# A Controlled Benchmark of Quantum-Latent GAN Augmentation for Brain MRI

arXiv: https://arxiv.org/abs/2606.18970 · HTML: https://mlsanity.com/paper/2606.18970/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 17 Jun 2026.

## Builds on (most cited first, 8 of 8)

- [Barren Plateaus in Variational Quantum Computing](https://mlsanity.com/paper/2405.00781/) (2024)
- [Diffusion Probabilistic Models beat GANs on Medical Images](https://mlsanity.com/paper/2212.07501/) (2022)
- [Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN](https://mlsanity.com/paper/2008.01910/) (2020)
- [Theoretical Foundations of t-SNE for Visualizing High-Dimensional Clustered Data](https://mlsanity.com/paper/2105.07536/) (2021)
- [Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend](https://mlsanity.com/paper/2311.13717/) (2023)
- [Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation](https://mlsanity.com/paper/2212.11614/) (2022)
- [Quantum Generative Learning for High-Resolution Medical Image Generation](https://mlsanity.com/paper/2406.13196/) (2024)
- [Hybrid Quantum-Classical Machine Learning with PennyLane: A Comprehensive Guide for Computational Research](https://mlsanity.com/paper/2511.14786/) (2025)

## Abstract (arXiv)

Medical image classification is often constrained by limited labeled data, motivating generative augmentation; recently, quantum generative models have been proposed for this purpose, frequently reporting accuracy gains. However, such claims are typically based on single training runs, do not match the parameter budgets of the quantum and classical generators, and do not characterize the data regime in which any benefit appears. We present a controlled benchmark that isolates the contribution of a quantum generator to brain-MRI augmentation. Images are encoded into a KL-regularized latent space in which a conditional Wasserstein GAN with gradient penalty is trained using either a variational quantum generator or a classical generator of near-identical parameter count (1648 vs. 1632). Synthetic samples are decoded and used to augment a pretrained classifier across labeled data fractions from 5% to 100%, evaluated over eight random seeds with paired significance testing (with multiple-comparison correction) and with intraset diversity and latent-distribution analyses. Across all fractions, no augmentation variant significantly outperforms real-data-only training, and the quantum and classical generators are statistically indistinguishable. Any low-data benefit behaves as regularization rather than faithful data expansion:synthetic samples are off distribution and severely mode collapsed precisely where data is scarce, and the quantum generator is no more diverse thanits classical counterpart. We release the protocol as a testbed for rigorous evaluation of quantum generative augmentation in medical imaging.