Recent unsupervised domain adaptation (UDA) methods in medical image segmentation commonly utilize Generative Adversarial Networks (GANs) for domain translation. However, the translated images often exhibit a distribution deviation from the ideal due to the inherent instability of GANs, leading to challenges such as visual inconsistency and incorrect style, consequently causing the segmentation model to fall into the fixed wrong pattern. To address this problem, we propose a novel UDA framework known as Dual Domain Distribution Disruption with Semantics Preservation (DDSP). Departing from the idea of generating images conforming to the target domain distribution in GAN-based UDA methods, we make the model domain-agnostic and focus on anatomical structural information by leveraging semantic information as constraints to guide the model to adapt to images with disrupted distributions in both source and target domains. Furthermore, we introduce the inter-channel similarity feature alignment based on the domain-invariant structural prior information, which facilitates the shared pixel-wise classifier to achieve robust performance on target domain features by aligning the source and target domain features across channels. Without any exaggeration, our method significantly outperforms existing state-of-the-art UDA methods on three public datasets (i.e., the heart dataset, the brain dataset, and the prostate dataset). The code is available at https://github.com/MIXAILAB/DDSPSeg.

中文翻译：

---

具有语义保留的双域分布中断：用于医学图像分割的无监督域适应


最近医学图像分割中的无监督域适应（UDA）方法通常利用生成对抗网络（GAN）进行域转换。然而，由于 GAN 固有的不稳定性，翻译后的图像常常表现出与理想分布的偏差，导致视觉不一致和风格不正确等挑战，从而导致分割模型陷入固定的错误模式。为了解决这个问题，我们提出了一种新颖的 UDA 框架，称为具有语义保留的双域分布中断 (DDSP)。与基于 GAN 的 UDA 方法中生成符合目标域分布的图像的思想不同，我们使模型与域无关，并通过利用语义信息作为约束来指导模型适应分布混乱的图像，并专注于解剖结构信息在源域和目标域中。此外，我们引入了基于域不变结构先验信息的通道间相似性特征对齐，这有助于共享像素分类器通过跨通道对齐源域特征和目标域特征来实现目标域特征的鲁棒性能。毫不夸张地说，我们的方法在三个公共数据集（即心脏数据集、大脑数据集和前列腺数据集）上显着优于现有最先进的 UDA 方法。代码可在 https://github.com/MIXAILAB/DDSPSeg 获取。