Pulmonary embolism (PE) is a prevalent lung disease that can lead to right ventricular hypertrophy and failure in severe cases, ranking second in severity only to myocardial infarction and sudden death. Pulmonary artery CT angiography (CTPA) is a widely used diagnostic method for PE. However, PE detection presents challenges in clinical practice due to limitations in imaging technology. CTPA can produce noises similar to PE, making confirmation of its presence time-consuming and prone to overdiagnosis. Nevertheless, the traditional segmentation method of PE can not fully consider the hierarchical structure of features, local and global spatial features of PE CT images. In this paper, we propose an automatic PE segmentation method called SCUNet++ (Swin Conv UNet++). This method incorporates multiple fusion dense skip connections between the encoder and decoder, utilizing the Swin Transformer as the encoder. And fuses features of different scales in the decoder subnetwork to compensate for spatial information loss caused by the inevitable downsampling in Swin-UNet or other state-of-the-art methods, effectively solving the above problem. We provide a theoretical analysis of this method in detail and validate it on publicly available PE CT image datasets FUMPE and CAD-PE. The experimental results indicate that our proposed method achieved a Dice similarity coefficient (DSC) of 83.47% and a Hausdorff distance 95th percentile (HD95) of 3.83 on the FUMPE dataset, as well as a DSC of 83.42% and an HD95 of 5.10 on the CAD-PE dataset. These findings demonstrate that our method exhibits strong performance in PE segmentation tasks, potentially enhancing the accuracy of automatic segmentation of PE and providing a powerful diagnostic tool for clinical physicians. Our source code and new FUMPE dataset are available at https://github.com/JustlfC03/SCUNet-plusplus.

翻译：肺栓塞（PE）是一种常见的肺部疾病，严重时可导致右心室肥厚和衰竭，其严重程度仅次于心肌梗死和猝死。肺动脉CT血管成像（CTPA）是临床广泛使用的PE诊断方法。然而，由于成像技术的局限性，PE检测在临床实践中面临挑战。CTPA可能产生与PE相似的噪声，导致确诊耗时且易出现过度诊断。此外，传统PE分割方法未能充分考虑PE CT图像中特征的层次结构、局部与全局空间特征。本文提出了一种名为SCUNet++（Swin Conv UNet++）的自动PE分割方法。该方法在编码器与解码器之间引入多重融合致密跳跃连接，采用Swin Transformer作为编码器，并在解码器子网络中融合不同尺度的特征，以弥补Swin-UNet等现有方法因不可避免的下采样造成的空间信息损失，有效解决了上述问题。我们对本方法进行了详细的理论分析，并在公开PE CT图像数据集FUMPE和CAD-PE上进行了验证。实验结果表明，在FUMPE数据集上，本方法实现了83.47%的Dice相似系数（DSC）和3.83的Hausdorff距离第95百分位数（HD95）；在CAD-PE数据集上，DSC达到83.42%，HD95为5.10。这些发现表明，本方法在PE分割任务中表现出强劲性能，有望提升PE自动分割的准确性，并为临床医生提供强大的诊断工具。我们的源代码及更新的FUMPE数据集已发布在https://github.com/JustlfC03/SCUNet-plusplus。