VALSE Webinar: Computer-Assisted Intervention and Navigation: Challenges and Future Directions
The VALSE Webinar on Computer-Assisted Intervention and Navigation: Challenges and Future Directions will be held on July 10, 2024 at 20:00 (Beijing Time). The webinar will be hosted by Hao Chen (Hong Kong University of Science and Technology) and will feature two speakers: Hong Song (Beijing Institute of Technology) and Yueming Jin (National University of Singapore). The webinar will be live-streamed on Bilibili. Here is the detailed information about the webinar.
VALSE Webinar: Computer-Assisted Intervention and Navigation: Challenges and Future Directions
Date and Time:
July 10, 2024 (Wednesday)
20:00 (Beijing Time)
Topic:
Computer-Assisted Intervention and Navigation: Challenges and Future Directions
Host:
Hao Chen (Hong Kong University of Science and Technology)
Live Stream:
https://live.bilibili.com/22300737
Speakers:
Hong Song (Beijing Institute of Technology)
Title: Intelligent Analysis of Medical Images and Applications in Surgical Navigation
Yueming Jin (National University of Singapore)
Title: Intelligent Robotic Surgical Scene Understanding and Reconstruction
Panel Discussion Topics:
- Review the historical development of computer-assisted intervention and navigation, current challenges, and opportunities.
- Differences in the application of computer-assisted intervention and navigation technologies in various medical fields.
- The importance of data processing in computer-assisted intervention and navigation, ensuring data accuracy in medical scenarios, and effective methods and technologies to address issues such as small datasets and expensive annotations.
- Development trends of computer-assisted intervention and navigation in the era of large models and potential future directions.
Panelists:
Hong Song (Beijing Institute of Technology)
Yueming Jin (National University of Singapore)
Shuangyi Wang (Institute of Automation, Chinese Academy of Sciences)
Guochen Ning (Tsinghua University)
Wei Shen (Shanghai Jiao Tong University)
Liansheng Wang (Xiamen University)
Feel free to leave your questions related to the topic below. The host and panelists will select some of the most popular questions to include in the panel discussion!
The following is the detailed information about the speakers, panelists, and host of this VALSE Webinar.
Speaker: Hong Song (Beijing Institute of Technology)
Title: Intelligent Analysis of Medical Images and Applications in Surgical Navigation
Biography:
Hong Song is a professor at the School of Computer Science, Beijing Institute of Technology, a member of the Teaching Steering Committee of the Ministry of Education, and a standing member of the Intelligent Service Committee of the Chinese Association for Artificial Intelligence. She has long been engaged in research on AI-assisted diagnosis, image analysis and processing, and augmented reality surgical navigation. She has led over ten major projects, including key projects of the National Natural Science Foundation, national key R&D projects, and major projects of the “Next Generation Artificial Intelligence” initiative. She has published over 90 SCI papers in leading journals such as TIP, TFS, and JBHI, participated in the formulation of one medical treatment standard, and applied for/obtained over 70 national invention patents. She has developed three sets of multi-modal image-guided surgical navigation systems with independent intellectual property rights, which have been applied in over 200 hospitals and more than ten enterprises, earning six national Class II/III medical device registration certificates. As a major contributor, she has won the Wu Wenjun Artificial Intelligence Science and Technology Progress Award and the Outstanding Achievement Award for China Industry-University-Research Cooperation.
Personal Homepage:
https://cs.bit.edu.cn/szdw/jsml/js/sh/index.htm
Abstract:
Minimally invasive surgery has significant advantages such as small trauma, fast recovery, and fewer postoperative complications, and it is widely used in the treatment of diseases in fields such as oncology, head and neck surgery, and orthopedics. Surgical navigation provides “eyes” for minimally invasive surgery, significantly improving the precision, safety, and efficiency of surgeries. This report focuses on core issues such as preoperative intelligent planning, intraoperative intelligent perception, and intelligent guidance of targets in surgical navigation. It introduces the research progress of the team in multi-modal image intelligent analysis, including image segmentation modeling, image elastic registration and fusion, and motion deformation perception and compensation, as well as the development and clinical application of multi-modal image fusion augmented reality surgical navigation systems.
References:
Qing Guo, Hong Song, Jingfan Fan, Danni Ai, Yuanjin Gao, Xiaoling Yu, Jian Yang. Portal Vein and Hepatic Vein Segmentation in Multi-Phase MR Images Using Flow-Guided Change Detection. IEEE Transactions on Image Processing. 31: 2503-2517, 2022.
Qing Guo, Hong Song, Cong Wang, Jingfan Fan, Danni Ai, Yuanjin Gao, Xiaoling Yu, and Jian Yang. Segmentation of 3D Anatomically Diffused Tissues in Magnetic Resonance Images Through Edge-Preserving Constrained Center-Free Fuzzy C-Means. IEEE Transactions on Fuzzy Systems, 2024, 32(6): 3444-3457.
Jinfu Li, Lei Liu, Hong Song*, Yuqi Huang, Junjun Jiang, Jian Yang. DCTNet: A Heterogeneous Dual-Branch Multi-Cascade Network for Infrared and Visible Image Fusion. IEEE Transactions on Instrumentation and Measurement, 72: 5030914, 2023.
Dingkun Liu, Danni Ai, Tianyu Fu, Yuanjin Gao, Jingfan Fan, Hong Song, Deqiang Xiao, Ping Liang*, Jian Yang. Local Contractive Registration with Biomechanical Model: Assessing Microwave Ablation after Compensation for Tissue Shrinkage. IEEE Journal of Biomedical and Health Informatics, 2024, 28: 415-426.
Qiang Li, Hong Song, Fengbo Yang, Zenghui Wei, Jingfan Fan, Danni Ai, Yucong Lin, Xiaoling Yu*, Jian Yang. Densely Connected U-Net with Criss-Cross Attention for Automatic Liver Tumor Segmentation in CT Images. IEEE-ACM Transactions on Computational Biology and Bioinformatics, 20(6): 3399-3410, 2022.
Jingshu Li, Tianyu Fu, Hong Song, Jingfan Fan, Deqiang Xiao, Yucong Lin, Ying Gu*, Jian Yang. Embedding-Alignment Fusion-Based Graph Convolution Network with Mixed Learning Strategy for 4D Medical Image Reconstruction. IEEE Journal of Biomedical and Health Informatics, 2024, 28(5): 2916-2929.
Li, Wentao, Song, Hong, Ai, Danni, Shi, Jieliang, Wang, Yuanyuan, Wu, Wencan*, Yang, Jian. Semi-supervised segmentation of orbit in CT images with paired copy-paste strategy. Computers in Biology and Medicine, 2024, 171: 108176.
Speaker: Yueming Jin (National University of Singapore)
Title: Intelligent Robotic Surgical Scene Understanding and Reconstruction
Biography:
Dr. Yueming Jin is an Assistant Professor in the Department of Biomedical Engineering and Electrical and Computer Engineering at the National University of Singapore. Previously, she was a senior research fellow in the Department of Computer Science at University College London. She received her Ph.D. from the Department of Computer Science and Engineering at The Chinese University of Hong Kong. Her research interests include developing artificial intelligence and machine learning techniques with a focus on medical image and robotic surgical data science. She received the Hong Kong PhD Fellowship in 2015 and several prestigious awards, including three best paper awards, the 1st prize of Best Paper Award of IJCARS-MICCAI 2021, Best Paper Award in Medical Robotics at ICRA, and Best Paper Award of MedIA-MICCAI in 2017. She has led teams to win several international grand challenges in AI for medical vision analysis and has published over 40 papers in top-tier conferences and high-impact journals. She serves as Area Chair of MICCAI’23-24, Publicity Chair of IEEE-RAS RoboSoft’23, Session Chair of ICRA’21, and Workshop and Challenge Organizer of ICLR’23, MICCAI’22-24. Her current Google Scholar citation count is over 3300 with an h-index of 24. She is listed in Forbes 30 Under 30 Asia.
Personal Homepage:
Abstract:
Robotic-assisted surgery has revolutionized modern minimally invasive surgery by significantly enhancing the dexterity and overall capability of surgeons. Automatic and intelligent visual analysis is fundamentally crucial for promoting cognitive assistance in robotic-assisted surgery. In this talk, I will present our latest interdisciplinary research in artificial intelligence for various surgical visual tasks to improve surgical visual question answering, robotic scene referring segmentation, and 3D reconstruction. The proposed methods cover a wide range of AI topics, including the design of network architectures and novel learning strategies such as vision foundation models, video-language learning, and Gaussian Splatting. The challenges, up-to-date progress, and promising future directions of intelligent robotic surgery will also be discussed.
Panelist: Shuangyi Wang (Institute of Automation, Chinese Academy of Sciences)
Biography:
Shuangyi Wang is a researcher at the Institute of Automation, Chinese Academy of Sciences, and a professor at the School of Artificial Intelligence, University of Chinese Academy of Sciences. He also serves as a professor at the Hong Kong Innovation Institute of Artificial Intelligence and Robotics of the Chinese Academy of Sciences. He has been selected for the Overseas High-Level Talent Program of the Chinese Academy of Sciences and the Xiaomi Young Scholar Program of the University of Chinese Academy of Sciences. He has long been engaged in interdisciplinary research on robotics, control, and medical imaging. He has published over 50 academic papers in high-level journals and conferences such as TMECH, TIE, TIM, TMRB, ICRA, and IROS. He has collaborated with several leading medical device companies to achieve technology transfer and has successfully conducted landmark clinical trials of robot-assisted imaging and surgery, which have been reported by authoritative media such as People’s Daily.
Personal Homepage:
https://people.ucas.edu.cn/~shuangyiwang
Panelist: Guochen Ning (Tsinghua University)
Biography:
Guochen Ning received his bachelor’s degree in biomedical engineering from Northeastern University in 2014 and his Ph.D. in biomedical engineering from Tsinghua University in 2021. He became an assistant researcher at Tsinghua University in the same year and was promoted to assistant professor, special researcher, and doctoral supervisor in 2023. His research focuses on key issues in autonomous robot diagnosis and treatment integration and clinical translation applications. He has conducted systematic research in the interdisciplinary fields of clinical medicine, robotics, automation, and medical imaging. He has published over 40 papers in academic journals and conferences in the interdisciplinary fields of medical and engineering, including IEEE Trans. series, Medical Image Analysis, Theranostics, and has received several international and domestic academic conference outstanding paper awards. He was selected for the 9th China Association for Science and Technology “Young Talent Support Project” and has led several research projects, including those funded by the National Natural Science Foundation.
Personal Homepage:
Panelist: Wei Shen (Shanghai Jiao Tong University)
Biography:
Wei Shen is a tenured associate professor and doctoral supervisor at the Institute of Artificial Intelligence, Shanghai Jiao Tong University. He is a recipient of the National Outstanding Youth Fund and a high-level overseas talent introduced by Shanghai. His research focuses on computer vision and medical image processing. He has published over 50 papers in top journals and conferences in the field of artificial intelligence, such as IEEE TPAMI, IEEE TIP, IEEE TMI, NeurIPS, CVPR, and ICCV, with over 10,000 citations on Google Scholar. He serves as Area Chair for NeurIPS 2023/2024, CVPR 2022/2023, and ACCV 2022, and as an editorial board member of the SCI journal Pattern Recognition and vice-chair of the Computer Vision Committee of the Shanghai Computer Society. His representative work won the MICCAI 2023 Young Scientist Award.
Personal Homepage:
https://shenwei1231.github.io/
Panelist: Liansheng Wang (Xiamen University)
Biography:
Liansheng Wang graduated from the Chinese University of Hong Kong and is a professor and doctoral supervisor at the School of Information Science and Engineering, Xiamen University, and a dual-appointed professor and doctoral supervisor at the Department of Gastroenterology, School of Medicine, Xiamen University. He is also the deputy director of the Digital Fujian Institute of Health and Medical Big Data, the head of the Medical Artificial Intelligence Research Institute at Xiamen University, and the deputy leader of the AI Group of the Radiology Branch of the Fujian Medical Association. He has long been engaged in research on medical image processing and has led and participated in several research projects, including the National Natural Science Foundation Instrument Special Project, the Science and Technology Innovation 2030 Project of the Ministry of Science and Technology, national key R&D projects, and National Natural Science Foundation projects. He has published over 120 research papers, including in Nature Machine Intelligence, Nature Communications, IEEE Transactions on Medical Imaging, Medical Image Analysis, and top AI conferences such as CVPR and AAAI. He has received the Tencent Rhino-Bird Research Award, the Second Prize of Fujian Science and Technology Progress Award, the First Prize of the Xiamen University Tian Zhaowu Interdisciplinary Award in 2023, and has led teams to win championships in 11 international medical imaging competitions.
Personal Homepage:
Host: Hao Chen (Hong Kong University of Science and Technology)
Biography:
Hao Chen is an assistant professor in the Department of Computer Science and Engineering and the Department of Chemical and Biological Engineering at the Hong Kong University of Science and Technology. His research interests include trustworthy artificial intelligence, medical image analysis, and explainable deep learning. He leads the Smart Lab, which focuses on cutting-edge research and translational applications of trustworthy AI technologies in the medical field. He received his Ph.D. from the Chinese University of Hong Kong in 2017. He has published over 100 papers in top journals and conferences such as MICCAI, IEEE-TMI, MIA, CVPR, ICCV, AAAI, IJCAI, Radiology, Lancet Digital Health, and Nature Machine Intelligence, with over 25,700 citations on Google Scholar and an h-index of 64. He has been listed in Stanford University’s top 2% of scientists globally and has extensive industrial research and technology transfer experience, holding over 20 patents in AI and image analysis. He has received several awards, including the 2023 Asian Young Scientist Award, the Second Prize of the Ministry of Education’s Higher Education Scientific Research Outstanding Achievement Award, the First Prize of Beijing Science and Technology Progress Award, the MICCAI Young Scientist Impact Award in 2019, the Elsevier-MICCAI Best Paper Award, the Best Paper Award at the Medical Image and Augmented Reality Conference, and the Forbes China 30 Under 30. He serves as an editorial board member for journals such as IEEE TNNLS, J-BHI, CMIG, and Medical Physics, and has served as Area Chair and Program Committee member for conferences such as ACM MM 2024, MICCAI 2021-2023, MIDL 2022-2024, and CVPR 2024. He has led teams to win over 15 international medical image analysis challenge championships.
Personal Homepage:
https://cse.hkust.edu.hk/~jhc/
Special thanks to the main organizers of this Webinar:
Main AC: Hao Chen (Hong Kong University of Science and Technology)
Co-organizing AC: Wei Shen (Shanghai Jiao Tong University) How to Participate:
VALSE Webinars are held weekly and streamed live on Bilibili. Follow us on Bilibili by searching for VALSE_Webinar!
Live Stream: https://live.bilibili.com/22300737
Historical Videos: https://space.bilibili.com/562085182/
VALSE Webinars are usually held at 20:00 on Wednesday evenings, but may occasionally be adjusted due to speaker time zones. To stay updated, follow the VALSE WeChat official account: valse_wechat or join the VALSE QQ group, Group Number: 863867505.
Note: To join the VALSE QQ group, you need to verify your name, organization, and identity. After joining, please use your real name, identity, and organization. For identity format, please use T for school and research institution personnel; I for enterprise R\&D; D for PhD students; M for master’s students.
The VALSE WeChat official account usually announces the next week’s Webinar report on Thursdays.
You can also directly check the Webinar activity information by visiting the VALSE homepage: http://valser.org/. The PPTs of the Webinar reports (with the speaker’s permission) will be updated at the bottom of each report notice on the VALSE website.