Integrating Artificial Intelligence (AI) in medicine transforms healthcare delivery, diagnostics, treatment planning, and patient care. This minitrack aims to explore the role of AI in medicine, with a particular focus on the infrastructures required for large-scale distribution of deep learning technologies, generative algorithms, and intelligent agents. We invite contributions that discuss the development, deployment, and evaluation of AI frameworks and systems in healthcare, including but not limited to: predictive analytics in patient care, personalized medicine, medical imaging analysis, and automated clinical decision support systems.
One of the most demanding challenges for AI development in medicine is the standardization and management of large quantities of multimodal, highly sensitive data. The complete workflow for AI model creation starts from data acquisition by clinical experts, through storing, sharing, anonymizing, and labelling of the data. The workflow also includes creating and maintaining pipelines for training and validating AI systems. All these processes can – and should be – supported by modern, state-of-the-art information and communication technology (ICT) infrastructures.
With disruptive new trends in AI in medicine, such as Generative AI, Agent Foundation Models, and Few-shot learning, it is widely recognized that the importance of AI in this domain will keep increasing in the upcoming years. The main areas of AI-driven applications in medicine in the near future are focused on supporting the work of radiologists, surgeons, and even general practitioners. The technological response to those needs is the availability of cluster/cloud/distributed (super)computing, large-scale federated learning infrastructures, digital-twin approaches, and cutting-edge visualization interfaces that highly improve the usability of novel technologies in medicine.
Moreover, as healthcare moves towards more personalized and preemptive models, the demand for dedicated AI frameworks that can process vast amounts of health data is ever-increasing. This minitrack seeks to highlight innovative approaches to building scalable, efficient, and secure AI infrastructures in healthcare settings. We encourage submissions from interdisciplinary teams that address the unique challenges at the intersection of AI and medicine, such as data privacy and security, model interpretability, and integrationing AI tools into clinical workflows. Additionally, we are interested in studies that assess the impact of AI technologies on patient outcomes, healthcare efficiency, and the accessibility of medical services and devices.
Hence, submissions may cover a wide range of topics including, but not limited to:
- Architectures and frameworks for deep learning in healthcare
- Research infrastructures and advanced systems for bio-data management and analysis
- Clinical decision support systems powered by AI algorithms
- Real-time data analysis for operating rooms and medical devices
- Ethical considerations and societal impacts of AI in medicine
- Data privacy and security challenges in medical AI applications
- Robot-guided surgery, visually-guided surgeon support systems
- Innovative case studies and applications of AI in medical research and patient care
- Generative AI in the context of medical data (especially imaging data)
- Integration of AI technologies into healthcare IT systems
- Evaluations of AI tools in clinical settings and their impact on healthcare delivery
- Agents and agent foundation models in medical applications
- Few-shot learning for imaging data (also for not medical data)
- Quantum computing applications in medicine
- Explainable AI for medical imaging
- Digital twins and digital transformation in medicine.
Our minitrack aims to bring together researchers, clinicians, and technologists to share their latest findings, methodologies, and insights on the role of AI in reshaping the medical landscapes of today and tomorrow.