On efficient expanding training datasets of breast tumor ultrasound segmentation model

Automatic segmentation of breast tumor ultrasound images can provide doctors with objective and efficient references for lesions and regions of interest. Both dataset optimization and model structure optimization are crucial for achieving optimal image segmentation performance, and it can be challenging to satisfy the clinical needs solely through model structure enhancements in the context of insufficient breast tumor ultrasound datasets for model training. While significant research has focused on enhancing the architecture of deep learning models to improve tumor segmentation performance, there is a relative paucity of work dedicated to dataset augmentation. Current data augmentation techniques, such as rotation and transformation, often yield insufficient improvements in model accuracy. The deep learning methods used for generating synthetic images, such as GANs is primarily applied to produce visually natural-looking images. Nevertheless, the accuracy of the labels for these generated images still requires manual verification, and the images exhibit a lack of diversity. Therefore, they are not suitable for the training datasets augmentation of image segmentation models. This study introduces a novel dataset augmentation approach that generates synthetic images by embedding tumor regions into normal images. We explore two synthetic methods: one using identical backgrounds and another with varying backgrounds. Through experimental validation, we demonstrate the efficiency of the synthetic datasets in enhancing the performance of image segmentation models. Notably, the synthetic method utilizing different backgrounds exhibits superior improvement compared to the identical background approach. Our findings contribute to medical image analysis, particularly in tumor segmentation, by providing a practical and effective dataset augmentation strategy that can significantly improve the accuracy and reliability of segmentation models.