School of Modern Information Technology, Zhejiang Polytechnic University of Mechanical and Electrical Engineering, 528 Binwen Road, Binjiang District, Hangzhou, 310053, Zhejiang, China.
Department of Ultrasound, The Second Affiliated Hospital, Zhejiang University School of Medicine, 88 Jiefang Road, Shangcheng District, Hangzhou 310009, Zhejiang, China.
Comput Biol Med. 2024 Dec;183:109274. doi: 10.1016/j.compbiomed.2024.109274. Epub 2024 Oct 30.
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.
自动分割乳腺肿瘤超声图像可以为医生提供病变和感兴趣区域的客观、高效参考。数据集优化和模型结构优化对于实现最佳的图像分割性能都至关重要，而在乳腺肿瘤超声数据集不足以满足模型训练需求的情况下，仅通过模型结构增强来满足临床需求可能具有挑战性。虽然已经有大量研究致力于增强深度学习模型的架构以提高肿瘤分割性能，但针对数据集增强的工作相对较少。当前的数据增强技术，如旋转和变换，通常在提高模型准确性方面效果有限。用于生成合成图像的深度学习方法，如 GAN，主要用于生成视觉上自然的图像。然而，这些生成图像的标签准确性仍需要人工验证，并且图像缺乏多样性。因此，它们不适合用于图像分割模型的训练数据集增强。本研究提出了一种新的数据集增强方法，通过将肿瘤区域嵌入到正常图像中来生成合成图像。我们探索了两种合成方法：一种使用相同的背景，另一种使用不同的背景。通过实验验证，我们证明了合成数据集在增强图像分割模型性能方面的有效性。值得注意的是，使用不同背景的合成方法比使用相同背景的方法具有更好的改进效果。我们的研究结果为医学图像分析，特别是肿瘤分割提供了一种实用且有效的数据集增强策略，可显著提高分割模型的准确性和可靠性。
