Zhang Kun, Xu Peixia, Wang Meirong, Lin Pengcheng, Crookes Danny, He Bosheng, Hua Liang
School of Electrical Engineering, Nantong University, Nantong, Jiangsu, China.
Nantong Key Laboratory of Intelligent Control and Intelligent Computing, Nantong Institute of Technology, Nantong, Jiangsu, China.
Front Physiol. 2023 Dec 11;14:1308987. doi: 10.3389/fphys.2023.1308987. eCollection 2023.
The structural morphology of mesenteric artery vessels is of significant importance for the diagnosis and treatment of colorectal cancer. However, developing automated vessel segmentation methods for this purpose remains challenging. Existing convolution-based segmentation methods have limitations in capturing long-range dependencies, while transformer-based models require large datasets, making them less suitable for tasks with limited training samples. Moreover, over-segmentation, mis-segmentation, and vessel discontinuity are common challenges in vessel segmentation tasks. To address these issues, we propose a parallel encoding architecture that combines transformers and convolutions to retain the advantages of both approaches. The model effectively learns position deviations and enhances robustness for small-scale datasets. Additionally, we introduce a vessel edge capture module to improve vessel continuity and topology. Extensive experimental results demonstrate the improved performance of our model, with Dice Similarity Coefficient and Average Hausdorff Distance scores of 81.64% and 7.7428, respectively.
肠系膜动脉血管的结构形态对于结直肠癌的诊断和治疗具有重要意义。然而，为此开发自动血管分割方法仍然具有挑战性。现有的基于卷积的分割方法在捕捉长程依赖方面存在局限性，而基于Transformer的模型需要大量数据集，这使得它们不太适合训练样本有限的任务。此外，过分割、误分割和血管不连续性是血管分割任务中常见的挑战。为了解决这些问题，我们提出了一种并行编码架构，该架构结合了Transformer和卷积，以保留两种方法的优点。该模型有效地学习位置偏差，并增强了对小规模数据集的鲁棒性。此外，我们引入了一个血管边缘捕捉模块来改善血管的连续性和拓扑结构。大量实验结果表明，我们的模型性能得到了提升，Dice相似系数和平均豪斯多夫距离分数分别为81.64%和7.7428。
