Speaker: Ming Dong, Computer Science, Wayne State University

Time: Wednesday, February 4, from 2:30 pm to 3:30 pm

Location for in-person participants: 1146 FAB 

Zoom link for online audience: https://wayne-edu.zoom.us/j/92845590121?pwd=CpRA5Wa5gzSMn2xiVkR2abD83O5nrH.1

Title: GenAI for Image Synthesis/Translation with Applications for Medical Imaging

Abstract: Generative AI has opened up powerful new possibilities for transforming images across domains — from turning sketches into photorealistic pictures to enhancing medical images for clinical use. A central challenge in image-to-image translation is to create outputs that are not only realistic and diverse but also faithful and reliable when precision is required. In this talk, I will begin with a brief overview of recent advances in generative AI techniques. I will then introduce two of our recent advances: one that uses Brownian bridge dynamics to achieve high-quality and diverse translations efficiently, and another that ensures deterministic and faithful outputs when consistency is essential. Finally, I will share how we are extending these techniques to medical imaging applications, where reliability and precision are critical, highlighting both opportunities and challenges in applying generative AI in healthcare.

Bio: Ming Dong is currently a professor of Computer Science and the Director of the Machine Vision and Pattern Recognition Laboratory at Wayne State University. He is also a co-director of the MS program on Data Science and Business Analytics. His research interests include generative AI, deep learning, data mining, and multimedia analysis, with applications on medical imaging and health informatics. His recent research is supported by NIH, NSF, Nvidia and Lambda Superintelligence Could. He has published 150+ technical articles, many in premium journals and conferences, and has a H-index of 41 based on Google Scholars.

______________________________________________________________________

CAD Seminar Series: Advancing Knowledge, Innovation, and Collaboration in Computation, AI, and Data Science (CAD)

The CAD Seminar Series is a dedicated platform for advancing knowledge, fostering innovation, and promoting collaboration across the fields of Computation, Artificial Intelligence, and Data Science. This series brings together leading experts, researchers, and professionals to explore the latest developments, tackle emerging challenges, and drive forward-thinking solutions at the convergence of these critical disciplines.

Objectives

• Advance knowledge: Share cutting-edge research and insights that push the boundaries of what is known in CAD.
• Foster innovation: Encourage the development of novel ideas and solutions through interdisciplinary dialogue and creative thinking.
• Promote collaboration: Unite expertise across disciplines and build bridges between academia, industry, and government to address complex problems and create opportunities for joint ventures.

Target Audience: The CAD Seminar Series is designed for a diverse audience, including faculty, researchers, students, and professionals in Computation, AI, Data Science, and related fields. It serves as a forum for exchanging ideas, networking, and contributing to the growth of these rapidly evolving areas. We highly recommend in-person attendance to enhance engagement and networking opportunities with speakers and fellow participants.

Call for Participation: We welcome contributions from researchers, practitioners, and students. Whether presenting your work, participating in discussions, or attending as a learner, your involvement is crucial to the success of this collaborative initiative.