Full-day workshop
September 23, 2025
Location: DCC1-1F-107
Daejeon, Republic of Korea
Overview
The Efficient Medical AI (EMA4MICCAI) Workshop aims to address the critical need for computationally efficient and resource-conscious AI solutions in medical applications. As medical AI models grow in complexity and deployment scales, challenges such as high computational costs, energy consumption, expensive annotation expenses, and latency in real-time clinical environments have emerged as significant barriers to widespread adoption. EMA focuses on advancing research and fostering discussion around innovative strategies to enhance the efficiency, scalability, and accessibility of medical AI, while maintaining or improving performance and reliability.
While the MICCAI community has extensively explored medical AI development and application, the computational efficiency of these solutions remains underrepresented. EMA directly addresses this gap by focusing on the practical challenges and opportunities for optimizing medical AI training and deployment procedures for real-world use. By integrating computational efficiency into the conversation, EMA will contribute to the MICCAI mission of advancing healthcare through innovative and deployable technologies.
Aim and Scope
The EMA4MICCAI Workshop focuses on advancing computational efficiency in medical AI by exploring innovative techniques such as lightweight model architectures, resource-conscious deployment strategies, and energy-efficient computing. Key themes include optimizing deep learning models for medical imaging and diagnostics, enabling scalable and privacy-preserving federated learning, leveraging edge and embedded systems for real-time clinical applications, and benchmarking efficiency metrics to drive sustainable AI development in healthcare. By addressing these themes, the workshop aims to bridge the gap between cutting-edge AI research and practical, deployable solutions in medical environments.
Keywords/Topics of Interest
The EMA workshop will cover, but is not limited to, the following topics:
Lightweight Architectures for Real-Time Medical Imaging AI
Scalable Federated Learning for Privacy-Preserving Healthcare AI
High-Performance AI for Resource-Constrained Clinical Environments
Real-Time Decision Support Systems Using Low-Latency AI Models
Pruning and Quantization Techniques for Medical AI Model Compression
Efficient Generative Models for Medical Image Synthesis and Augmentation
Emerging Hardware Solutions for Efficient Medical AI Computing
Panelist & Invited Speakers
Technical University of Munich
The University of Sydney
University of British Columbia
The University of Hong Kong
University of Manchester
Alibaba DAMO Academy
The Chinese University of Hong Kong
ZEISS Corporate Research
Nagoya University
Technical University of Munich
Organizers
The University of Sydney
Alibaba DAMO Academy
TUM/MCML
Stanford University
University College of London
CAIR, HK-ISI
University of Edinburg
University of Strasbourg
TUM/MCML
Program Committee
Ruicheng Ao, The Hong Kong University of Science and Technology (Guangzhou)
Yuan Bi, Technical University of Munich/Munich Center for Machine Learning
Boyu Chen, University College London
Keqi Chen, University of Strasbourg
Beilei Cui, The Chinese University of Hong Kong
Chengliang Dai, Imperial College London
Wenzhen Dong, The Chinese University of Hong Kong
Zhicheng He, Beijing Jiaotong University
Yiming Huang, The Chinese University of Hong Kong
Yunsoo Kim, University College London
Feng Li, Technical University of Munich/Munich Center for Machine Learning
Ruochen Li, Technical University of Munich
Shi Li, University of Strasbourg
Wei Li, Shanghai Jiao Tong University
Yanheng Li, City University of Hong Kong
Zexi Li, University of Oxford
Zhihua Liu, University of Edinburgh
Zihao Luo, Shanghai Innovation Institute
Boyi Ma, University of Toronto
Xinyu Ma, Macao Polytechnic University
Chi Kit Ng, The Chinese University of Hong Kong
Bo Peng, University College London
Yaling Shen, Monash University
Zechao Sun, University of Adelaide
Rui Tang, Fuzhou University
An Wang, The Chinese University of Hong Kong
Guankun Wang, The Chinese University of Hong Kong
Hongqiu Wang, Hong Kong University of Science and Technology (Guangzhou)
Jie Wang, Pujiang Lab
Jingsong Wang, Shandong University
Junyi Wang, The Chinese University of Hong Kong
Wenyang Wang, The University of Sydney
Yu Wang, University College London
Yunheng Wu, Nagoya University
Shilong Yao, City University of Hong Kong
Jieming Yu, Hong Kong University of Science and Technology
Weiyi Zhang, The Hong Kong Polytechnic University
Yanguang Zhao, National University of Singapore
Conference Venue
Daejeon Convention Center
107 Expo-ro, Yuseong District, Daejeon, South Korea