Intraretinal Layer Segmentation Using Cascaded Compressed U-Nets.
Intraretinal Layer Segmentation Using Cascaded Compressed U-Nets.
复制标题
DOI：
10.3390/jimaging8050139
复制
发表时间：
2022-05-17
影响因子：
3.2
通讯作者：
中科院分区：
文献类型：
--
作者：
量化中枢神经系统疾病（如多发性硬化症、阿尔茨海默氏痴呆症或帕金森病）的神经变性和神经炎症的可靠生物标志物是一个未满足的临床需求。黄斑光学相干断层扫描（OCT）图像上的视网膜内层厚度是一种有前途的无创生物标志物，可以近细胞分辨率查询神经视网膜结构。然而，变化通常是微妙的，而组织梯度可能很弱，使得视网膜内分割成为一项具有挑战性的任务。一种不需要或最少需要人工校正的强大而有效的方法是促进可靠和可重复的研究以及临床应用的未满足需求。在这里，我们提出并验证了一个用于视网膜内层分割的级联两阶段网络，两个网络都是U-Net （CCU-INSEG）的压缩版本。第一个网络负责从OCT b扫描中分割视网膜组织。第二网络以高保真度划分了8个网络层。在后处理阶段，我们引入了基于拉普拉斯的离群点检测，并采用自适应非线性插值填充层表面孔。此外，我们提出了一个加权版本的焦点损失，以尽量减少训练数据中的前景和背景像素不平衡。我们使用来自自身免疫性视神经病变（即多发性硬化症）患者和健康对照者的17,458次b扫描来训练我们的方法。与手动分割相比，体素比较产生的平均绝对误差为2.3 μm，在相同的数据集上优于当前最先进的方法。当使用相同的金标准分割方法时，与外部青光眼数据进行体素比较的平均绝对误差为2.6 μm，而在外部分割数据集上的平均绝对误差为3.7 μm。在严重视神经萎缩患者的扫描中，3.5%的b扫描分割结果被经验丰富的评分者拒绝，而使用基于图的参考方法分割的b扫描结果为41.4%。验证结果表明，该方法可以鲁棒地分割具有严重神经视网膜病变的眼睛的黄斑扫描。
Reliable biomarkers quantifying neurodegeneration and neuroinflammation in central nervous system disorders such as Multiple Sclerosis, Alzheimer’s dementia or Parkinson’s disease are an unmet clinical need. Intraretinal layer thicknesses on macular optical coherence tomography (OCT) images are promising noninvasive biomarkers querying neuroretinal structures with near cellular resolution. However, changes are typically subtle, while tissue gradients can be weak, making intraretinal segmentation a challenging task. A robust and efficient method that requires no or minimal manual correction is an unmet need to foster reliable and reproducible research as well as clinical application. Here, we propose and validate a cascaded two-stage network for intraretinal layer segmentation, with both networks being compressed versions of U-Net (CCU-INSEG). The first network is responsible for retinal tissue segmentation from OCT B-scans. The second network segments eight intraretinal layers with high fidelity. At the post-processing stage, we introduce Laplacian-based outlier detection with layer surface hole filling by adaptive non-linear interpolation. Additionally, we propose a weighted version of focal loss to minimize the foreground–background pixel imbalance in the training data. We train our method using 17,458 B-scans from patients with autoimmune optic neuropathies, i.e., multiple sclerosis, and healthy controls. Voxel-wise comparison against manual segmentation produces a mean absolute error of 2.3 μm, outperforming current state-of-the-art methods on the same data set. Voxel-wise comparison against external glaucoma data leads to a mean absolute error of 2.6 μm when using the same gold standard segmentation approach, and 3.7 μm mean absolute error in an externally segmented data set. In scans from patients with severe optic atrophy, 3.5% of B-scan segmentation results were rejected by an experienced grader, whereas this was the case in 41.4% of B-scans segmented with a graph-based reference method. The validation results suggest that the proposed method can robustly segment macular scans from eyes with even severe neuroretinal changes.