This is a past event.

Chemistry Seminar Series
Dr.  Weihua Zhou,  Assistant Professor, College of Computing
Michigan Technological University

Abstract:
Machine learning (ML) has shown great advantages to overcome the challenges of high-dimensional complexity and inter-correlation among clinical predictors and help physicians make patient-specific clinical decisions related to diagnosis and treatment. Deep learning as a type of more complicated ML methods has been extensively used to extract information from medical records and images, and predict outcomes with a very high accuracy. Convolutional neural networks (CNN) are state-of-the-art deep learning techniques for computer vision, such as medical image segmentation and classification. This research talk will introduce our approaches of applying these artificial intelligence (AI) techniques to medical image analysis, particularly on image segmentation. We will also give an example about building a clinically accurate and practical AI-based software toolkit to improve percutaneous coronary intervention (PCI) for the treatment of patients with coronary artery disease. 

Bio:
Dr. Weihua Zhou, is an Assistant Professor of Applied Computing at Michigan Tech. He has been doing research on medical imaging and informatics since 2008. Prior to joining Michigan Tech, he was a post-doctoral fellow at Emory University School of Medicine from 2012 to 2015 and was an Assistant Professor of Computer Science at The University of Southern Mississippi from 2015 to 2019. Dr. Zhou’s research is driven by clinical significance. His research record includes more than 70 publications, 1 active patent, and 7 invention disclosures. His software applications are being used by 3 clinical trials and more than 30 hospitals.