College of Computer Science, Shenyang Aerospace University, Shenyang, China.
School of Software, Jiangxi Normal University, Nanchang, China.
Comput Biol Med. 2023 Sep;164:107269. doi: 10.1016/j.compbiomed.2023.107269. Epub 2023 Jul 18.
There has been steady progress in the field of deep learning-based blood vessel segmentation. However, several challenging issues still continue to limit its progress, including inadequate sample sizes, the neglect of contextual information, and the loss of microvascular details. To address these limitations, we propose a dual-path deep learning framework for blood vessel segmentation. In our framework, the fundus images are divided into concentric patches with different scales to alleviate the overfitting problem. Then, a Multi-scale Context Dense Aggregation Network (MCDAU-Net) is proposed to accurately extract the blood vessel boundaries from these patches. In MCDAU-Net, a Cascaded Dilated Spatial Pyramid Pooling (CDSPP) module is designed and incorporated into intermediate layers of the model, enhancing the receptive field and producing feature maps enriched with contextual information. To improve segmentation performance for low-contrast vessels, we propose an InceptionConv (IConv) module, which can explore deeper semantic features and suppress the propagation of non-vessel information. Furthermore, we design a Multi-scale Adaptive Feature Aggregation (MAFA) module to fuse the multi-scale feature by assigning adaptive weight coefficients to different feature maps through skip connections. Finally, to explore the complementary contextual information and enhance the continuity of microvascular structures, a fusion module is designed to combine the segmentation results obtained from patches of different sizes, achieving fine microvascular segmentation performance. In order to assess the effectiveness of our approach, we conducted evaluations on three widely-used public datasets: DRIVE, CHASE-DB1, and STARE. Our findings reveal a remarkable advancement over the current state-of-the-art (SOTA) techniques, with the mean values of Se and F1 scores being an increase of 7.9% and 4.7%, respectively. The code is available at https://github.com/bai101315/MCDAU-Net.
在基于深度学习的血管分割领域已经取得了稳步的进展。然而，一些具有挑战性的问题仍然继续限制其进展，包括样本量不足、忽略上下文信息以及微血管细节的丢失。为了解决这些限制，我们提出了一种用于血管分割的双路径深度学习框架。在我们的框架中，将眼底图像划分为具有不同尺度的同心斑块，以缓解过拟合问题。然后，提出了一种多尺度上下文密集聚合网络（MCDAU-Net），从这些斑块中准确提取血管边界。在 MCDAU-Net 中，设计并将级联扩张空间金字塔池化（CDSPP）模块合并到模型的中间层中，增强感受野并生成富含上下文信息的特征图。为了提高低对比度血管的分割性能，我们提出了一种 InceptionConv（IConv）模块，它可以探索更深层次的语义特征并抑制非血管信息的传播。此外，我们设计了一种多尺度自适应特征聚合（MAFA）模块，通过跳过连接为不同的特征图分配自适应权系数，融合多尺度特征。最后，为了探索互补的上下文信息并增强微血管结构的连续性，设计了一个融合模块，以结合来自不同大小斑块的分割结果，实现精细的微血管分割性能。为了评估我们方法的有效性，我们在三个广泛使用的公共数据集上进行了评估：DRIVE、CHASE-DB1 和 STARE。我们的研究结果表明，与当前最先进的技术（SOTA）相比，我们的方法取得了显著的进步，Se 和 F1 分数的平均值分别提高了 7.9%和 4.7%。代码可在 https://github.com/bai101315/MCDAU-Net 上获得。
