Deep Generative Models

1. Front Matter

   Pages i-x

   PDF

2. Methods

   1. Front Matter

      Pages 1-1

      PDF

   2. Flow-Based Visual Quality Enhancer for Super-Resolution Magnetic Resonance Spectroscopic Imaging

      • Siyuan Dong, Gilbert Hangel, Eric Z. Chen, Shanhui Sun, Wolfgang Bogner, Georg Widhalm et al.

      Pages 3-13

   3. Cross Attention Transformers for Multi-modal Unsupervised Whole-Body PET Anomaly Detection

      • Ashay Patel, Petru-Daniel Tudosiu, Walter Hugo Lopez Pinaya, Gary Cook, Vicky Goh, Sebastien Ourselin et al.

      Pages 14-23

   4. Interpreting Latent Spaces of Generative Models for Medical Images Using Unsupervised Methods

      • Julian Schön, Raghavendra Selvan, Jens Petersen

      Pages 24-33

   5. What is Healthy? Generative Counterfactual Diffusion for Lesion Localization

      • Pedro Sanchez, Antanas Kascenas, Xiao Liu, Alison Q. O’Neil, Sotirios A. Tsaftaris

      Pages 34-44

   6. Learning Generative Factors of EEG Data with Variational Auto-Encoders

      • Maksim Zhdanov, Saskia Steinmann, Nico Hoffmann

      Pages 45-54

   7. An Image Feature Mapping Model for Continuous Longitudinal Data Completion and Generation of Synthetic Patient Trajectories

      • Clément Chadebec, Evi M. C. Huijben, Josien P. W. Pluim, Stéphanie Allassonnière, Maureen A. J. M. van Eijnatten

      Pages 55-64

3. Applications

   1. Front Matter

      Pages 65-65

      PDF

   2. Novel View Synthesis for Surgical Recording

      • Mana Masuda, Hideo Saito, Yoshifumi Takatsume, Hiroki Kajita

      Pages 67-76

   3. Anomaly Detection Using Generative Models and Sum-Product Networks in Mammography Scans

      • Marc Dietrichstein, David Major, Martin Trapp, Maria Wimmer, Dimitrios Lenis, Philip Winter et al.

      Pages 77-86

   4. Image Translation Based Nuclei Segmentation for Immunohistochemistry Images

      • Roger Trullo, Quoc-Anh Bui, Qi Tang, Reza Olfati-Saber

      Pages 87-96

   5. 3D (c)GAN for Whole Body MR Synthesis

      • Daniel Mensing, Jochen Hirsch, Markus Wenzel, Matthias Günther

      Pages 97-105

   6. Airway Measurement by Refinement of Synthetic Images Improves Mortality Prediction in Idiopathic Pulmonary Fibrosis

      • Ashkan Pakzad, Mou-Cheng Xu, Wing Keung Cheung, Marie Vermant, Tinne Goos, Laurens J. De Sadeleer et al.

      Pages 106-116

   7. Brain Imaging Generation with Latent Diffusion Models

      • Walter H. L. Pinaya, Petru-Daniel Tudosiu, Jessica Dafflon, Pedro F. Da Costa, Virginia Fernandez, Parashkev Nachev et al.

      Pages 117-126

4. Back Matter

   Pages 127-127

   PDF

This book constitutes the refereed proceedings of the Second MICCAI Workshop on Deep Generative Models, DG4MICCAI 2022, held in conjunction with MICCAI 2022, in September 2022. The workshops took place in Singapore. 

DG4MICCAI 2022 accepted 12 papers from the 15 submissions received. The workshop focusses on recent algorithmic developments, new results, and promising future directions in Deep Generative Models. 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.

• artificial intelligence
• bioinformatics
• color image processing
• color images
• computer vision
• digital image
• image analysis
• image matching
• image processing
• image quality
• image reconstruction
• image segmentation
• imaging systems
• machine learning
• medical images
• pattern recognition
• signal processing

• TU Darmstadt, Darmstadt, Germany

  Anirban Mukhopadhyay

• Istanbul Technical University, Istanbul, Turkey

  Ilkay Oksuz

• University Hospital Heidelberg, Heidelberg, Germany

  Sandy Engelhardt

• The University of Texas at Arlington, Arlington, USA

  Dajiang Zhu

• University of Hong Kong, Hong Kong, Hong Kong

  Yixuan Yuan

Policies and ethics