• contact@aiih.cc
  • Jesus College, University of Cambridge, UK

Special Session: Multimodal Generative AI in Healthcare

AI is transforming healthcare with its great potential in combining and analyzing diverse data types, such as medical images, bio signals, and electronic health records, to enable comprehensive understanding of health conditions for improved decision-making. For example, multimodal AI helps to better understand complex relationships in different types of health data to provide more in-depth insights and predictions. Generative models have demonstrated immense potential in diverse application areas, such as synthesizing new data for rare conditions and minority groups to improve the diversity of training data, improving
model robustness and fairness while reducing reliance on scarce real-world examples. These advancements promise significant improvements in diagnosis, personalized treatment planning, and other healthcare applications. Recent developments in Multimodal Generative AI, including vision-language models and foundation models, have demonstrated potential in areas such as automatic radiology report generation, integrating electronic health records with imaging data, cross-lingual medical report creation, and clinical note analysis. Despite these advances, practical challenges remain. These include effectively integrating heterogeneous data modalities, ensuring model robustness and clinical utility, and addressing concerns about trust and reliability in these systems. This special session aims to feature innovative methods and applications of Multimodal Generative AI in healthcare that explore multimodal medical data such as radiology and pathology images, signals, medical reports, electronic health records, radiomics and genomics. It will also address key challenges, such as data integration and interpretability, and propose solutions to improve the reliability and effectiveness of multimodal AI approaches in healthcare.

Impact: The session offers a platform for AI and clinical researchers to share insights, exchange ideas, and collaborate on advancing healthcare applications of multimodal AI. Participants will gain exposure to cutting-edge techniques, real-world use cases, and the potential impact of these methods in transforming healthcare practices.

Organisers:

Submission format:

This Special Session welcomes both full length papers (12 pages plus up to 2 pages of references) and abstracts (up to 5 pages including references). Click here for detailed submission guidelines and templates.

Deadline:

All deadlines, including submission deadline and review timeline are the same as the main conference. Please follow this link to see all the Important Dates.

If you have any questions regarding this Special Session, please contact the organiser.

Click here to submit your papers on CMT.