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

arXiv: https://arxiv.org/abs/2207.11223 · HTML: https://mlsanity.com/paper/2207.11223/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 51 references that are in the map.
- First posted on arXiv 13 Jul 2022.

## Builds on (most cited first, 26 of 26)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2012.00926/) (2020)
- [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1808.00948/) (2018)
- [StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation](https://mlsanity.com/paper/2112.11427/) (2021)
- [A U-Net Based Discriminator for Generative Adversarial Networks](https://mlsanity.com/paper/2002.12655/) (2020)
- [MarrNet: 3D Shape Reconstruction via 2.5D Sketches](https://mlsanity.com/paper/1711.03129/) (2017)
- [PacGAN: The power of two samples in generative adversarial networks](https://mlsanity.com/paper/1712.04086/) (2017)
- [Unsupervised Learning of 3D Structure from Images](https://mlsanity.com/paper/1607.00662/) (2016)
- [Generation of 3D Brain MRI Using Auto-Encoding Generative Adversarial Networks](https://mlsanity.com/paper/1908.02498/) (2019)
- [Learning to Reconstruct Shapes from Unseen Classes](https://mlsanity.com/paper/1812.11166/) (2018)
- [Variational Approaches for Auto-Encoding Generative Adversarial Networks](https://mlsanity.com/paper/1706.04987/) (2017)
- [VConv-DAE: Deep Volumetric Shape Learning Without Object Labels](https://mlsanity.com/paper/1604.03755/) (2016)
- [3D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Images](https://mlsanity.com/paper/2107.09700/) (2021)
- [Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-based CT Image Augmentation for Object Detection](https://mlsanity.com/paper/1906.04962/) (2019)
- [Modelling the Distribution of 3D Brain MRI using a 2D Slice VAE](https://mlsanity.com/paper/2007.04780/) (2020)
- [Automated Treatment Planning in Radiation Therapy using Generative Adversarial Networks](https://mlsanity.com/paper/1807.06489/) (2018)
- [Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation](https://mlsanity.com/paper/1802.09987/) (2018)

## Built on by (most cited first, 2 of 2)

- [A Bayesian Non-parametric Approach to Generative Models: Integrating Variational Autoencoder and Generative Adversarial Networks using Wasserstein and Maximum Mean Discrepancy](https://mlsanity.com/paper/2308.14048/) (2023)
- [A Deep Bayesian Nonparametric Framework for Robust Mutual Information Estimation](https://mlsanity.com/paper/2503.08902/) (2025)

## 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.