Most of his academic research involves developing novel biomarkers for a variety of imaging modalities including dual-energy X-ray Absorptiometry (DXA) scan for bone density and body composition, mammography for breast density and tissue textural measures as risk factors for breast cancer, and 3-D optical whole body scanning for quantifying body shape as a risk factor for metabolic diseases. Using these modalities, he uses advanced statistical methods to extract more information from images. The methods include principal component analysis, shape and appearance modeling, deep learning, and artificial intelligence approaches. While at UCSF he accumulated over 4 million mammograms for the study of breast cancer risk from imaging and was one of the first to show that volumetric breast density measures are a stronger risk predictor than areal density measures.