Longitudinal Disease Tracking and Modelling with Medical Images and Data

October 10, 2024

Submission deadline EXTENDED to 28 June 2024

Aims and Scope

Clinical workflows are increasing data-driven. Medical data, including imaging, is routinely employed to track the progression of disease or to assess response to treatment. For example, patients with cancer are often followed up longitudinally using radiological imaging (e.g., CT/MR/PET) to identify and track lesions, and assess treatment response. Recent developments in AI and machine learning have shown promise in automating or improving parts of the clinical workflow, from being able to find lesions in various organs, to classification and diagnosis of diseases. Unfortunately, despite the key role of serial imaging in the clinical workflow, developing AI systems that can track or model disease progression by learning from and exploiting longitudinal imaging has not received much attention until recently. Besides their role in the everyday clinical workflow, such models can enhance biological understanding of diseases to shape prevention and intervention strategies, inform clinical trial design, and support clinical decision making, such as patient diagnosis and prognosis.Therefore, in this workshop, we solicit submissions which adhere to the general theme of tracking and modeling disease progression with imaging and/or multimodal data.

Two areas are of particular interest:

The workshop is not limited to the above disease areas and we welcome submissions related to other diseases or applications as well. While the focus is on longitudinal data, we also welcome submissions which perform DPM with cross-sectional data. Finally, we also welcome and encourage submissions related to new datasets that can enable the research of tomorrow.

The scope of the conference includes, but is not limited to:

Call for Papers

CMT submission website

We solicit submissions consistent with the aims and scope of the workshop. The following types of submissions will be accepted:

All papers must adhere to the formatting and style used by the MICCAI main conference -- they should be anonymized and use the manuscript templates available at Lecture Notes in Computer Science. Accepted papers will be published as part of a Springer Lecture Notes in Computer Science volume.

Important Dates

All deadlines are 23:59 UTC-12/Anywhere on Earth (AoE)

Keynote Speakers

Dr. Jacob Vogel

Dr. Jacob Vogel

DDLS Fellow, Lund University

Website

Leveraging disease progression models toward biological insights and clinical practice in neurodegenerative disease

Neurodegenerative diseases are characterized by accumulation of pathological proteins leading to progressive damage to select neuronal populations and concomitant clinical decline. Models have emerged that build around biological properties of these diseases in order to model their progression. Many of these “disease progression models” were initially employed to provide holistic descriptions of the disease process, or to test specific hypotheses. However, insofar as disease progression models act as multifaceted simulations of a disease, they have great potential to be extended to provide novel biological insights and even clinically useful information. In this talk, I will discuss work using two different types of disease progression models. I will first discuss connectome-based models — which operate under the assumption that disease pathology travels through the brain’s intrinsic axonal architecture — in the context of accumulation of the tau protein in Alzheimer’s disease. Second, I will discuss applications of the Subtype and Stage Inference disease subtyping algorithm across a different neurodegenerative diseases, including Alzheimer’s disease, Lewy body disease and TDP-43 proteinopathy. Throughout the talk, there will be a specific focus on how we and others have employed these models to formulate new hypotheses about disease biology, as well as preliminary work toward building disease progression models into clinically useful tools.

Dr. Farouk Dako, MD MPH

Dr. Farouk Dako

Assistant Professor of Radiology, University of Pennsylvania

Website

Talk title: TBD

TBD

Agenda

Time Session
1:30 PM - 1:35 PM Welcome and introduction
1:35 AM - 2:20 PM Keynote 1
Dr. Jacob Vogel
2:20 PM - 2:31 PM DP-MoSt for detecting sub-trajectories in the natural history of pathologies
Alessandro Viani
2:31 PM - 2:42 PM Back to the Future: Challenges of Sparse and Irregular Medical Image Time Series
Nico A Disch
2:42 PM - 2:53 PM Probabilistic Temporal Prediction of Continuous Disease Trajectories and Treatment Effects Using Neural SDEs
Joshua D Durso-Finley
2:53 PM - 3:04 PM Enhancing Spatiotemporal Disease Progression Models via Latent Diffusion and Prior Knowledge
Lemuel Puglisi
3:04 PM - 3:15 PM Individualized multi-horizon MRI trajectory prediction for Alzheimer's Disease
Rosemary Y He
3:15 PM - 3:30 PM Towards Longitudinal Characterization of Multiple Sclerosis Atrophy Employing SynthSeg Framework and Normative Modeling
Pedro Macias Gordaliza
3:30 PM - 4:00 PM Coffee Break
4:00 PM - 4:45 PM Keynote 2
Dr. Farouk Dako
4:45 PM - 4:50 PM Automated Segmentation and Registration of Fundus Autofluorescence Imaging facilitates better monitoring of Geographic Atrophy Growth
Yoga Advaith Veturi
4:50 PM - 5:01 PM SegHeD: Segmentation of Heterogeneous Data for Multiple Sclerosis Lesions with Anatomical Constraints
Berke D Basaran
5:01 PM - 5:12 PM Longitudinal Segmentation of MS Lesions via Temporal Difference Weighting
Maximilian R Rokuss
5:12 PM - 5:23 PM Registration of Longitudinal Liver Examinations for Tumor Progress Assessment
Walid Yassine
5:23 PM - 5:34 PM Tracking lesion evolution using a Boundary Enhanced Approach for MS change segmentation (BEAMS)
Prateek Mathur
5:34 PM - 5:45 PM A Radiological-based Coordinate System for the Human Body: A Proof-of-Concept
Stefano Trebeschi
5:45 PM - 5:56 PM Vestibular schwannoma growth prediction from longitudinal MRI by time conditioned neural fields
Yunjie Chen
5:56 PM - 6:00 PM Closing remarks and adjournment

Organizers

Alessa Hering
Alessa Hering
Radboudumc, Nijmegen, The Netherlands
and Fraunhofer MEVIS, Germany
Alexandra Young
Alexandra Young
Centre for Medical Image Computing,
University College London, London, UK
Anna Schroder
Anna Schroder
Centre for Medical Image Computing,
University College London, London, UK
Bruno Jedynak
Bruno Jedynak
Department of Mathematics and Statistics,
Portland State University, Portland, USA
Isaac Llorente-Saguer
Isaac Llorente-Saguer
Centre for Medical Image Computing,
University College London, London, UK
Jacob Vogel
Jacob Vogel
Clinical Memory Research Unite,
Lund University, Lund, Sweden
Neil Oxtoby
Neil Oxtoby
Centre for Medical Image Computing,
University College London, London, UK
Peter Wijeratne
Peter Wijeratne
Department of Informatics,
University of Sussex, Brighton, UK
Pritam Mukherjee
Pritam Mukherjee
National Institutes of Health,
Clinical Center, Bethesda, USA
Sara Garbarino
Sara Garbarino
Life Science Computational Laboratory,
IRCCS Ospedale Policlinico San Martino, Genoa, Italy
Sven Kuckertz
Sven Kuckertz
Fraunhofer MEVIS,
Lübeck, Germany,
Tejas Mathai
Tejas Mathai
National Institutes of Health,
Clinical Center, Bethesda, USA
Tiantian He
Tiantian He
Centre for Medical Image Computing,
University College London, London, UK