基于改进CycleGAN模型的跨模态迁移学习用于超声图像中肾脏的精准分割
研究提出Seg-CycleGAN跨模态迁移学习方法,从带标注的腹部CT图像生成模拟肾脏超声图像,结合少量真实标注超声图像微调分割网络。在全部测试集上Dice相似系数达0.8548,异常肾脏测试集为0.7622,较现有数据增强和迁移学习方法提升了分割精度与泛化能力。
要点
- Seg-CycleGAN从标注腹部CT生成模拟肾脏超声,缓解超声标注稀缺问题。
- 全部测试集Dice相似系数0.8548,异常肾脏测试集为0.7622。
- 该方法在有限训练数据下提升了分割网络的精度与泛化能力。
核心结论
- 与现有数据增强和迁移学习方法相比,该方法在有限训练数据集上提升了肾脏超声图像分割网络的精度与泛化能力。
- 该方法因此有潜力显著降低临床环境中的标注成本。
研究设计与样本
- 研究提出并验证一种基于改进CycleGAN的跨模态迁移学习方法Seg-CycleGAN,用于肾脏超声图像分割。
- Seg-CycleGAN包含标准CycleGAN网络(从公开标注腹部CT数据集视觉模拟肾脏超声)和分割网络(确保超声图像中肾脏解剖结构准确)。
- 基于大量模拟肾脏超声图像和少量真实标注肾脏超声图像,采用微调策略获得分割结果。
- 在正常和异常肾脏超声图像上测试该方法,全部测试集Dice相似系数0.8548,异常测试集0.7622。
诊断标准与关键数值
- 分割精度以Dice相似系数评价:全部测试数据集为0.8548,异常测试数据集为0.7622。
临床应用与阅片要点
- 作者认为该方法有潜力显著降低临床环境中的标注成本。
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: Deep-learning algorithms have been widely applied in the field of automatic kidney ultrasound (US) image segmentation. However, obtaining a large number of accurate kidney labels clinically is very difficult and time-consuming. To solve this problem, we have proposed an efficient cross-modal transfer learning method to improve the performance of the segmentation network on a limited labeled kidney US dataset.
METHODS: We aim to implement an improved image-to-image translation network called Seg-CycleGAN to generate accurate annotated kidney US data from labeled abdomen computed tomography images. The Seg-CycleGAN framework primarily consists of two structures: (i) a standard CycleGAN network to visually simulate kidney US from a publicly available labeled abdomen computed tomography dataset; (ii) and a segmentation network to ensure accurate kidney anatomical structures in US images. Based on the large number of simulated kidney US images and small number of real annotated kidney US images, we then aimed to employ a fine-tuning strategy to obtain better segmentation results.
RESULTS: To validate the effectiveness of the proposed method, we tested this method on both normal and abnormal kidney US images. The experimental results showed that the proposed method achieved a segmentation accuracy of 0.8548 in dice similarity coefficient on all testing datasets and 0.7622 on the abnormal testing dataset.
CONCLUSIONS: Compared with existing data augmentation and transfer learning methods, the proposed method improved the accuracy and generalization of the kidney US image segmentation network on a limited number of training datasets. It therefore has the potential to significantly reduce annotation costs in clinical settings.
引用
- Guo S, Chen H, Sheng X, et al. Cross-modal Transfer Learning Based on an Improved CycleGAN Model for Accurate Kidney Segmentation in Ultrasound Images. Ultrasound Med Biol. 2024. PMID: 39181806. doi:10.1016/j.ultrasmedbio.2024.06.009
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。