论文标题

在OCT中自动分割和可视化脉络膜,知识注入深度学习

Automatic Segmentation and Visualization of Choroid in OCT with Knowledge Infused Deep Learning

论文作者

Zhang, Huihong, Yang, Jianlong, Zhou, Kang, Li, Fei, Hu, Yan, Zhao, Yitian, Zheng, Ce, Zhang, Xiulan, Liu, Jiang

论文摘要

脉络膜为外视网膜提供氧气和滋养,因此与各种眼部疾病的病理有关。光学相干断层扫描(OCT)在可视化和量化体内的脉络膜方面是有利的。 (1)OCT中脉络膜的下边界(脉络膜 - 斯莱拉界面)是模糊的,这使自动分割变得困难和不准确。 (2)脉络膜的可视化受到内部视网膜浅层层的船只阴影的阻碍。在本文中,我们建议将医学和成像的先验知识与深度学习结合在一起,以解决这两个问题。我们提出了一个用于脉络膜分割的生物标志物注入全球到本地网络。它利用脉络膜厚度(临床上的主要生物标志物),以提高分割精度的限制。我们还在脉络膜分段中设计了一种全球到本地的策略:全球模块用于同时抑制过度拟合和提供全球结构信息的所有视网膜和脉络膜层,然后使用局部模块通过生物标志物输注来完善细分。为了消除视网膜的阴影,我们提出了一条管道,该管道首先使用解剖学和OCT成像知识使用其在视网膜色素上皮层上的投影来定位阴影,然后在阴影位置的脉络膜脉管系统中的内容物,预测具有边缘到边缘性的生成的生产性的eversative Inversarial Interpaintail网络。实验表明,我们的方法在分割和阴影消除任务上都优于现有方法。我们在临床前瞻性研究中进一步应用了所提出的方法,以通过检测与眼内压力升高有关的脉络膜的结构和血管变化来理解青光眼的病理。

The choroid provides oxygen and nourishment to the outer retina thus is related to the pathology of various ocular diseases. Optical coherence tomography (OCT) is advantageous in visualizing and quantifying the choroid in vivo. (1) The lower boundary of the choroid (choroid-sclera interface) in OCT is fuzzy, which makes the automatic segmentation difficult and inaccurate. (2) The visualization of the choroid is hindered by the vessel shadows from the superficial layers of the inner retina. In this paper, we propose to incorporate medical and imaging prior knowledge with deep learning to address these two problems. We propose a biomarker infused global-to-local network for the choroid segmentation. It leverages the choroidal thickness, a primary biomarker in clinic, as a constraint to improve the segmentation accuracy. We also design a global-to-local strategy in the choroid segmentation: a global module is used to segment all the retinal and choroidal layers simultaneously for suppressing overfitting and providing global structure information, then a local module is used to refine the segmentation with the biomarker infusion. To eliminate the retinal vessel shadows, we propose a pipeline that firstly use anatomical and OCT imaging knowledge to locate the shadows using their projection on the retinal pigment epithelium layer, then the contents of the choroidal vasculature at the shadow locations are predicted with an edge-to-texture generative adversarial inpainting network. The experiments show our method outperforms the existing methods on both the segmentation and shadow elimination tasks. We further apply the proposed method in a clinical prospective study for understanding the pathology of glaucoma by detecting the structure and vascular changes of the choroid related to the elevation of intra-ocular pressure.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源