IEEE Trans Cybern. 2020 Jul;50(7):3358-3366. doi: 10.1109/TCYB.2019.2897162. Epub 2019 Feb 15.
Irreversible visual impairment is often caused by primary angle-closure glaucoma, which could be detected via anterior segment optical coherence tomography (AS-OCT). In this paper, an automated system based on deep learning is presented for angle-closure detection in AS-OCT images. Our system learns a discriminative representation from training data that captures subtle visual cues not modeled by handcrafted features. A multilevel deep network is proposed to formulate this learning, which utilizes three particular AS-OCT regions based on clinical priors: 1) the global anterior segment structure; 2) local iris region; and 3) anterior chamber angle (ACA) patch. In our method, a sliding window-based detector is designed to localize the ACA region, which addresses ACA detection as a regression task. Then, three parallel subnetworks are applied to extract AS-OCT representations for the global image and at clinically relevant local regions. Finally, the extracted deep features of these subnetworks are concatenated into one fully connected layer to predict the angle-closure detection result. In the experiments, our system is shown to surpass previous detection methods and other deep learning systems on two clinical AS-OCT datasets.
不可逆性视力损害通常由原发性闭角型青光眼引起，可以通过眼前节光学相干断层扫描（AS-OCT）进行检测。本文提出了一种基于深度学习的自动系统，用于在 AS-OCT 图像中进行闭角检测。我们的系统从训练数据中学习到一种有判别力的表示，该表示捕捉到了手工特征无法建模的细微视觉线索。提出了一种多层次的深度网络来制定这种学习，该网络利用了基于临床先验的三个特定的 AS-OCT 区域：1）全局前段结构；2）局部虹膜区域；和 3）前房角（ACA）斑块。在我们的方法中，设计了一个基于滑动窗口的检测器来定位 ACA 区域，将 ACA 检测作为回归任务来解决。然后，三个并行的子网应用于提取全局图像和临床相关局部区域的 AS-OCT 表示。最后，将这些子网的提取的深度特征串联成一个全连接层，以预测闭角检测结果。在实验中，我们的系统在两个临床 AS-OCT 数据集上的表现优于以前的检测方法和其他深度学习系统。
