Invited Speakers

Prof. Guoyan Zheng

Shanghai Jiao Tong University, China

Prof. Dr. Guoyan Zheng received his Ph.D. degree in Biomedical Engineering from University of Bern, Switzerland in 2002. He was an associate professor at the same university until the end of 2018. Since Jan. 2019, he is a full professor and the deputy dean of the Institute of Medical Robotics, Shanghai Jiao Tong University, China. He is also the director of the Center for Robot Vision and Image-Guidance. He has published more than 266 peer-reviewed papers in top-notch conferences and journals such as CVPR, MICCAI as well as IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Medical Imaging, Medical Image Analysis, Pattern Recognition, etc. The total number of Google citations of his work is more than 6810 times. He has been awarded 6 US patents and 2 European Patents, and won more than 10 national and international awards including the 1st Prize of the 2019 Global Innovation Design Competition of Medical Robotics, the Best Technical Podium Presentation Award at the 18th CAOS Annual Meeting, the Springer Best Paper Award at the 15th International Conference on Image Analysis and Recognition, the Best Paper Award in MICCAI 2017 International Workshop on Machine Learning in Medical Imaging, the Shape Modeling Grand Challenge Award in the 2014 International Conference on Statistical Shape Modeling, the Poster Award in the 2014 International Conference on Computer Assisted Radiology and Surgery, the Best Basic Science Paper published in the Journal of Laryngology and Otology in year 2011, the 2009 Ypsomed Innovation Prize on Research and Development, etc. He was a member of the board of directors of the International Society for Medical Image Computing and Computer Assisted Interventions. At this moment, he serves as an associate editor for IEEE Transactions on Biomedical Engineering, IEEE Journal of Biomedical and Health Informatics and Computerized Medical Imaging and Graphics.

Speech Title: Label-efficient Deep Learning for Medical Image Segmentation
Abstract: The past few years witnessed remarkable progress in computer vision and medical image analysis due to the increasing availability of data and the rapid development of deep learning techniques. Deep learning-based methods, such as convolutional neural networks, are excellent at learning from large amounts of data, but can be poor at generalizing learned knowledge to new datasets that differ from the training data, which hinders the effective deployment of deep learning models to clinical settings. Additionally, fine-labelled medical image data are hard to find and manually annotating pixel-/voxel-wise labels is time consuming, tedious, requirement of medical expertise and thus expensive. Consequently, the application of fully-supervised deep learning model for medical image segmentation is severely limited. In this talk, I will discuss our recent work on label-efficient deep learning for medical image segmentation. Applications to abdominal, cardiac and musculoskeletal image segmentation tasks will be presented.

Prof. Hongkai Wang

Dalian University of Technology, China

Hongkai Wang, professor of biomedical engineering at Dalian university of technology, China. His research interests include medical image processing and digital human modeling. He received the B.Eng. degree in electronic information engineering from Beihang University, Beijing, China, in 2003, and the Ph.D. degree in biomedical engineering from Tsinghua University, Beijing, in 2009. From 2009 to 2011, he was a Post-Doctoral Fellow with the University of California, Los Angeles, CA, USA, where he was a Senior Researcher from 2011 to 2014. From 2014, he became a faculty of Dalian university of technology China. He developed deformable digital phantoms of Chinese human and laboratory mice which have been commercialized by Chinese and American enterprises. He has published in top-level journals including IEEE Transactions on Medical Imaging and Medical Image Analysis and is also serving as a reviewer of these journals. He is the member of IEEE and the MICCAI society, as well as the co-founders and committee members of international digital medicine council and the Medical Image Computing Society, respectively.

Speech Title: Deformable Digital Human Phantoms Based on Large Medical Image Dataset
Abstract: Digital human phantoms are widely used in biomedical simulation and digital medicine. Nowadays, digital human phantoms have been developed in different countries. Most of these phantoms were constructed using a limited number of carvada cryosection images or living subject medical images. Due to the lack of a large sample set, most current phantoms do not represent the statistical features of the large population. In our study, over a thousand whole-body CT images were collected from the hospitals across the country. Artificial intelligent methods were developed to segment anatomical structures and construct three-dimensional models from the CT images. Statistical shape modelling method was used to learn inter-subject anatomical variations from the segmented structures. A whole-body scale deformable phantom was developed for the Chinese population. The phantom includes over one hundred shape parameters to adjust the anatomical features such as height, weight, body mass index, internal organ distribution, local body part shape, heart motion and facial features. Physiological features like bone density and glucose metabolism were also learned from the sample images (CT and PET) and were incorporated into the phantom. We have developed automatic methods to register the phantom to personal photo, video, medical images or body surface scans to realize individualized modelling. The phantom has been used for digital twin modelling, biomechanical and electromagnetical simulation, ergonomics product design, sports training, surgical planning and anatomy education. Software products based on this phantom has been used by numeric hospitals, research institutes and enterprises.

Prof. Li Zhang

South-Central Minzu University, China

Graduated from School of Optics and Electronic Information, Huazhong University of Science and Technology, Ph.D. in Engineering. Professor of South-Central Minzu University, the first batch of the Ministry of Education's national pool of 10,000 outstanding innovation and entrepreneurship mentors, the Ministry of Education's Degree Center's pool of experts, and accredited expert of Shenzhen, Jiangsu, Jiangxi, Hubei and other provincial science and technology department, presided over and participated in many national and provincial projects, published more than thirty SCI/EI indexed papers. The main research interests are: physiological signal detection and processing, development and design of intelligent instruments, artificial intelligence and medical data mining, etc.

Speech Title: Health "guardians"-Multi-physiological Parameters Remote Monitoring Service Platform
Abstract: Cardiovascular disease is the first factor of human death, cardiovascular diseases are mostly chronic diseases, long course, accompanied by several years or lifelong, some will be acute attack, found late or even sudden death, but if we can do in daily life to carefully monitor the physiological indicators related to the disease, such as: pulse, blood pressure, blood sugar, weight, etc., abnormalities, timely medical care, and improve lifestyle, most cardiovascular diseases can be effectively controlled.

The current home medical testing devices are single and isolated in function and do not have data storage, data analysis and networking functions, which are not conducive to long-term monitoring and tracking of chronic diseases, so we built a remote monitoring service platform for multiple physiological parameters based on artificial intelligence and Internet of Things technology. The platform includes two parts: front-end multi-physiological parameter collection and health monitoring platform. The front-end measures users' multi-physiological indicators and uploads them to the cloud platform for storage with one click, while artificial intelligence diagnostic algorithms such as ECG and heart rate abnormalities are deployed in the cloud platform to detect abnormalities and alert them in time. The health monitoring platform generates a health report for each user, which includes daily recorded physiological indicators and visualized diagnostic reports and regular physical examination reports uploaded by the user himself, so that the user can have a good understanding of his own physical condition and intervene in a timely manner once abnormalities are detected, so that the physical condition is always balanced in a healthy state. In the future, we will cooperate with medical institutions to provide expert diagnostic services and build a bridge between patients and hospitals for the diagnosis of difficult problems.

Assoc. Prof. Li Xiao

Institute of computing, Chinese Academy of Sciences, China

Li Xiao, associate professor of Institute of computing, Chinese Academy of Sciences&Professor of Ningbo Huamei hospital, University of Chinese Academy of Sciences, and Recipient of Hundred Talented Program in Chinese Academy of Science. He has been deeply contributed to the modeling and computation of medical big data, invented a series of innovative algorithms such as multi-scale modeling, multi-layer GCN aggregation, multi-task training, He has collaborated with 20+ well-known hospitals, including Peking University Third Hospital, West China Hospital, Peking Union Medical College Hospital,, published 30+ papers on international high impact journals/conferences such as Science, MedIA, TMI, MICCAI, and invented 10+ intellectual property rights and transferred to relevant companies with millions of yuan.

Speech Title: Micro-scale Biomedical Computing System
Abstract: With the development of AI technique, AI for science and other related fields and technologies, using the computer to interpret micro-scale biomedical data has played an increasingly important role in basic biomedical research and clinical diagnosis and treatment. The speaker will introduce his research on relevant technologies and methods in molecular dynamics accelerated simulation and microscopic image intelligent diagnosis at multi-scales in this talk. He will also explore the prospects and challenges of the whole cell simulation and other frontier directions.

Assoc. Prof. Shulong Li

Southern Medical University, China


Shulong Li, associate professor and postgraduate supervisor of Southern Medical University, Ph.D majored in Pure Mathematics from Sun Yat-sen University, visiting scholar of National Sun Yat-sen University in Taiwan and visiting scholar of Southwest Medical Center (utsw) of University of Texas (2016.7-2017.11). She has presided over a number of general projects and youth projects of National Natural Science Foundation of China, seedling raising project of Guangdong Provincial Department of education and other projects, and has published more than 30 high-level papers, including medical image analysis (if = 11.148). Research interests include machine learning and deep learning, medical image analysis and medical artificial intelligence. Some progress has been made in AI assisted diagnosis and treatment of lung cancer and pancreatic cancer.

Speech Title: The intelligent CAD Algorithms in Pancreatic Cancer
Abstract: Pancreatic cancer (PC) is the malignant cancer of its kind; its mortality is almost that of its morbidity. Artificial intelligence (AI) based on medical data including medical images presents a great potential to improve this situation by constructing intelligent CAD algorithms. However, the studies on intelligent CAD algorithms in PC is still in its infancy because PC is a relatively uncommon but most deadly cancer. In this speech, the research status on intelligent CAD algorithms in PC is introduced; then our research advance on intelligent CAD algorithms in PC is introduced, including two aspects mainly based on CT images. The first is a multimodal model fusing multiphase contrast-enhanced CT and clinical characteristics for predicting lymph node metastases of PC; the second is a noncontrast CT-based algorithm for detecting the pancreatic lesions including various pathological types.

Assoc. Prof. Gen Li

Chongqing University of Technology, China

Gen Li is an Associate Professor in the Department of Biomedical Engineering at Chongqing University of Technology, where he has been since 2018. He received a B.S. in Electrical Engineering from Chongqing University of Technology in 2013, and a Ph.D. in Biomedical Engineering from Chongqing University in 2018. Since July 2021, he has become a Postdoctoral Researcher in the Department of Neurosurgery at Southwest Hospital. From September 2021, he has worked as a Visiting Scholar in Institute of Medical Engineering and Translational Medicine at Tianjin University. His research interests include wearable technology, non-invasive detection and processing of biomedical signals, etc. His research has been sponsored by the Natural Science Foundation of China, the Natural Science Foundation of Chongqing, the Science and Technology Research Project of the Chongqing Education Commission, the High-level Talents Research Startup Project, et al. He has published more than 20 papers in scientific journals. He also reviewed many manuscripts for more than 5 journals. In 2020, he was awarded the Chongqing Talent Innovation and Entrepreneurship Demonstration Team. In 2021, he was selected into the Western Light Talent Training Program of China.