Principal Investigator: Assistant Professor Yu Gan
My research covers a wide spectrum of machine learning and deep learning techniques that facilitate biomedical imaging and dig out hidden information from medical/biomedical images.
I have been serving as PI for multiple research grants supported by National health institute (NIH), NJ Health Foundations, National Science Foundation (NSF), U.S. Department of Agriculture (USDA), and Burrough Wellcome foundation.
My research agenda aims to develop cutting-edge medical data analytics and human computer interaction techniques to unlock the value of big medical image data, obtain new insights, generate actionable guidance, and facilitate clinical decision making.
Super resolution and artifacts removal
We are developing a deep learning-based framework to enhance the optical and digital resolution of optical coherence tomography (OCT) systems. We develop a sparse representation-based method to removal saturation artifacts in OCT images.
We developed a region proposal network to identify diseased regions in human coronaries and football players in sports data analysis.
We developed a robust deep learning network to segment tissue regions within medical images.
We developed a de-noising framework to de-noise MRI and ultrasound images.
Cervical collagen fiber image analysis and image informatics to better our understanding of preterm birth
Breast cancer identification for surgical margin detection