DGM4MICCAI

Deep Generative Models workshop @ MICCAI 2024

Overview

Deep generative models such as Generative Adversarial Network (GAN) and Variational Auto-Encoder (VAE) are currently receiving widespread attention from not only the computer vision and machine learning communities, but also in the MIC and CAI community. These models combine the advanced deep neural networks with classical density estimation (either explicit or implicit) for achieving state-of-the-art results. DGM4MICCAI workshop at MICCAI 2024 will be all about Deep Generative Models in Medical Image Computing and Computer Assisted Interventions.

The decisions are out: We have 51.2% acceptance rate. Congratulations to the authors of all accepted papers.

The workshop will take place in the Palmeraie meeting room in Conference Center.

Submission Details

We seek contributions that include, but are not limited to:

  • Novel architectures, loss functions, and theoretical developments for:
    • GANs and Adversarial Learning
    • Variational Auto-Encoder
    • Disentanglement
    • Flow
    • Autoregressive models
  • Stable Diffusion Models
  • Causal generative models
  • Multi-Modality and Cross-Modality linking
  • Novel metrics and uncertainty estimates for performance assessment and interpretability of generative models
  • Generative models under limited, sparse and noisy image inputs
  • Supervised and Unsupervised Domain Adaptation, Transfer Learning and Multi-Task Learning
  • Segmentation, Detection, Synthesis, Reconstruction, Denoising, Supersampling, Registration
  • Image-to-Image translation for Synthetic Training Data Generation or Augmented Reality
  • Neural Rendering
  • Diffusion Models, Normalizing Flow Models, Invertible Networks

We particularly welcome papers driven by the theme "MIC meets CAI". Interesting novel applications of deep generative models in MIC and CAI beyond these topics are also welcome.

Workshop proceedings are published as part of Springer Nature's Lecture Notes in Computer Science (LNCS) series. Manuscripts will be reviewed in double-blinded peer-review. Please prepare your workshop papers according to the MICCAI submission guidelines (LNCS template, 8 pages maximum).
Supplementary material: PDF documents or mp4 videos, 10 MB maximum file size.

Timeline

Event Date
Paper Submission Deadline 24. June 2024
Review Release 15. July 2024
Final Decision 15. July 2024
Camera ready papers due 24. July 2024
DGM4MICCAI Workshop 10. October 2024

Program

DGM4MICCAI workshop will be a half-day event (Room: Palmeraie), following the agenda below:
Start End Topic
8:00 AM 8:15 AM Opening
8:15 AM 10:00 AM Long Oral
10:00 AM 10:30 AM Coffee Break
10:30 AM 11:15 AM Keynote
11:15 AM 12:20 PM Short Oral
12:20 PM 12:30 PM Closing

Please note that times might be subject to change, so keep an eye on the schedule or follow us on Twitter to be up-to-date.

Keynote Speaker

Jelmer Wolterink

Assistant Professor, University of Twente

Netherlands

Neural fields for deep generative modeling in medical imaging

Neural fields, also referred to as implicit neural representations, provide an efficient way to model complex continuous functions on low-dimensional domains. They have seen wide applications in medical imaging, including novel view synthesis (NeRFs), registration, reconstruction, and segmentation. More recently, neural fields have emerged as a powerful tool for data representation in generative modeling. In my talk, I will present some of our latest work on image and shape synthesis, demonstrating how neural fields can be seamlessly integrated with popular generative models such as GANs and diffusion models.

Oral Sessions

Long Oral

Paper IDTitle
2DeReStainer: H&E to IHC Pathological Image Translation via Decoupled Staining Channels
3WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesis
6SynthBrainGrow: Synthetic Diffusion Brain Aging for Longitudinal MRI Data Generation in Young People
10Energy-Based Prior Latent Space Diffusion model for Reconstruction of Lumbar Vertebrae from Thick Slice MRI
11Interactive Generation of Laparoscopic Videos with Diffusion Models
17Anatomically-Guided Inpainting for Local Synthesis of Normal Chest Radiographs
21Five Pitfalls When Assessing Synthetic Medical Images with Reference Metrics
25Enhancing Cross-Modal Medical Image Segmentation through Compositionality
30TiBiX: Leveraging Temporal Information for Bidirectional X-ray and Report Generation
35Unpaired Modality Translation for Pseudo Labeling of Histology Images
42SNAFusion: Distilling 2D axial plane diffusion priors for sparse-view 3D cone-beam CT imaging

Short Oral

Paper IDTitle
7Denoising Diffusion Models for 3D Healthy Brain Tissue Inpainting
8Panoptic Segmentation of Mammograms with Text-To-Image Diffusion Model
13Multi-parametric MRI to FMISO PET synthesis for Hypoxia prediction in brain tumors
18qMRI Diffuser: Quantitative T1 Mapping of the Brain using a Denoising Diffusion Probabilistic Model
19On Differentially Private 3D Medical Image Synthesis with Controllable Latent Diffusion Models
27Augmenting Prostate MRI Dataset with Synthetic Volumetric Images from Zone-conditioned
Diffusion Generative Model
37Segmentation-guided MRI reconstruction for meaningfully diverse reconstructions
38Non-Reference Quality Assessment for Medical Imaging: Application to Synthetic Brain MRIs
41LatentArtiFusion: an Effective and Efficient Histological Artifacts Restoration Framework
43How To Segment in 3D Using 2D Models: Automated 3D Segmentation of Prostate Cancer
Metastatic Lesions on PET Volumes Using Multi-Angle Maximum Intensity Projections and Diffusion Models

Organizing Committee

  • Anirban Mukhopadhyay, TU Darmstadt, Germany
  • Sandy Engelhardt, Heidelberg University, Germany
  • Ilkay Oksuz, Istanbul Technical University, Turkey
  • Dorit Merhof, Universität Regensburg, Germany
  • Yixuan Yuan, City University of Hong Kong, China
Student organizers:
  • Lalith Sharan, University Hospital Heidelberg, Germany
  • Henry Krumb, TU Darmstadt, Germany
  • Amin Ranem, TU Darmstadt, Germany
  • John Kalkhof, TU Darmstadt, Germany
  • Yannik Frisch, TU Darmstadt, Germany
  • Ssharvien Kumar Sivakumar, TU Darmstadt, Germany
  • Caner Özer, Istanbul Technical University, Turkey

Program Chair

  • Camila González, Stanford University, USA
  • Salman Ul Hussain Dar, Heidelberg University Hospital, Germany
  • Reza Azad, RWTH Aachen, Germany
  • Moritz Fuchs, TU Darmstadt, Germany

Program Committee

  • Li Wang, University of Texas at Arlington, USA
  • Tong Zhang , Peng Cheng Laboratory, Shenzhen, China
  • Ping Lu, Oxford University, UK
  • Roxane Licandro, Medical University of Vienna, Austria
  • Veronika Zimmer, TU Muenchen, Germany
  • Dwarikanath Mahapatra, Inception Institute of AI, UAE
  • Michael Sdika, CREATIS Lyon, France
  • Jelmer Wolterink, Univ. of Twente, The Netherlands
  • Subhamoy Mandal, IIT Kharagpur, India
  • Alejandro Granados, King's College London, UK
  • Jinglei Lv, The University of Sydney, Australia
  • Onat Dalmaz, Bilkent University, Turkey
  • Angshuman Paul, IIT Jodhpur, India
  • Magda Paschali, Stanford University, USA

Contact:
anirban.mukhopadhyay[at]gris.informatik.tu-darmstadt.de