SinGAN-Seg: Synthetic training data generation for medical image segmentation
This addresses the challenge of data scarcity in medical imaging for segmentation tasks, particularly for rare abnormalities, by providing a privacy-preserving synthetic data solution, though it is incremental as it builds on existing GAN and style transfer techniques.
The paper tackles the problem of limited training data for medical image segmentation by introducing SinGAN-Seg, a synthetic data generation pipeline that uses only a single image and its ground truth mask to produce alternative datasets. The results show that models trained with synthetic data achieve performance close to those trained on real data in data-rich scenarios and improve performance when data is scarce, with quantitative comparisons indicating it outperforms other state-of-the-art GANs in limited-data settings.
Analyzing medical data to find abnormalities is a time-consuming and costly task, particularly for rare abnormalities, requiring tremendous efforts from medical experts. Artificial intelligence has become a popular tool for the automatic processing of medical data, acting as a supportive tool for doctors. However, the machine learning models used to build these tools are highly dependent on the data used to train them. Large amounts of data can be difficult to obtain in medicine due to privacy, expensive and time-consuming annotations, and a general lack of data samples for infrequent lesions. Here, we present a novel synthetic data generation pipeline, called SinGAN-Seg, to produce synthetic medical images with corresponding masks using a single training image. Our method is different from the traditional GANs because our model needs only a single image and the corresponding ground truth to train. Our method produces alternative artificial segmentation datasets with ground truth masks when real datasets are not allowed to share. The pipeline is evaluated using qualitative and quantitative comparisons between real and synthetic data to show that the style transfer technique used in our pipeline significantly improves the quality of the generated data and our method is better than other state-of-the-art GANs to prepare synthetic images when the size of training datasets are limited. By training UNet++ using both real and the synthetic data generated from the SinGAN-Seg pipeline, we show that models trained with synthetic data have very close performances to those trained on real data when the datasets have a considerable amount of data. In contrast, Synthetic data generated from the SinGAN-Seg pipeline can improve the performance of segmentation models when training datasets do not have a considerable amount of data. The code is available on GitHub.