mlsanityData to 7 Oct 2026

Improved α-GAN architecture for generating 3D connected volumes with an application to radiosurgery treatment planning

arXiv 2207.11223 ↗First posted 13 Jul 2022eess.IV cs.CV cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Generative Adversarial Networks (GANs) have gained significant attention in several computer vision tasks for generating high-quality synthetic data. Various medical applications including diagnostic imaging and radiation therapy can benefit greatly from synthetic data generation due to data scarcity in the domain. However, medical image data is typically kept in 3D space, and generative models suffer from the curse of dimensionality issues in generating such synthetic data. In this paper, we investigate the potential of GANs for generating connected 3D volumes. We propose an improved version of 3D α-GAN by incorporating various architectural enhancements. On a synthetic dataset of connected 3D spheres and ellipsoids, our model can generate fully connected 3D shapes with similar geometrical characteristics to that of training data. We also show that our 3D GAN model can successfully generate high-quality 3D tumor volumes and associated treatment specifications (e.g., isocenter locations). Similar moment invariants to the training data as well as fully connected 3D shapes confirm that improved 3D α-GAN implicitly learns the training data distribution, and generates realistic-looking samples. The capability of improved 3D α-GAN makes it a valuable source for generating synthetic medical image data that can help future research in this domain.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 26 of its 51 references that are in the map. First posted on arXiv 13 Jul 2022.

Builds on

26 of 51 references.

References · 26

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  3. 2014Going Deeper with Convolutionscited by 4,231
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  6. 2017Improved Training of Wasserstein GANscited by 2,223
  7. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  8. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  9. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  10. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  11. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  12. 2018Diverse Image-to-Image Translation via Disentangled Representationscited by 296
14 more
  1. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  2. 2020A U-Net Based Discriminator for Generative Adversarial Networkscited by 128
  3. 2017MarrNet: 3D Shape Reconstruction via 2.5D Sketchescited by 108
  4. 2017PacGAN: The power of two samples in generative adversarial networkscited by 104
  5. 2016Unsupervised Learning of 3D Structure from Imagescited by 67
  6. 2019Generation of 3D Brain MRI Using Auto-Encoding Generative Adversarial Networkscited by 65
  7. 2018Learning to Reconstruct Shapes from Unseen Classescited by 60
  8. 2017Variational Approaches for Auto-Encoding Generative Adversarial Networkscited by 52
  9. 2016VConv-DAE: Deep Volumetric Shape Learning Without Object Labelscited by 50
  10. 20213D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Imagescited by 32
  11. 2019Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-based CT Image Augmentation for Object Detectioncited by 29
  12. 2020Modelling the Distribution of 3D Brain MRI using a 2D Slice VAEcited by 20
  13. 2018Automated Treatment Planning in Radiation Therapy using Generative Adversarial Networkscited by 11
  14. 2018Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representationcited by 7

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 1.

2 papers.

  1. 2023A Bayesian Non-parametric Approach to Generative Models: Integrating Variational Autoencoder and Generative Adversarial Networks using Wasserstein and Maximum Mean Discrepancycited by 1
  2. 2025A Deep Bayesian Nonparametric Framework for Robust Mutual Information Estimationcited by 0