Deep Generative Models workshop @ MICCAI 2022


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 2022 will be all about Deep Generative Models in Medical Image Computing and Computer Assisted Interventions.

Associated Challenge: AdaptOR

The workshop will take place in the Virgo2 room.
Previous DGM4MICCAI Workshop Proceedings are available via Springer Link.

Submission Details

The online submission for DGM4MICCAI is open until 25. June 2022, 11:59 PM PST. Contributions must be submitted online through the CMT submission system.

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

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.


Event Date
Paper Submission Deadline 25 June 2022
Review Release 13 July 2022
Final Decision 16 July 2022
Camera ready papers due 27 July 2022
DGM4MICCAI Workshop 22 September 2022


DGM4MICCAI workshop will be a half-day event (Room: Virgo2), following the agenda below:
Start End Topic Session chair
8:00 AM 8:15 AM Opening
8:15 AM 8:50 AM Plenary session 1 (Islem Rekik) Sandy Engelhardt; Ilkay Oksuz
8:50 AM 9:15 AM Oral Method session 1 (Papers 10, 7, 14) + Q&A Sandy Engelhardt; Ilkay Oksuz
9:15 AM 9:40 AM Oral Method session 2 (Papers 1, 3, 15) + Q&A Sandy Engelhardt; Ilkay Oksuz
9:40 AM 10:00 AM Coffee break
10:00 AM 10:35 AM Plenary session 2 (Michal Rosen-Zvi) Sandy Engelhardt; Anirban Mukhopadhyay
10:35 AM 11:00 AM Oral Application session 1 (Papers 13, 5, 12) + Q&A Ilkay Oksuz; Anirban Mukhopadhyay
11:00 AM 11:25 AM Oral Application session 2 (Papers 4, 8, 11) + Q&A Ilkay Oksuz; Anirban Mukhopadhyay
11:25 AM 11:30 PM AdaptOR Challenge and closing remarks

All times are given in SGT time and the workshop will take place in the Virgo2 room. 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 Speakers

Michal Rosen-Zvi

IBM Research


Deep generative models for drug discovery

Islem Rekik

Istanbul Technical University


A roadmap to non-invasive brain mapping and diagnosis with/out data

Oral Sessions

Method Session

Paper IDTitleAuthorsTime Slot
1Flow-based Visual Quality Enhancer for Super-resolution Magnetic Resonance Spectroscopic ImagingSiyuan, Dong; Gilbert, Hangel, Eric, Z. Chen; Shanhui, Sun; Wolfgang, Bogner; Georg, Widhalm; Chenyu, You; John, A. Onofrey; Robin, A. de Graaf; James, S. Duncan9:15 AM - 9:40 AM
3Cross Attention Transformers for Multi-modal Unsupervised Whole-Body PET Anomaly DetectionAshay, Patel; Petru-Daniel, Tudosiu; Walter, Hugo Lopez Pinaya; Gary, Cook; Vicky, Goh; Sebastien, Ourselin; Jorge, Cardoso9:15 AM - 9:40 AM
7Interpreting Latent Spaces of Generative Models for Medical Images using Unsupervised MethodsJulian, Schön; Raghavendra, Selvan; Jens, Petersen8:50 AM - 9:15 AM
10What is Healthy? Generative Counterfactual Diffusion for Lesion LocalizationPedro, Sanchez; Antanas, Kascenas; Xiao, Liu; Alison, Q. O'Neil; Sotirios, Tsaftaris8:50 AM - 9:15 AM
14Learning Generative Factors of EEG Data with Variational auto-encodersMaksim, Zhdanov; Saskia, Steinmann; Nico, Hoffmann8:50 AM - 9:15 AM
15An Image Feature Mapping Model for Continuous Longitudinal Data Completion and Generation of Synthetic Patient TrajectoriesClément, Chadebec; Evi, M.C. Huijben; Josien, P.W. Pluim; Stéphanie, Allassonnière; Maureen, A.J.M van Eijnatten9:15 AM - 9:40 AM

Application Session

Paper IDTitleAuthorsTime Slot
4Novel View Synthesis for Surgical RecordingMana, Masuda; Hideo, Saito; Yoshihumi, Takatsume; Hiroki, Kajita11:00 AM - 11:25 AM
5Anomaly Detection using Generative Models and Sum-Product Networks in Mammography ScansMarc, Dietrichstein; David, Major; Martin, Trapp; Maria, Wimmer; Dimitrios, Lenis; Philip, Winter; Astrid, Berg; Theresa, Neubauer; Katja, Bühler10:35 AM - 11:00 AM
8Image Translation Based Nuclei Segmentation for Immunohistochemistry ImagesRoger, Trullo; Quoc-Anh, BUI; Qi, Tang; Reza, Olfati-Saber11:00 AM - 11:25 AM
113D (c)GAN for whole body MR synthesisDaniel, Mensing; Jochen, Hirsch; Markus, T. Wenzel; Matthias, Guenther11:00 AM - 11:25 AM
12Airway measurement by refinement of synthetic images improves mortality prediction in idiopathic pulmonary fibrosisAshkan, Pakzad; Moucheng, Xu; Wing, Keung Cheung; Marie, Vermant; Tinne, Goos; Laurens, De Sadeleer; Stijn, Verleden; Wim, Wuyts; John, Hurst; Joseph, Jacob10:35 AM - 11:00 AM
13Brain Imaging Generation with Latent Diffusion ModelsWalter, Hugo Lopez Pinaya; Petru-Daniel, Tudosiu; Jessica, Dafflon; Pedro, F. da Costa; Virginia, Fernandez; Parashkev, Nachev; Sebastien, Ourselin; Jorge, Cardoso10:35 AM - 11:00 AM