Prof. Hongmin Cai

http://www2.scut.edu.cn/bioinformatics/

Biography: 

Hongmin Cai is a professor and doctoral supervisor at the School of Computer Science and Engineering, South China University of Technology. In 2016, he was promoted to doctoral supervisor and the professor in abnormality. Hongmin Cai is a visiting professor at Kyoto University, a member of the Bioinformatics and Artificial Life Committee of CAAI, a member of the Bioinformatics Committee and Standing Committee of CCF, and a PC Member of many international conferences such as ISBI, ISBRA, ICIC, BIBM and GIW. Professor Cai is also the Chairman of ICDKE 2012, ICBBB2021, ICBBB 2022, Vice Chairman of Guangdong Translational Medicine Ophthalmology Branch, Vice Chairman of Guangdong Precision Medicine Application Society - Digital Intelligence Branch, Vice Chairman of Guangdong Biomedical Engineering Society Intelligent Medical Imaging Branch. Professor Cai has been involved in the research work of biomedical image and biological information processing for a long time and has accumulated rich research experience in the fields of medical image analysis and understanding, biological information analysis, multi-source data fusion, pattern recognition and data mining. In related journals such as IEEE T-PAMI, IEEE T-Cybern, IEEE T-Image Proce., IEEE T-Medical Imaging, NeuroImage, Bioinformatics, Briefings in Bio., more than 100 SCI/EI papers have been published, including 80 SCI/EI papers regarding Professor Cai as the corresponding author or the first author. In recent 5 years, a total of 49 SCI/EI papers and 1 ESI highly cited paper have been published on the theory and application of integrated analysis of multi-source and small sample data. The total IF of the papers in recent 5 years exceeds 200.

Speech title: 

Research on the theory and application of integrated analysis of small sample data from multiple sources

Abstract: 

With the popularization of new generation sequencing technology and the rapid development of single cell sequencing technology, multi-omics data at different scales are derived. With the rapid development of various new imaging technologies, multimodal image data under different imaging conditions are derived. Such multi-source data has problems such as small sample size, high dimension, multi-mode, cross-scale and multi-attribute missing, etc. It is of great scientific significance to integrate and analyze such multi-source heterogeneous data, which can provide computing tools for life computation and medical assisted diagnosis. Our lab takes the integration theory of multi-source heterogeneous data as the research center, and establishes the tensor spectral clustering theory framework for small sample learning, so as to realize the effective fusion of multi-source information. In order to realize the medical and health-oriented data mining as the research goal, the micro multi-omics and macro image group related application analysis is carried out for two important data sources: genomics data and medical images. This report will report the research progress of our laboratory in the above three aspects.