Enhancing Fetal Plane Classification Accuracy with Data Augmentation Using Diffusion Models
This addresses data scarcity in medical imaging for ultrasound diagnosis, but is incremental as it applies an existing method (diffusion models) to a specific domain.
The paper tackled the problem of limited annotated ultrasound images for fetal health assessment by using diffusion models to generate synthetic images, which improved fetal plane classification accuracy when incorporated into training pipelines compared to using real images alone.
Ultrasound imaging is widely used in medical diagnosis, especially for fetal health assessment. However, the availability of high-quality annotated ultrasound images is limited, which restricts the training of machine learning models. In this paper, we investigate the use of diffusion models to generate synthetic ultrasound images to improve the performance on fetal plane classification. We train different classifiers first on synthetic images and then fine-tune them with real images. Extensive experimental results demonstrate that incorporating generated images into training pipelines leads to better classification accuracy than training with real images alone. The findings suggest that generating synthetic data using diffusion models can be a valuable tool in overcoming the challenges of data scarcity in ultrasound medical imaging.