Harini Veeraraghavan, PhD

I am an assistant attending computer scientist in the Department of Medical Physics. I work to combine techniques from machine learning and estimation theory with computer vision methods to solve difficult problems in automated and semi-automated image segmentation, using multiple imaging modalities and sequences for segmentation, tissue–tumor classification, and image registration. My work has resulted in the publication of several papers on robotics, computer vision, and medical image analysis.

My current research interests are focused on developing computer algorithms and software for computer-aided analysis of medical images.

After receiving a PhD in computer science in 2006 from the University of Minnesota, Twin Cities, I developed algorithms for human robot interaction using machine learning and computer vision as a postdoctoral fellow in the Computer Science Department at Carnegie Mellon. Subsequently, I worked as a computer vision scientist for General Electric Research, developing image analysis algorithms for interactive segmentation with active learning for robust tumor segmentation and techniques for multiple modality segmentation of hard-to-detect metastatic breast, kidney, and skin cancers.