Unsupervised Cross-Modality Adaptation via Dual Structural-Oriented Guidance for 3D Medical Image Segmentation
Unsupervised Cross-Modality Adaptation via Dual Structural-Oriented Guidance for 3D Medical Image Segmentation
复制标题
DOI：
10.1109/tmi.2023.3238114
复制
发表时间：
2023-01
影响因子：
10.6
通讯作者：
Junlin Xian;Xiang Lisa Li;Dandan Tu;Senhua Zhu;Changzheng Zhang;Xiaowu Liu;X. Li;Xin Yang
中科院分区：
文献类型：
--
作者：
Junlin Xian;Xiang Lisa Li;Dandan Tu;Senhua Zhu;Changzheng Zhang;Xiaowu Liu;X. Li;Xin Yang
深度卷积神经网络（CNN）在医学图像分割方面取得了令人印象深刻的性能;然而，当部署到具有异构特征的不可见数据时，其性能可能会显着下降。无监督域自适应（UDA）是解决这个问题的一个很有前途的解决方案。在这项工作中，我们提出了一种新型的UDA方法，称为双重自适应引导网络（DAG-Net），它在训练中结合了两种高效且互补的结构导向指导，以协作地将分割模型从标记的源域调整到未标记的目标域。具体来说，我们的DAG-Net由两个核心模块组成：1）基于傅立叶的对比风格增强（FCSA），它隐含地引导分割网络专注于学习模态不敏感和结构相关的特征，以及2）残差空间对齐（RSA），它提供明确的指导，以基于切片间相关性的3D先验来增强目标模态中预测的几何连续性。我们已经广泛评估了我们的方法与心脏子结构和腹部多器官分割的双向跨模态适应MRI和CT图像之间。两个不同任务的实验结果表明，我们的DAG网络大大优于最先进的UDA方法的3D医学图像分割的未标记的目标图像。
Deep convolutional neural networks (CNNs) have achieved impressive performance in medical image segmentation; however, their performance could degrade significantly when being deployed to unseen data with heterogeneous characteristics. Unsupervised domain adaptation (UDA) is a promising solution to tackle this problem. In this work, we present a novel UDA method, named dual adaptation-guiding network (DAG-Net), which incorporates two highly effective and complementary structural-oriented guidance in training to collaboratively adapt a segmentation model from a labelled source domain to an unlabeled target domain. Specifically, our DAG-Net consists of two core modules: 1) Fourier-based contrastive style augmentation (FCSA) which implicitly guides the segmentation network to focus on learning modality-insensitive and structural-relevant features, and 2) residual space alignment (RSA) which provides explicit guidance to enhance the geometric continuity of the prediction in the target modality based on a 3D prior of inter-slice correlation. We have extensively evaluated our method with cardiac substructure and abdominal multi-organ segmentation for bidirectional cross-modality adaptation between MRI and CT images. Experimental results on two different tasks demonstrate that our DAG-Net greatly outperforms the state-of-the-art UDA approaches for 3D medical image segmentation on unlabeled target images.