Diffusion Model-based Medical Image Generation as a Potential Data Augmentation Strategy for AI Applications.
Authors
Affiliations (4)
Affiliations (4)
- Institute of Medical Technology, Peking University Health Science Center, Beijing 100191, China.
- State Key Laboratory of Nuclear Physics and Technology, Peking University School of Physics, Beijing 100871, China.
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, 999077, China.
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital & Institute, Beijing 100142, China.
Abstract
This study explored a generative image synthesis method based on diffusion models, potentially providing a low-cost and high-efficiency training data augmentation strategy for medical artificial intelligence (AI) applications. The MedMNIST v2 dataset was utilized as a small-volume training dataset under low-performance computing conditions. Based on the characteristics of existing samples, new medical images were synthesized using the proposed annotated diffusion model. In addition to observational assessment, quantitative evaluation was performed based on the gradient descent of the loss function during the generation process and the Fréchet Inception Distance (FID), using various loss functions and feature vector dimensions. Compared to the original data, the proposed diffusion model successfully generated medical images of similar styles but with dramatically varied anatomic details. The model trained with the Huber loss function achieved a higher FID of 15.2 at a feature vector dimension of 2048, compared with the model trained with the L2 loss function, which achieved the best FID of 0.85 at a feature vector dimension of 64. The use of the Huber loss enhanced model robustness, while FID values indicated acceptable similarity between generated and real images. Future work should explore the application of these models to more complex datasets and clinical scenarios. This study demonstrated that diffusion model-based medical image synthesis is potentially applicable as an augmentation strategy for AI, particularly in situations where access to real clinical data is limited. Optimal training parameters were also proposed by evaluating the dimensionality of feature vectors in FID calculations and the complexity of loss functions.