Chen Xu, Pang Yunkui, Yap Pew-Thian, Lian Jun
College of Computer Science and Technology, Huaqiao University, Xiamen, Fujian, China.
Key Laboratory of Computer Vision and Machine Learning (Huaqiao University), Fujian Province University, Xiamen, Fujian, China.
Med Phys. 2024 Dec;51(12):8804-8813. doi: 10.1002/mp.17378. Epub 2024 Sep 3.
Cone beam computed tomography (CBCT) image segmentation is crucial in prostate cancer radiotherapy, enabling precise delineation of the prostate gland for accurate treatment planning and delivery. However, the poor quality of CBCT images poses challenges in clinical practice, making annotation difficult due to factors such as image noise, low contrast, and organ deformation.
The objective of this study is to create a segmentation model for the label-free target domain (CBCT), leveraging valuable insights derived from the label-rich source domain (CT). This goal is achieved by addressing the domain gap across diverse domains through the implementation of a cross-modality medical image segmentation framework.
Our approach introduces a multi-scale domain adaptive segmentation method, performing domain adaptation simultaneously at both the image and feature levels. The primary innovation lies in a novel multi-scale anatomical regularization approach, which (i) aligns the target domain feature space with the source domain feature space at multiple spatial scales simultaneously, and (ii) exchanges information across different scales to fuse knowledge from multi-scale perspectives.
Quantitative and qualitative experiments were conducted on pelvic CBCT segmentation tasks. The training dataset comprises 40 unpaired CBCT-CT images with only CT images annotated. The validation and testing datasets consist of 5 and 10 CT images, respectively, all with annotations. The experimental results demonstrate the superior performance of our method compared to other state-of-the-art cross-modality medical image segmentation methods. The Dice similarity coefficients (DSC) for CBCT image segmentation results is %, and the average symmetric surface distance (ASSD) is . Statistical analysis confirms the statistical significance of the improvements achieved by our method.
Our method exhibits superiority in pelvic CBCT image segmentation compared to its counterparts.
锥形束计算机断层扫描（CBCT）图像分割在前列腺癌放疗中至关重要，它能够精确勾勒前列腺，以进行准确的治疗计划和实施。然而，CBCT图像质量较差，在临床实践中带来了挑战，由于图像噪声、低对比度和器官变形等因素，使得标注变得困难。
本研究的目的是利用从富含标签的源域（CT）中获得的有价值见解，为无标签目标域（CBCT）创建一个分割模型。通过实施跨模态医学图像分割框架来解决不同域之间的域差距，从而实现这一目标。
我们的方法引入了一种多尺度域自适应分割方法，在图像和特征层面同时进行域自适应。主要创新在于一种新颖的多尺度解剖正则化方法，该方法（i）在多个空间尺度上同时将目标域特征空间与源域特征空间对齐，（ii）跨不同尺度交换信息，以从多尺度视角融合知识。
对盆腔CBCT分割任务进行了定量和定性实验。训练数据集包括40对未配对的CBCT-CT图像，其中只有CT图像有标注。验证和测试数据集分别由5张和10张CT图像组成，所有图像均有标注。实验结果表明，与其他现有跨模态医学图像分割方法相比，我们的方法具有卓越的性能。CBCT图像分割结果的骰子相似系数（DSC）为 %，平均对称表面距离（ASSD）为 。统计分析证实了我们的方法所取得改进的统计学意义。
与同类方法相比，我们的方法在盆腔CBCT图像分割中表现出优越性。
