Speaker: Xishuang Dong

When: 12:00pm, Dec 2, 2020

Where: webinar/Zoom

Recording: [watch]


Coronavirus disease 2019 (COVID-19) is an ongoing global pandemic in over 200 countries and territories, which has resulted in a great public health concern across the international community. Imaging findings in CT scan and X-ray play a critical role in timely and accurate screening and fighting against COVID-19. Deep learning has been applied to recognize COVID-19 pathology by image classification and image segmentation. However, these studies focus on supervised deep learning techniques that require a large amount of annotated images to complete training models with high performance, which is not applicable for data analysis that is related to emerging events such as COVID-19 outbreak. To address this challenge, this paper proposed a semi-supervised deep learning model based on Residual Neural Network (ResNet) for COVID-19 pathology classification on medical images. Specifically, the proposed method is capable of completing classification with an extremely limited amount of annotated images and substantial unannotated images. Experimental results on the big medical image dataset COVIDx demonstrate that the proposed model is able to achieve very promising performance even by learning on the extremely limited amount of labeled medical images.

Speaker Bio

Dr. Xishuang Dong is a member of CRI Center for Computational Systems Biology at Prairie View A&M University (PVAMU). He is an Assistant Professor of Department of Electrical and Computer Engineering at PVAMU. He received B.S. degree in computer science and technique (sub-field of computer engineering) at Harbin University of Science and Technology, M.S. degree in computer software and theory (sub-field of computer engineering) at Harbin Engineering University, and Ph.D. in computer application (sub-field of computer engineering) at Harbin Institute of Technology.

His research interests include: (1) machine learning based computational systems biology; (2) biomedical data analytics; (3) deep learning methods and applications; (4) natural language processing.