Workshop on Generative AI for Synthetic Medical Data
ACCV 2024, Dec 8-9, Hanoi, Vietnam
Organised by: Insight SFI Research Centre for Data Analytics, University of Galway, Ireland
Workshop Abtract
Interest in integrating machine learning (ML) models into the healthcare domain has grown rapidly in recent years. Researchers have been designing clinical applications, particularly for medical image interpretation and analysis using Deep Neural Networks (DNNs) and have reported significantly improved accuracies with improved diagnosis speed. However, despite these promising results, many clinicians are still reluctant to fully adopt ML-based diagnostic systems and perform interventions or provide/personalize the treatment based on the computer-aided diagnostic (CAD) system’s recommendation. One major hurdle in the adaptation of these models in clinical settings is the limited availability of clinical data, including medical images (such as computer tomography angiography), electronic health records (radiology finding reports), laboratory test records (blood test results in tabular form), and patient demography (medical and family history of diseases in textual format) for training and testing generalizability of the developed ML models. Other contributing factors such as data privacy concerns, the time and resource-intensive manual annotation, the scarcity of disease-annotated data, and the variations introduced by different imaging modalities obtained from the same manufacturer’s scanners or variations in the same image modalities from different scanner manufacturers, further complicate the adoption of ML system in a clinical setting. A single-trained model cannot adapt to all these variations and other factors. Furthermore, different hospitals use templates and wording for textual reports, and record systems output tabular data in differing formats.
Researchers have proposed various solutions to try to overcome these challenges. For example, researchers have been using data augmentation techniques to overcome the limited availability of medical image datasets. While these techniques increase the training data for an ML algorithm, they often generate highly correlated images and potentially lead to a non-generalizable trained model. Image resizing is performed to transform the input image so that it can match the image size required by the trained model. This resizing affects (shrinks or enlarges) the anatomy of the region of interest which creates problems of accurate training, diagnosis, and interventions for specific diseases by clinicians. Generative models have been proposed as a solution to overcome data augmentation and data privacy issues. These generative models help in data anonymization, however, most of the studies only generate medical images and do not also consider the generation of corresponding masks or ground truth, which are essential prerequisites for model training. Moreover, efficient training of generative models (e.g. Generative Adversarial Networks or diffusion models) and generation of synthetic medical data through these models is also complex and time-consuming.
These multifaceted natured challenges emphasize on the need for collaborative efforts across disciplines, to refine existing solutions and develop novel approaches that can effectively mitigate the challenges incurred during the analysis of medical images.
Objectives
The main objective of this workshop is to explore and advance ML techniques for medical data synthesis and evaluation, focusing specifically on generative models. The workshop aims to deepen our knowledge of:
(1) generative network implementations for synthetic data generation along with corresponding annotations; and
(2) customizing generative architectures to make them adaptable to diverse modalities (multimodal models).
Thus, we aim to bring experts, researchers, and clinicians to discuss and address the critical issues around the adoption of generative models in healthcare for medical image analysis and CAD as well as discuss the knowledge discovery aspect to reduce the time complexities of the model. We invite submissions of original research articles, case studies and innovative solutions to overcome the above-mentioned challenges and advance our knowledge in the field.
Scope and Topics
The relevant topics to this include but are not limited to:
Implementation of generative models for medical data synthesis.
Customization of generative architectures for adaptive image synthesis.
Applications of synthetic data generation in medical/clinical data analytics.
Generation of synthetic medical data using 3D models.
Challenges and future directions of generative models in medical domain.
Foundational Models for generating high-quality synthetic data in medical domains with a focus on different modalities (images, tabular and time series datasets).
Challenges and limitations of synthetic data in terms of privacy risks, quality assessment, and generalization to diverse datasets.
Applications of synthetic data in training machine learning models, reducing bias, enhancing privacy, and improving data diversity.
Chairpersons
Dr Talha Iqbal
Dr Talha Iqbal received his Ph.D. degree from the University of Galway, Galway, Ireland, in 2023. He is currently employed as a postdoctoral researcher in the Insight SFI Research Center for Data Analytics, University of Ireland, Galway. His research spans the disciplines of engineering and medicine, with a focus on AI/machine learning, data science, biosensors, wearable devices, signal processing and healthcare. He has actively published original articles and a book chapter on the topic of use of generative (machine learning) models in healthcare domain.
Prof. Michael G Madden
Professor Michael Madden is the Established Professor of Computer Science in the University of Galway. He leads the Machine Learning Research Group that he set up in 2001 in Galway. His research focuses on new theoretical advances in machine learning, motivated by addressing important data-driven applications in medicine, engineering, and the physical sciences. He has organized and chaired several national as well as international conferences sessions, including organising the 1st and 2nd International Workshop on AI in Security at IJCAI 2017 and EMCL 2018.
Dr Ihsan Ullah
Dr Ihsan Ullah is an Assistant Professor with the School of Computer Science, University of Galway, Ireland. His current research interests include designing lightweight neural networks, federated learning, image/video processing, medical image analysis, signal processing, and explainable AI. He has organized and chaired Special Session on Federated Learning for Industry 4.0 and Smart Manufacturing in International Conference on Industry 4.0 and Smart Manufacturing in 2022, 2023, and 2024, A Human-Centric Perspective of Explainability, Interpretability and Resilience in Computer Vision in IJCNN 2024.
Questions?
Contact [talha.iqbal; michael.madden; ihsan.ullah] @universityofgalway.ie or @insight-centre.org to get more information about the workshop