School of Automation, Northwestern Polytechnical University, Xi'an, China.
Shenzhen Research Institute of Northwestern Polytechnical University, Shenzhen, Guangdong, China.
J Biophotonics. 2022 Oct;15(10):e202200067. doi: 10.1002/jbio.202200067. Epub 2022 Jul 7.
Automatic optical coherence tomography angiography (OCTA) vessel segmentation is of great significance to retinal disease diagnoses. Due to the complex vascular structure, however, various existing factors make the segmentation task challenging. This paper reports a novel end-to-end three-stage channel and position attention (CPA) module integrated graph reasoning convolutional neural network (CGNet) for retinal OCTA vessel segmentation. Specifically, in the coarse stage, both CPA and graph reasoning network (GRN) modules are integrated in between a U-shaped neural network encoder and decoder to acquire vessel confidence maps. After being directed into a fine stage, such confidence maps are concatenated with the original image and the generated fine image map as a 3-channel image to refine retinal micro-vasculatures. Finally, both the fine and refined images are fused at the refining stage as the segmentation results. Experiments with different public datasets are conducted to verify the efficacy of the proposed CGNet. Results show that by employing the end-to-end training scheme and the integrated CPA and GRN modules, CGNet achieves 94.29% and 85.62% in area under the ROC curve (AUC) for the two different datasets, outperforming the state-of-the-art existing methods with both improved operability and reduced complexity in different cases. Code is available at https://github.com/GE-123-cpu/CGnet-for-vessel-segmentation.
自动光学相干断层扫描血管造影术 (OCTA) 血管分割对视网膜疾病的诊断具有重要意义。然而，由于血管结构复杂，各种现有因素使得分割任务具有挑战性。本文提出了一种新颖的端到端三阶段通道和位置注意 (CPA) 模块集成图推理卷积神经网络 (CGNet)，用于视网膜 OCTA 血管分割。具体来说，在粗阶段，CPA 和图推理网络 (GRN) 模块都集成在 U 形神经网络编码器和解码器之间，以获取血管置信图。在进入精细阶段后，这些置信图与原始图像和生成的精细图像图作为 3 通道图像连接起来，以细化视网膜微血管。最后，在细化阶段将精细图像和细化图像融合作为分割结果。通过不同的公共数据集进行实验验证了 CGNet 的有效性。结果表明，通过采用端到端的训练方案和集成的 CPA 和 GRN 模块，CGNet 在两个不同数据集的 ROC 曲线下面积 (AUC) 方面分别达到 94.29%和 85.62%，优于最先进的现有方法，在不同情况下具有提高的可操作性和降低的复杂性。代码可在 https://github.com/GE-123-cpu/CGnet-for-vessel-segmentation 上获得。
