School of Automation Science and Electrical Engineering, Beihang University (BUAA), Beijing, 100191, China.
School of Automation Science and Electrical Engineering, Beihang University (BUAA), Beijing, 100191, China; School of Electrical Engineering and Intelligentization, Dongguan University of Technology, Dongguan, 523808, China.
Comput Biol Med. 2021 Sep;136:104727. doi: 10.1016/j.compbiomed.2021.104727. Epub 2021 Aug 4.
BACKGROUND: In anti-vascular endothelial growth factor (anti-VEGF) therapy, an accurate estimation of multi-class retinal fluid (MRF) is required for the activity prescription and intravitreal dose. This study proposes an end-to-end deep learning-based retinal fluids segmentation network (RFS-Net) to segment and recognize three MRF lesion manifestations, namely, intraretinal fluid (IRF), subretinal fluid (SRF), and pigment epithelial detachment (PED), from multi-vendor optical coherence tomography (OCT) imagery. The proposed image analysis tool will optimize anti-VEGF therapy and contribute to reducing the inter- and intra-observer variability. METHOD: The proposed RFS-Net architecture integrates the atrous spatial pyramid pooling (ASPP), residual, and inception modules in the encoder path to learn better features and conserve more global information for precise segmentation and characterization of MRF lesions. The RFS-Net model is trained and validated using OCT scans from multiple vendors (Topcon, Cirrus, Spectralis), collected from three publicly available datasets. The first dataset consisted of OCT volumes obtained from 112 subjects (a total of 11,334 B-scans) is used for both training and evaluation purposes. Moreover, the remaining two datasets are only used for evaluation purposes to check the trained RFS-Net's generalizability on unseen OCT scans. The two evaluation datasets contain a total of 1572 OCT B-scans from 1255 subjects. The performance of the proposed RFS-Net model is assessed through various evaluation metrics. RESULTS: The proposed RFS-Net model achieved the mean F scores of 0.762, 0.796, and 0.805 for segmenting IRF, SRF, and PED. Moreover, with the automated segmentation of the three retinal manifestations, the RFS-Net brings a considerable gain in efficiency compared to the tedious and demanding manual segmentation procedure of the MRF. CONCLUSIONS: Our proposed RFS-Net is a potential diagnostic tool for the automatic segmentation of MRF (IRF, SRF, and PED) lesions. It is expected to strengthen the inter-observer agreement, and standardization of dosimetry is envisaged as a result.
背景：在抗血管内皮生长因子（anti-VEGF）治疗中，需要准确估计多类视网膜液（MRF），以确定治疗活动和玻璃体内剂量。本研究提出了一种基于端到端深度学习的视网膜液分割网络（RFS-Net），用于从多供应商光学相干断层扫描（OCT）图像中分割和识别三种 MRF 病变表现，即视网膜内液（IRF）、视网膜下液（SRF）和色素上皮脱离（PED）。所提出的图像分析工具将优化抗 VEGF 治疗，并有助于减少观察者间和观察者内的变异性。
方法：所提出的 RFS-Net 架构在编码器路径中集成了空洞空间金字塔池化（ASPP）、残差和 inception 模块，以学习更好的特征，并保留更多的全局信息，从而更精确地分割和描述 MRF 病变。该 RFS-Net 模型使用来自多个供应商（Topcon、Cirrus、Spectralis）的 OCT 扫描进行训练和验证，这些扫描来自三个公开可用的数据集。第一个数据集由来自 112 个受试者（总共 11334 个 B 扫描）的 OCT 体积组成，用于训练和评估目的。此外，其余两个数据集仅用于评估目的，以检查在未见的 OCT 扫描上训练的 RFS-Net 的泛化能力。这两个评估数据集共包含来自 1255 个受试者的 1572 个 OCT B 扫描。通过各种评估指标评估所提出的 RFS-Net 模型的性能。
结果：所提出的 RFS-Net 模型在分割 IRF、SRF 和 PED 方面的平均 F 分数分别为 0.762、0.796 和 0.805。此外，通过对三种视网膜表现的自动分割，与 MRF 的繁琐和要求高的手动分割过程相比，RFS-Net 带来了相当大的效率提高。
结论：我们提出的 RFS-Net 是一种用于自动分割 MRF（IRF、SRF 和 PED）病变的潜在诊断工具。预计它将增强观察者间的一致性，并期望实现剂量学的标准化。
Comput Methods Programs Biomed. 2020-10
Transl Vis Sci Technol. 2020-10-8
Transl Vis Sci Technol. 2025-4-1
Biomed Opt Express. 2023-6-30
Clin Exp Ophthalmol. 2023-11
Bioengineering (Basel). 2023-3-24
Zotero 插件