Multiple surface segmentation using convolution neural nets: application to retinal layer segmentation in OCT images
Multiple surface segmentation using convolution neural nets: application to retinal layer segmentation in OCT images
复制标题
DOI：
10.1364/boe.9.004509
复制
发表时间：
2018-09-01
影响因子：
3.4
通讯作者：
Wu, Xiaodong
中科院分区：
文献类型：
--
作者：
Shah, Abhay;Zhou, Leixin;Wu, Xiaodong
在许多生物医学应用中，物体边界或表面的自动分割对于定量图像分析至关重要。例如，光学相干断层扫描（OCT）图像中的视网膜表面在视网膜疾病的诊断和治疗中起着至关重要的作用。近年来，基于图的曲面分割和轮廓建模得到了发展和优化，可用于各种曲面分割任务。这些方法需要经过专业设计的特定于应用程序的转换，包括成本函数、约束和模型参数。然而，基于深度学习的方法能够直接从训练数据中学习模型和特征。在本文中，我们提出了一种基于卷积神经网络（CNN）的框架来同时分割多个表面。我们演示了该方法的应用，通过训练单个CNN来分割两种类型OCT图像中的三个视网膜表面：正常视网膜和中度年龄相关性黄斑变性（AMD）视网膜。训练后的网络在一次扫描中直接推断出每次b扫描的分割。该方法在50个视网膜OCT体积（3000个b扫描）上进行了验证，其中包括25个正常和25个中度AMD受试者。我们的实验表明，与凸先验（OSCS）的最佳表面分割方法和两种基于深度学习的UNET方法相比，两种类型的数据的分割精度都有统计学上的显著提高。对于所提出的方法，分割整个OCT体积（每个由60个b扫描组成）的平均计算时间为12.3秒，与基于图的最优表面分割和基于UNET的方法相比，显示出更低的计算成本和更高的性能。(C) 2018年美国光学学会根据OSA开放获取出版协议的条款
Automated segmentation of object boundaries or surfaces is crucial for quantitative image analysis in numerous biomedical applications. For example, retinal surfaces in optical coherence tomography (OCT) images play a vital role in the diagnosis and management of retinal diseases. Recently, graph based surface segmentation and contour modeling have been developed and optimized for various surface segmentation tasks. These methods require expertly designed, application specific transforms, including cost functions, constraints and model parameters. However, deep learning based methods are able to directly learn the model and features from training data. In this paper, we propose a convolutional neural network (CNN) based framework to segment multiple surfaces simultaneously. We demonstrate the application of the proposed method by training a single CNN to segment three retinal surfaces in two types of OCT images normal retinas and retinas affected by intermediate age-related macular degeneration (AMD). The trained network directly infers the segmentations for each B-scan in one pass. The proposed method was validated on 50 retinal OCT volumes (3000 B-scans) including 25 normal and 25 intermediate AMD subjects. Our experiment demonstrated statistically significant improvement of segmentation accuracy compared to the optimal surface segmentation method with convex priors (OSCS) and two deep learning based UNET methods for both types of data. The average computation time for segmenting an entire OCT volume (consisting of 60 B-scans each) for the proposed method was 12.3 seconds, demonstrating low computation costs and higher performance compared to the graph based optimal surface segmentation and UNET based methods. (C) 2018 Optical Society of America under the terms of the OSA Open Access Publishing Agreement