This $252,456 National Science Foundation Project Grant supports the development of generative deep learning algorithms and a data-driven approach to produce additional high-resolution information from low-resolution optical coherence tomography images of coronary arteries. Funded under the NSF's Computer and Information Science and Engineering program (CFDA 47.070), this research aims to generate new super-resolution and cross-modality image translation techniques for improving pathological visualization in coronary imaging. Specifically, the grantee will develop volumetric super-resolution using a generative adversarial network to maintain fast scanning speeds while improving resolution for optical coherence tomography. An unpaired training scheme using a generative adversarial framework will also map optical coherence tomography images to histopathology images. This work is expected to benefit coronary disease treatment guidance and potentially other fields involving multi-camera surveillance and multimodal biomedical imaging. The Stevens Institute of Technology in Hoboken, New Jersey will receive the funding from January 1, 2022 to July 31, 2022 to carry out this technical research project.