学习校正光学相干断层扫描（OCT）中的轴向运动以进行三维视网膜成像。
LEARNING TO CORRECT AXIAL MOTION IN OCT FOR 3D RETINAL IMAGING.
作者信息
Wang Yiqian, Warter Alexandra, Cavichini-Cordeiro Melina, Freeman William R, Bartsch Dirk-Uwe G, Nguyen Truong Q, An Cheolhong
机构信息
Department of Electrical and Computer Engineering, University of California, San Diego.
Jacobs Retina Center, Shiley Eye Institute, La Jolla, California, USA.
出版信息
Proc Int Conf Image Proc. 2021 Sep;2021:126-130. doi: 10.1109/icip42928.2021.9506620. Epub 2021 Aug 23.
Optical Coherence Tomography (OCT) is a powerful technique for non-invasive 3D imaging of biological tissues at high resolution that has revolutionized retinal imaging. A major challenge in OCT imaging is the motion artifacts introduced by involuntary eye movements. In this paper, we propose a convolutional neural network that learns to correct axial motion in OCT based on a single volumetric scan. The proposed method is able to correct large motion, while preserving the overall curvature of the retina. The experimental results show significant improvements in visual quality as well as overall error compared to the conventional methods in both normal and disease cases.
光学相干断层扫描（OCT）是一种强大的技术，可对生物组织进行高分辨率的非侵入性三维成像，它彻底改变了视网膜成像。OCT成像中的一个主要挑战是由不自主眼球运动引入的运动伪影。在本文中，我们提出了一种卷积神经网络，该网络基于单次容积扫描学习校正OCT中的轴向运动。所提出的方法能够校正较大的运动，同时保留视网膜的整体曲率。实验结果表明，与传统方法相比，在正常和疾病情况下，视觉质量以及总体误差都有显著改善。
Zotero 插件