IEEE CAI Workshop on Foundation Models for Healthcare 

About the Workshop

Foundation models have garnered significant attention from both research and industry communities. It holds profound potential for healthcare applications. These models, which can be trained using vast amounts of unlabelled data, including medical images, medical reports, and Electronic Medical Records (EMR), without requiring explicit data annotation, hold immense potential for healthcare AI. Their ability to be trained with diverse data from multiple sources offers numerous benefits, including reduced reliance on data annotation for fine-tuning and the capacity for robust generalization in real-world applications across various cohorts, ethnicities, and devices. This workshop aims to explore and advance the application of foundation models, especially multimodal foundation model including medical image, medical reports, genetic, etc. It will also look into foundation models from the lens of robustness, privacy preserving, explainable, federated and distributed perspectives in healthcare. The workshop will consist of keynote presentations, paper presentations, poster sessions, panel discussions, and hands-on tutorials to facilitate knowledge sharing and collaboration among participants.

 Call For Papers

This workshop is intended for researchers, practitioners, and industry professionals interested in the intersection of foundation models and healthcare applications. Participants will gain insights into cutting-edge research, practical implementations, and ethical considerations related to utilizing foundation models in the healthcare sector. 

The workshop will bring together experts and researchers to delve into a wide range of topics, including but not limited to:

1. Medical Image Foundation Model

   • Techniques for training foundation models on medical images.

   • Image synthesis and augmentation using foundation models for improved diagnostics.

   • Exploring the integration of radiomics and foundation models for medical image analysis.

2. Medical Report Foundation Model

   • Natural language processing approaches for training foundation models on medical reports.

   • Automated medical report generation and analysis.

   • Cross-lingual medical report understanding with foundation models.

3. Multimodal Medical Vision-Language Foundation Model

   • Techniques for combining medical images and reports in a single foundation model.

   • Integrating vision and language understanding for comprehensive healthcare solutions.

   • Multimodal transfer learning for improved patient care.

4. Genetic Foundation Model

   • Leveraging foundation models to analyze genetic data for personalized medicine.

   • Predictive modeling for genetic diseases.

   • Ethical considerations in genetic foundation model applications.

5. Robust Foundation Model for Healthcare

   • Ensuring model robustness against adversarial attacks and data variations.

   • Handling uncertainty and bias in healthcare predictions.

   • Case studies of real-world applications of robust foundation models in healthcare.

6. Efficient Foundation Model for Healthcare

   • Model compression and optimization techniques for resource-constrained environments.

   • Edge computing and on-device deployment of foundation models.

   • Balancing efficiency and accuracy in healthcare AI.

7. Privacy-Preserving Foundation Model for Healthcare

   • Techniques for preserving patient privacy in foundation model applications.

   • Federated learning and secure multiparty computation in healthcare AI.

   • Compliance with healthcare data regulations and standards.

8. Explainable Foundation Model for Healthcare

   • Interpretability and transparency in healthcare AI.

   • Visualizing foundation model decision-making in medical contexts.

   • Ethical and legal implications of explainable AI in healthcare.

9. Federated Foundation Model

   • Federated learning approaches for collaborative healthcare AI.

   • Privacy and security considerations in federated healthcare models.

   • Case studies of successful federated model deployments in healthcare.

10. Distributed Foundation Model

    • Scalability and distributed training of foundation models in healthcare.

    • Edge and cloud computing in healthcare AI solutions.

    • Ensuring real-time, distributed healthcare AI applications.

Please refer to the Submission page for submission instructions. 

Important Dates

Abstract submission: 31 Mar 2024 30 Apr 2024

Paper submission: 7 Apr 2024 30 Apr 2024

Outcome notification: 28 Apr 2024 21 May 2024

Program

Program

 Organization

Organizing Committee Members

Tentative List of Program Committee Members

• Behzad Bozorgtabar, EPFL

• Élodie Puybareau, EPITA Research and Development Laboratory (LRDE)

• Erjian Guo, University of Sydney

• He Zhao, Beijing Institute of Technology

• Heng Li, Southern University of Science and Technology

• Jiawei Du, IHPC, A*STAR

• Jinkui Hao, Cixi Institute of Biomedical Engineering, Ningbo Institute of Industrial Technology, CAS

• Kang Zhou, ShanghaiTech University

• Ke Zou, Sichuan university

• Olfa Ben Ahmed, University of Poitiers

• Pushpak Pati, IBM Research Zurich

• Sarah Leclerc, University of Burgundy

• Shaohua Li, IHPC, A*STAR

• Shihao Zhang, National University of Singapore

• Tao Zhou, Nanjing University of Science and Technology

• Xiaofeng Lei, IHPC, A*STAR

• Yan Hu, Southern University of Science and Technology

• Yanmiao Bai, Cixi Institute of Biomedical Engineering, Ningbo Institute of Industrial Technology, CAS

• Yanyu Xu, IHPC, A*STAR

• Yiming Qian, IHPC, A*STAR

• Yinglin Zhang, Southern University of Science and Technology

• Yuming Jiang, Nanyang Technological University