Digital Twin for Healthcare
© International Workshop on Digital Twin for Healthcare (DT4H) in MICCAI 2025 (Daejeon, Republic of Korea)

Overview

Digital twin (DT) is an emerging frontier in healthcare, offering dynamic, patient-specific virtual models that combine medical imaging, physiological data, and computational simulations to replicate and predict real-world health outcomes. While DT technology is still nascent in the MICCAI community, its potential to transform personalized medicine, surgical planning, and clinical decision-making is immense. This workshop seeks to establish DTs as a vibrant new topic within the MICCAI community, bridging interdisciplinary domains like medical imaging, computational modeling in medicine, biomechanics, and trustworthy AI.

By introducing this workshop, we aim to catalyze discussions on integrating DT models with more conventional medical imaging and computational tools, providing a forum to explore innovations and build a new MICCAI sub-community dedicated to digital twins in healthcare. This workshop is strategically positioned to expand MICCAI’s scope by attracting researchers from fields such as computational modeling, electrophysiology, hemodynamic, biomechanical modeling, and sensor data analysis. DTs not only align with MICCAI topics like image-guided surgery, personalized medicine, and trustworthy AI, but also open doors to underexplored applications, including real-time patient monitoring and population imaging informatics. The workshop also emphasizes inclusivity by addressing affordable and accessible imaging solutions for DTs, especially in under-represented populations.

Topic

  • Digital twin modeling for organs, tissues, and diseases
  • Multi-modal data integration (imaging, signals, genomics, biosensors)
  • AI-driven simulation and predictive modeling for digital twins
  • Digital twin-guided diagnosis, treatment, and intervention planning
  • Verification, Validation, and uncertainty quantification in digital twins
  • Trustworthy AI, fairness, and explainability in digital twin applications
  • Cloud-based and federated learning approaches for scalable digital twins
  • Ethical, regulatory, and clinical translation challenges of digital twins
  • Digital twins for drug development and in silico clinical trials
  • Simulation and visualization techniques for clinical environments

Timeline

May
Paper Abstract Submission. 20 May 2025
June
Paper Submission Deadline. 15 June 30 June 2025
July
Reviews Due. 15 July 2025
Notification of Acceptance. 20 July 2025
Aug
Camera Ready Submission. 1 August 2025
Sep
DT4H workshop (Daejeon, Republic of Korea). 23 September 2025

Call for Paper

We invite original research contributions on digital twins for healthcare. Papers should be a maximum of 8 pages (including text, figures, and tables) with up to 2 additional pages for references. Submissions must follow the Springer LNCS format (Latex or MS Word templates) and undergo double-blind peer review. The workshop will be held in person only, and authors of accepted papers are required to present their work in person.

All submissions will be reviewed by external experts and the organizing committee for oral or poster presentation. Accepted papers will be published with Springer LNCS, and the best papers will be recognized with industry-sponsored awards. We encourage both theoretical and applied research, including proof-of-concept studies that explore novel directions in digital twins. As MICCAI expands its global reach, we especially welcome submissions that address challenges in digital twins for low- and middle-income countries. This workshop will also feature live demonstrations, allowing authors to showcase their digital twin applications in AI-driven modeling, real-time simulations, and clinical decision support.

Submissions should be made via CMT system, with email registration required before submission. If you experience any issues, please contact the Program Chairs via the submission platform or email. We invite contributions on topics such as:

  • Development of digital twins using medical imaging data.
  • Integrating imaging and non-imaging data for dynamic digital twins.
  • Computational modeling of specific diseases (e.g., cardiovascular, neurology, oncology, pulmonology oncology, etc).
  • AI techniques for digital twin efficiency and accuracy.
  • Validation and deployment challenges for digital twins in clinical practice.

Program

Agenda

📅 23 Sep 2025 📍 Daejeon, South Korea (DCC1-2F-205)

13:30
40
Opening Remarks
50
Opening Remarks
14:00
10
20
Keynote 1: Prof. Linwei Wang
30
40
50
15:00
Oral Session 1: Session Chair: Xiaoyue Liu
10
20
30
40
Keynote 2: Prof. Mathias Unberath
50
16:00
10
Poster Session/Break
20
Sponsor Session AWS - Product Introduction
30
40
50
17:00
Oral Session 2: Session Chair: Yilin Lyu
10
20
30
40
Keynote 3: Prof. Henggui Zhang
50
Discussion/Awards
18:00
Closing

Keynote Speakers

Mathias Unberath
Linwei Wang
Professor, Rochester Institute of Technology
Predictive Hybrid Digital Twins: Theory, Methods, and Applications
Advances in digital-twin technology within the healthcare sector are confronted with a long-standing challenge: instead of a one-time static construction that fits observed data, a digital twin needs to rapidly adapt to live data and to provide predictive decision support beyond what has been observed. Attaining these breakthroughs face two fundamental hurdles. First, current mechanistic models struggle with rapid adaptation and imperfect knowledge, while data-driven models are limited in interpretability and generalizability. Second, the prevalent twinning strategies based on data-fitting, previously largely tailored for mechanistic models, become the root cause of an un-identifiable data-driven model with limited predictive capabilities. In this talk, we discuss our recent efforts in addressing these challenges towards the ultimate goal of predictive twinning: a what-how & when meta-learning framework for learning to rapidly and continually personalize a latent forecasting function, endowed with strong predictive ability owing to its theoretical identifiability, and hybrid neural-mechanistic modeling that combines the generalizable and interpretable mechanistic know-how with flexible data-driven learning to resolve the residual between general knowledge and individuals’ data. We will extend these discussions to applications in learning personalized digital twins of the heart.
BIOGRAPHY
Dr. Linwei Wang is a Professor of Computing and Information Sciences at the Rochester Institute of Technology (RIT) in Rochester, NY, where she serves as the Director of the Personalized Healthcare Technology (PHT180) Research Center that consists of over 120 faculty affiliates across nine colleges at RIT. Prior to that, Dr. Wang obtained her BS degree in Optic-Electrical Engineering from Zhejiang University (China) in 2005, her M.Phil degree in Electronic and Computer Engineering from Hong Kong University of Science and Technology in 2007, and her PhD in Computing and Information Sciences from RIT prior to joining the faculty of RIT in 2009. Dr. Wang also directs the Computational Biomedical Lab at RIT, with core research interests centered around statistical inference, Bayesian deep learning, and inverse problems with applications to signal and image analysis in a variety of domains including healthcare, astrophysics, and material design. Dr. Wang is a recipient of the NSF CAREER Award in 2014 and the United States Presidential Early Career Award for Scientists and Engineers (PECASE) in 2019. Dr. Wang currently serves as the Executive Secretary on the Board of the Medical Image Computing and Computer-Assisted Intervention (MICCAI) Society.
Mathias Unberath
Mathias Unberath
Associate Professor, Johns Hopkins University
Digital Twins for Surgical Data Science
Digital twins are virtual representations of real-world environments and processes. By virtue of being computational, digital twins offer abundant possibilities for optimizing and supporting real-world processes through algorithmic analysis and feedback. In this context, digital twins play a critical role in advancing surgical data science, an emerging research thrust striving to improve the quality of interventional healthcare. In this talk, I will first provide a contextual framework in support of digital twins as a useful representation for scene analysis and then showcase some exciting research outcomes and opportunities that demonstrate the potential for digital twins in surgical data science and beyond.
BIOGRAPHY
Dr. Mathias Unberath is the John C. Malone Associate Professor of Computer Science at Johns Hopkins University. He’s the Research Director for Embodied AI in the Data Science and AI Institute, core member of the Malone Center for Engineering in Healthcare and the Laboratory for Computational Sensing and Robotics, and a member of the Institute for Assured Autonomy. He holds secondary appointments in the School of Medicine. With his team, the ARCADE research group on Advanced Robotics and Computationally AugmenteD Environments, he builds the future of AI-assisted medicine. Through synergistic research on imaging, computer vision, machine learning, and interaction design, he creates human-centered solutions that are embodied in emerging technology such as mixed reality and robotics. Mathias has published more than 190 journal and conference articles, and has received numerous awards, grants, and fellowships, including the NSF Career, NIH NIBIB R21 Trailblazer and Google Research Scholar Award, and more than 20 international paper awards.
Henggui Zhang
Henggui Zhang
Chief Scientist, Beijing Academy of Artificial Intelligence. Chair Professor, University of Manchester
Development of the virtual heart for the study of cardiac arrhythmias
Cardiac arrhthmias are the most common cardiac diseases causing morbidity and mortality. Understanding and treating cardiac arrhythmias remains a significant challenge in cardiovascular practices. While experimental techniques provide valuable insights, they are often limited in resolution, scalability, and personalisation. In this talk, I will present the development and application of a multi-scale, multi-physics virtual heart platform - an integrative computational framework that simulates cardiac electrophysiology from ion channels to the whole heart. Built upon biophysically detailed cellular models, tissue-level conduction networks, and anatomically accurate geometries, the virtual heart enables mechanistic exploration of arrhythmia initiation, maintenance, and termination in normal and abnormal physiological/pathological conditions.
BIOGRAPHY
Dr. Henggui Zhang is Chief Scientist at the Beijing Academy of Artificial Intelligence, where he leads the Centre for Life Simulation and Modelling, and Chair Professor of Biological Physics at the University of Manchester.   Dr. Zhang received a BSc in Physics (1985), an MSc in Laser Physics and Computer Science (1988), and a PhD in Nonlinear Science focusing on Mathematical Cardiology (1990) from the University of Leeds. He subsequently held postdoctoral fellowships at both Johns Hopkins University and the University of Leeds. In 2001, he joined UMIST (now part of the University of Manchester), where he progressed from Lecturer to Reader and ultimately the Chair of Biological Physics. He was elected as a Fellow of the Royal Society of Biology (FRSB) and Fellow of the Royal Society of Arts (FRSA) in 2019.   Dr. Zhang’s research spans multi-scale modeling of cardiac cells, tissues, and organs; spatiotemporal complexity; and nonlinear and chaotic time-series dynamics. He has published over 500 scientific works, including more than 280 peer-reviewed articles in computational cardiology, electrophysiology, and systems biology. His Google Scholar profile reports an h-index of 60 with over 14,000 citations, reflecting his significant contributions to atrial fibrillation research, sinoatrial node modeling, digital twin heart simulations, AI-driven arrhythmia detection, and drug safety evaluation through in-silico pharmacological modeling. As a pioneer in computational cardiology and digital physiological modeling, Dr. Zhang continues to shape the field through innovations that bridge foundational science and real-world clinical applications.

Oral Presentations

Oral Session 1
  1. Trung-Dung Hoang (UniBE, Switzerland)
    Real-Time Digital Twin for Type 1 Diabetes using Simulation-Based inference
  2. Minjee Seo (Yonsei University, South Korea)
    Acoustic Simulation with Deep Learning for Low-intensityTranscranial Focused Ultrasound Digital Twins
  3. Yilin Lyu (NUS, Singapore)
    Personalized 3D Ml Geometry Reconstruction from Cine MRl with Explicit Cardiac Motion Modeling
  4. Seonaeng Cho (Yonsei University, South Korea)
    Towards Digital Twin of RF Ablation: Real-Time Prediction of Time-Dependent Thermal Effects Using Transformer
Oral Session 2
  1. Xiaoyue Liu (NUS, Singapore)
    Personalized 4D Whole Heart Geometry Reconstruction from Cine MRl for Cardiac Digital Twins
  2. Robert Graf (TUM, Germany)
    Rules based Key-Point Extraction for MR-Guided Biomechanical Digital Twins of the Spine
  3. Mathias Unberath (JHU, USA)
    Towards Robust Algorithms for Surgical Phase Recognition via Digital Twin Representation
  4. Oliver Frings (Siemens Healthineers, Germany)
    Retrospective Evaluation of a Patient-Specific Liver Digital Twin to Predict Thermal Ablation Outcomes in HCC

Accepted Papers

Personalized 3D Myocardial Infarct Geometry Reconstruction from Cine MRI with Explicit Cardiac Motion Modeling
Authors: Yilin Lyu, Fan Yang, Xiaoyue Liu, Zichen Jiang, Joshua R. Dillon, Debbie Zhao, Martyn P. Nash, Charlene Mauger, Alistair Young, Ching-Hui Sia, Mark YY Chan, Lei Li*
Microvascular Retinal Digital Twins from Non-Invasive Clinical Images
Authors: Remi Hernandez*, Wahbi El-Bouri
Validating Digital Twins with Tactile-Visual Liver Phantoms for Robot-Assisted Surgical Workflows
Authors: Chengzheng Mao*, Ying Zhen Tan, Yujia Gao
A Real-Time Digital Twin for Type 1 Diabetes using Simulation-Based Inference
Authors: Trung-Dung Hoang*, Alceu Emanuel Bissoto, Vihangkumar Naik, Tim Fluehmann, Artemii Shlychkov, José Fernando Garcia Tirado, Lisa Margret Koch
Retrospective Evaluation of a Patient-Specific Liver Digital Twin to Predict Thermal Ablation Outcomes in HCC
Authors: Chloé Audigier*, Felix Meister, Fouad Georges Akkari, Andrea Tonglet, Oliver Frings, Rafael Duran
Acoustic Simulation with Deep Learning for Low-intensity Transcranial Focused Ultrasound Digital Twins
Authors: Minjee Seo*, Minwoo Shin, Gunwoo Noh, Seung-Schik Yoo, Kyungho Yoon
Towards Digital Twin of RF Ablation: Real-Time Prediction of Time-Dependent Thermal Effects Using Transformer
Authors: Seonaeng Cho*, Minjee Seo, Minwoo Shin, Kyungho Yoon
Finite-Element Electrophysiological Modeling of Human Uterine Smooth Muscle Using a Reduced Tong Model
Authors: Zhen Li*, Alberto Corrias
TF-TransUNet1D: Time-Frequency Guided Transformer U-Net for Robust ECG Denoising in Digital Twin
Authors: Shijie Wang*, Lei Li
DeformMLP: Effective Deformation Prediction for Breast Cancer Using Graph Topology-Assisted MLPs
Authors: Yong-Min Shin, Kyunghyun Lee, Sunghwan Lim, Kyungho Yoon, Won-Yong Shin*
Rule-based Key-Point Extraction for MR-Guided Biomechanical Digital Twins of the Spine
Authors: Robert Graf*, Tanja Lerchl, Kati Nispel, Hendrik Möller, Matan Atad, Julian Mc Ginnis, Julius Maria Watrinet, Johannes Paetzold, Daniel Rueckert, Jan S. Kirschke
Towards Robust Algorithms for Surgical Phase Recognition via Digital Twin Representation
Authors: Hao Ding*, Yuqian Zhang, Wenzheng Cheng, Xinyu Wang, Xu Lian, Chenhao Yu, Hongchao Shu, Ji Woong Kim, Axel Krieger, Mathias Unberath
Personalized 4D Whole Heart Geometry Reconstruction from Cine MRI for Cardiac Digital Twins
Authors: Xiaoyue Liu*, Xicheng Sheng, Xiahai Zhuang, Vicente Grau, Mark Y Chan, Ching-Hui Sia, Lei Li
Secure Medical Digital Twins: A Use-Case Driven Approach
Authors: Salmah Ahmad*, Stefan Wesarg
Explainable Prediction of Recurrence After Prostate Cancer Radiotherapy Using In Silico Digital Twin Model and Machine Learning
Authors: Valentin Septiers*, Carlos Sosa-Marrero, Eleonora Poeta, Hilda Chourak, Aurélien Briens, Renaud De Crevoisier, Maria Zuluaga, Oscar Acosta

Organization

Organizers

Lei Li
Assistant Professor
National of University Singapore, Singapore
Viktor Jirsa
Professor
Institut de Neurosciences des Systèmes, France
Jianfeng Feng
Professor
Fudan University, Shanghai, China
Jun Deng
Professor
Yale University, New Haven, USA
Luca Dede’
Associate Professor
Politecnico di Milano, Milano, Italy
Sora An
Research Professor
Ewha Womans University, Republic of Korea

Delivery

Yilin Lyu, National University of Singapore, Singapore

Xiaoyue Liu, National University of Singapore, Singapore

Copyright © 2025 Digital Twin for Healthcare. All rights reserved.