Generative learning models in medical research are crucial in developing training data for deep learning models and advancing diagnostic tools, but the problem of high quality, diverse images is an open topic of research. Quantum-enhanced generative models have been proposed and tested in the literature but have been restricted to small problems below the scale of industry relevance. In this paper, we propose quantum-enhanced diffusion and variational autoencoder (VAE) models and test them on the Fundus retinal image generation task. In our numerical experiments, the images generated using quantum-enhanced models are of higher quality and match more closely in features to the real image distribution compared to the ones generated using classical diffusion models, even when the classical diffusion models are larger than the quantum model. Additionally, we perform noisy testing and experimental runs on hardware to confirm the numerical experiments, finding that quantum-enhanced diffusion model can sometimes produce higher quality images, both in terms of diversity and fidelity, when tested with quantum noise.
Generative learning models in medical research are crucial in developing training data for deep learning models and advancing diagnostic tools, but the problem of high quality, diverse images is an open topic of research. Quantum-enhanced generative models have been proposed and tested in the literature but have been restricted to small problems below the scale of industry relevance. In this paper, we propose quantum-enhanced diffusion and variational autoencoder (VAE) models and test them on the Fundus retinal image generation task. In our numerical experiments, the images generated using quantum-enhanced models are of higher quality and match more closely in features to the real image distribution compared to the ones generated using classical diffusion models, even when the classical diffusion models are larger than the quantum model. Additionally, we perform noisy testing and experimental runs on hardware to confirm the numerical experiments, finding that quantum-enhanced diffusion model can sometimes produce higher quality images, both in terms of diversity and fidelity, when tested with quantum noise.
Generative Artificial Intelligence is one of the most relevant technologies of our century, enabling digital machines not only to analyze or classify data but also to generate new content such as images, text, and video. This technology relies on deep learning algorithms designed to capture complex relationships from finite data sets. In this context, Diffusion Models have recently emerged as state-of-the-art in deep generative modeling thanks to their ability to produce high-quality data. Their pipeline typically consists of a forward diffusion process, where data samples are progressively corrupted into pure (classical) noise, and a reverse denoising process, where deep neural networks learn to reverse the diffusion process and then generate new synthetic samples. In parallel, Quantum Machine Learning represents one of the most promising applications of quantum computing. However, currently available quantum processors, known as Noisy Intermediate-Scale Quantum (NISQ) devices, are composed of tens or hundreds of noisy qubits. Therefore, designing scalable and efficient practical quantum algorithms represents a significant challenge. This thesis proposes the first generalization of classical Denoising Diffusion Probabilistic Models to the quantum domain, introducing the novel generative paradigm of Quantum Diffusion Models. In particular, the three possible scenarios are formalized and implemented: (i) classical data corrupted with Gaussian noise and a reverse process implemented via a quantum neural network; (ii) quantum data corrupted with quantum noise and a denoising process through a classical deep neural network; and (iii) a fully quantum approach, where both forward and backward processes are implemented within a quantum framework. Subsequently, the impact of different stochastic dynamics in the forward process is analyzed using the formalism of Quantum Stochastic Walks. We observe that a specific hybrid quantum-classical dynamics produces more statistically robust models, capable of generating sets of images closely resembling real ones compared to purely classical dynamics. Furthermore, we propose a hybrid quantum-classical diffusion model based on Quantum Walks that exploits the intrinsic noise of real quantum processors as a useful resource for generating images. This model is implementable on current NISQ devices and scalable, as it allows the generation of images of any size, requiring q + 1 qubits for grayscale images with pixel intensities in the range [0, 2^q - 1]. Finally, an application in the context of medical imaging is presented, specifically the generation of 64 × 64 color images of blood cells from the BloodMNIST dataset and 200 × 200 brain MRI images from the BraTS2020 dataset.
We propose a quantum implicit neural representation (QINR)-based autoencoder (AE) and variational autoencoder (VAE) for image reconstruction and generation tasks. Our purpose is to demonstrate that the QINR in VAEs and AEs can transform information from the latent space into highly rich, periodic, and high-frequency features. Additionally, we aim to show that the QINR-VAE can be more stable than various quantum generative adversarial network (QGAN) models in image generation because it can address the low diversity problem. Our quantum-classical hybrid models consist of a classical convolutional neural network (CNN) encoder and a quantum-based QINR decoder. We train the QINR-AE/VAE with binary cross-entropy with logits (BCEWithLogits) as the reconstruction loss. For the QINR-VAE, we additionally employ Kullback-Leibler divergence for latent regularization with beta/capacity scheduling to prevent posterior collapse. We introduce learnable angle-scaling in data reuploading to address optimization challenges. We test our models on the MNIST, E-MNIST, and Fashion MNIST datasets to reconstruct and generate images. Our results demonstrate that the QINR structure in VAE can produce a wider variety of images with a small amount of data than various generative models that have been studied. We observe that the generated/reconstructed images from the QINR-VAE/AE are clear with sharp boundaries and details. Overall, we find that the addition of QINR-based quantum layers into the AE/VAE frameworks shows improved performance of reconstruction/generation under the constrained experimental setting relative to the specific baselines.
Abstract Recent proposals for quantum generative adversarial networks (GANs) suffer from the issue of mode collapse, analogous to classical GANs, wherein the distribution learnt by the GAN fails to capture the high mode complexities of the target distribution. Mode collapse can arise due to the use of uninformed prior distributions in the generative learning task. To alleviate the issue of mode collapse for quantum GANs, this work presents a novel hybrid quantum-classical generative model, the VAE-QWGAN, which combines the strengths of a classical variational autoencoder (VAE) with a hybrid quantum Wasserstein GAN (QWGAN). The VAE-QWGAN fuses the VAE decoder and QWGAN generator into a single quantum model and utilizes the VAE encoder for data-dependent latent vector sampling during training. This, in turn, enhances the diversity and quality of generated images. To generate new data from the trained model at inference, we sample from a Gaussian mixture model (GMM) prior that is learnt on the latent vectors generated during training. We conduct extensive experiments for image generation QGANs on MNIST/Fashion-MNIST datasets and compute a range of metrics that measure the diversity and quality of generated samples. We show that VAE-QWGAN demonstrates significant improvement over existing QGAN approaches.
Variational Autoencoders (VAEs) are fundamental for generative modeling and image reconstruction, yet their performance often struggles to maintain high fidelity in reconstructions. This study introduces a hybrid model, Quantum Variational Autoencoder (Q-VAE), which integrates quantum encoding within the encoder while utilizing fully connected layers to extract meaningful representations. The decoder uses transposed convolution layers for up-sampling. The Q-VAE is evaluated against the classical VAE and the classical direct-passing VAE, which utilizes windowed pooling filters. Results on the MNIST and USPS datasets demonstrate that Q-VAE consistently outperforms classical approaches, achieving lower Fréchet Inception Distance scores, thereby indicating superior image fidelity and enhanced reconstruction quality. These findings highlight the potential of Q-VAE for high-quality synthetic data generation and improved image reconstruction in generative models.
With millions of medical data being produced daily, it is important to leverage current technology to improve the healthcare system. As traditional deep learning models are unable to effectively handle high-dimensional data, a hybrid classical-quantum approach is used to enhance traditional deep learning algorithms. The hybrid classical-quantum models are built upon the classical deep learning framework with quantum techniques. The classical layers are utilized for feature extraction while the quantum layer is used for computational tasks. This addresses computational limitations and data imbalance challenges in medical image analysis. Transfer learning models, such as ResNet18 and InceptionV3, are used in conjunction with a quantum variational circuit to perform the task. The model is trained on a chest X-ray dataset, which consists of two sets of data: binary and multiclass. The binary dataset consists of Normal and COVID-19 images, while the multiclass dataset has COVID-19, Normal, and Tuberculosis images for classification. PennyLane, as a simulator, has been used to perform quantum computing. The dataset has also been used to train the traditional transfer learning models, pre-trained ResNet18, and their results have been compared. Out of all the models tested, the hybrid classical-quantum model, namely Hybrid ResNet18, performed the best. It achieved an accuracy of 93.22% for the binary classification task and 93.91% for the multiclass classification. The results show that there is a statistically significant improvement in classification accuracy and F1-score of the hybrid approach over the classical transfer learning baselines under a simulation-based environment. This sets the stage for further research on real-world physical quantum hardware. Class imbalance and overlapping predictions have been addressed using methods such as data augmentation and confusion matrix analysis. Thus, quantum machine learning could be used as a vital tool to analyze medical data for better diagnostic results.
Classical diffusion models have achieved remarkable results in terms of sample quality and variability. The quantum counterpart of these models is still to be explored thoroughly and offers a promising research direction in the field of quantum generative models. In this work, we introduce two versions of a quantum diffusion model, using parameterized quantum circuits to sample from quantum state distributions, while performing training via classical simulations. The first model is a quantum-hardware-oriented design, based on denoising diffusion probabilistic models, for which we demonstrate an implementation on real quantum hardware. The second model is a hybrid approach, based on denoising diffusion implicit models, that uses a classical neural network to enhance the expressive power. We show that the second version produces samples of higher quality and variability, but requires additional classical-quantum encoding and decoding overhead, underscoring a trade-off between expressive power and hardware efficiency. We demonstrate our method on MNIST images encoded as quantum states, as sample quality is easier to visualize and objective metrics are more widely available. While our results do not surpass classical diffusion models in the generation of classical samples, this study suggests the viability of using quantum diffusion models for learning quantum state distributions.