IMPROVE: Improving Medical Plausibility without Reliance on HumanValidation -- An Enhanced Prototype-Guided Diffusion Framework
This addresses the need for more medically accurate synthetic images in healthcare applications, such as rare disease dataset enhancement, without the slow and expensive process of human expert feedback, representing a novel method for a known bottleneck.
The paper tackles the problem of low medical plausibility in synthetic medical images generated by existing models, which rely on costly human feedback for improvement, and proposes IMPROVE, a prototype-guided diffusion framework that substantially enhances biological plausibility without human validation, as demonstrated on Bone Marrow and HAM10000 datasets.
Generative models have proven to be very effective in generating synthetic medical images and find applications in downstream tasks such as enhancing rare disease datasets, long-tailed dataset augmentation, and scaling machine learning algorithms. For medical applications, the synthetically generated medical images by such models are still reasonable in quality when evaluated based on traditional metrics such as FID score, precision, and recall. However, these metrics fail to capture the medical/biological plausibility of the generated images. Human expert feedback has been used to get biological plausibility which demonstrates that these generated images have very low plausibility. Recently, the research community has further integrated this human feedback through Reinforcement Learning from Human Feedback(RLHF), which generates more medically plausible images. However, incorporating human feedback is a costly and slow process. In this work, we propose a novel approach to improve the medical plausibility of generated images without the need for human feedback. We introduce IMPROVE:Improving Medical Plausibility without Reliance on Human Validation - An Enhanced Prototype-Guided Diffusion Framework, a prototype-guided diffusion process for medical image generation and show that it substantially enhances the biological plausibility of the generated medical images without the need for any human feedback. We perform experiments on Bone Marrow and HAM10000 datasets and show that medical accuracy can be substantially increased without human feedback.