Rate My Professor Mingchen Gao

Mingchen Gao is an Associate Professor in the Department of Computer Science and Engineering within the University at Buffalo's School of Engineering and Applied Sciences. He also serves as Program Director for the Engineering Sciences (Artificial Intelligence) MS Program at the Institute for Artificial Intelligence and Data Science. Gao earned his B.E. in Computer Science and Engineering from Southeast University in Nanjing, China, in 2007, and his Ph.D. in Computer Science from Rutgers University in 2014, with a doctoral thesis titled "Cardiac Reconstruction and Analysis from High Resolution CT Images" advised by Prof. Dimitris Metaxas. Prior to joining UB in 2017 as an Assistant Professor, he completed a postdoctoral fellowship at the National Institutes of Health's Center for Infectious Disease Imaging from 2014 to 2017. His earlier roles include research assistantships and internships at Rutgers University, Siemens Medical Solutions, and Google Inc.

Gao's research centers on big healthcare data, medical imaging informatics, computer vision, and machine learning. He develops algorithms to enhance AI models for medical image analysis, tackling issues such as adaptation to real-world data, handling limited samples for rare diseases, preserving patient privacy, and mitigating catastrophic forgetting in deep learning. Notable achievements include the National Science Foundation CAREER Award of $578,519 for AI-assisted medical imaging diagnostics. Other honors encompass the NIH Fellows Award for Research Excellence (2017), NIH Imaging Sciences Training Program Fellowship (2014-2016), IPMI Scholarship for Junior Researchers (2013), and Best Paper Award at the 6th Conference on Functional Imaging and Modeling of the Heart (2011). Key publications include "Joint solution for PET image segmentation, denoising, and partial volume correction" in Medical Image Analysis (2018), "Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning" in IEEE Transactions on Medical Imaging (2016), "Holistic classification of CT attenuation patterns for interstitial lung diseases via deep convolutional neural networks" (CMBBE 2016), and "Highly precise partial volume correction for PET images: An iterative approach via shape consistency" in IEEE ISBI (2015, oral). Gao advises PhD and MS students, serves on committees, and reviews for journals such as IEEE Transactions on Medical Imaging and conferences like MICCAI and ISBI. He is recognized as a faculty expert on AI-powered medical imaging techniques.