通过内容与风格联合增强，提升医学图像分割模型的泛化能力。
ConStyX: Content Style Augmentation for Generalizable Medical Image Segmentation
- 同时增强图像内容与风格，扩大数据域覆盖范围。
- 在训练中保留优质增强特征，抑制过度增强的负面影响。
- 适合需要跨域泛化的医学图像分割研究者使用。
医学图像通常来自多个数据域，导致域偏移影响分割模型性能。领域泛化（DG）旨在通过训练具备强泛化能力的模型来应对这一问题。近期大量基于域随机化的DG方法被提出，但存在两个局限：1）受限于仅依赖图像风格扰动，域随机化效率低下；2）忽视了过度增强图像对模型训练的负面作用。为此，我们提出一种新型基于域随机化的DG方法——内容风格增强（ConStyX），用于通用医学图像分割。具体而言，ConStyX一方面同时增强训练数据的内容与风格，使增强后数据能更广泛覆盖不同数据域；另一方面，在模型训练中利用良好增强特征，同时缓解过度增强特征的负面影响。在多个数据域上的大量实验表明，ConStyX实现了更优的泛化性能。代码已公开于https://github.com/jwxsp1/ConStyX。
原文摘要 · Abstract (English)
Medical images are usually collected from multiple domains, leading to domain shifts that impair the performance of medical image segmentation models. Domain Generalization (DG) aims to address this issue by training a robust model with strong generalizability. Recently, numerous domain randomization-based DG methods have been proposed. However, these methods suffer from the following limitations: 1) constrained efficiency of domain randomization due to their exclusive dependence on image style perturbation, and 2) neglect of the adverse effects of over-augmented images on model training. To address these issues, we propose a novel domain randomization-based DG method, called content style augmentation (ConStyX), for generalizable medical image segmentation. Specifically, ConStyX 1) augments the content and style of training data, allowing the augmented training data to better cover a wider range of data domains, and 2) leverages well-augmented features while mitigating the negative effects of over-augmented features during model training. Extensive experiments across multiple domains demonstrate that our ConStyX achieves superior generalization performance. The code is available at https://github.com/jwxsp1/ConStyX.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。