Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.
Department of Endocrinology, Beijing Tongren Hospital, Capital Medical University, Beijing 100730, China.
Comput Math Methods Med. 2022 Aug 4;2022:4316507. doi: 10.1155/2022/4316507. eCollection 2022.
As an extension of optical coherence tomography (OCT), optical coherence tomographic angiography (OCTA) provides information on the blood flow status at the microlevel and is sensitive to changes in the fundus vessels. However, due to the distinct imaging mechanism of OCTA, existing models, which are primarily used for analyzing fundus images, do not work well on OCTA images. Effectively extracting and analyzing the information in OCTA images remains challenging. To this end, a deep learning framework that fuses multilevel information in OCTA images is proposed in this study. The effectiveness of the proposed model was demonstrated in the task of diabetic retinopathy (DR) classification.
First, a U-Net-based segmentation model was proposed to label the boundaries of large retinal vessels and the foveal avascular zone (FAZ) in OCTA images. Then, we designed an isolated concatenated block (ICB) structure to extract and fuse information from the original OCTA images and segmentation results at different fusion levels.
The experiments were conducted on 301 OCTA images. Of these images, 244 were labeled by ophthalmologists as normal images, and 57 were labeled as DR images. An accuracy of 93.1% and a mean intersection over union (mIOU) of 77.1% were achieved using the proposed large vessel and FAZ segmentation model. In the ablation experiment with 6-fold validation, the proposed deep learning framework that combines the proposed isolated and concatenated convolution process significantly improved the DR diagnosis accuracy. Moreover, inputting the merged images of the original OCTA images and segmentation results further improved the model performance. Finally, a DR diagnosis accuracy of 88.1% (95%CI ± 3.6%) and an area under the curve (AUC) of 0.92 were achieved using our proposed classification model, which significantly outperforms the state-of-the-art classification models. As a comparison, an accuracy of 83.7 (95%CI ± 1.5%) and AUC of 0.76 were obtained using EfficientNet. . The visualization results show that the FAZ and the vascular region close to the FAZ provide more information for the model than the farther surrounding area. Furthermore, this study demonstrates that a clinically sophisticated designed deep learning model is not only able to effectively assist in the diagnosis but also help to locate new indicators for certain illnesses.
作为光学相干断层扫描（OCT）的扩展，光相干断层扫描血管造影（OCTA）提供了微水平血流状态的信息，并且对眼底血管的变化敏感。然而，由于 OCTA 的独特成像机制，现有的主要用于分析眼底图像的模型在 OCTA 图像上效果不佳。有效地提取和分析 OCTA 图像中的信息仍然具有挑战性。为此，本研究提出了一种融合 OCTA 图像中多层次信息的深度学习框架。该模型在糖尿病视网膜病变（DR）分类任务中的有效性得到了验证。
首先，提出了一种基于 U-Net 的分割模型，用于标记 OCTA 图像中大血管和中心凹无血管区（FAZ）的边界。然后，我们设计了一种孤立串联块（ICB）结构，从原始 OCTA 图像和不同融合水平的分割结果中提取和融合信息。
实验在 301 张 OCTA 图像上进行。其中 244 张图像由眼科医生标记为正常图像，57 张图像标记为 DR 图像。使用所提出的大血管和 FAZ 分割模型，获得了 93.1%的准确率和 77.1%的平均交并比（mIOU）。在 6 倍验证的消融实验中，结合所提出的孤立和串联卷积过程的深度学习框架显著提高了 DR 诊断准确率。此外，输入原始 OCTA 图像和分割结果的合并图像进一步提高了模型性能。最后，使用我们提出的分类模型，DR 诊断准确率为 88.1%（95%CI ± 3.6%），曲线下面积（AUC）为 0.92，显著优于最新的分类模型。相比之下，使用 EfficientNet 获得的准确率为 83.7（95%CI ± 1.5%），AUC 为 0.76。可视化结果表明，FAZ 和靠近 FAZ 的血管区域为模型提供的信息多于更远的周围区域。此外，本研究表明，临床设计复杂的深度学习模型不仅能够有效地辅助诊断，还能够帮助定位某些疾病的新指标。
