Beyond a Single Mode: GAN Ensembles for Diverse Medical Data Generation
This work addresses the challenge of synthetic data generation in medical imaging, which is crucial for enhancing diagnostic models, but it is incremental as it builds on existing GAN techniques.
The paper tackled the problem of generating diverse and high-fidelity synthetic medical images by proposing a method to select optimal GAN ensembles through multi-objective optimization, resulting in improved quality and utility for downstream diagnostic tasks, as evaluated on three medical datasets with 110 configurations.
The advancement of generative AI, particularly in medical imaging, confronts the trilemma of ensuring high fidelity, diversity, and efficiency in synthetic data generation. While Generative Adversarial Networks (GANs) have shown promise across various applications, they still face challenges like mode collapse and insufficient coverage of real data distributions. This work explores the use of GAN ensembles to overcome these limitations, specifically in the context of medical imaging. By solving a multi-objective optimisation problem that balances fidelity and diversity, we propose a method for selecting an optimal ensemble of GANs tailored for medical data. The selected ensemble is capable of generating diverse synthetic medical images that are representative of true data distributions and computationally efficient. Each model in the ensemble brings a unique contribution, ensuring minimal redundancy. We conducted a comprehensive evaluation using three distinct medical datasets, testing 22 different GAN architectures with various loss functions and regularisation techniques. By sampling models at different training epochs, we crafted 110 unique configurations. The results highlight the capability of GAN ensembles to enhance the quality and utility of synthetic medical images, thereby improving the efficacy of downstream tasks such as diagnostic modelling.