Yang Ziyun, Soltanian-Zadeh Somayyeh, Chu Kengyeh K, Zhang Haoran, Moussa Lama, Watts Ariel E, Shaheen Nicholas J, Wax Adam, Farsiu Sina
Department of Biomedical Engineering, Duke University, Durham, NC 27708, USA.
Center for Esophageal Diseases and Swallowing, University of North Carolina, Chapel Hill, NC 27599, USA.
Biomed Opt Express. 2021 Sep 15;12(10):6326-6340. doi: 10.1364/BOE.434775. eCollection 2021 Oct 1.
Optical coherence tomography (OCT) is used for diagnosis of esophageal diseases such as Barrett's esophagus. Given the large volume of OCT data acquired, automated analysis is needed. Here we propose a bilateral connectivity-based neural network for human esophageal OCT layer segmentation. Our method, connectivity-based CE-Net (Bicon-CE), defines layer segmentation as a combination of pixel connectivity modeling and pixel-wise tissue classification. Bicon-CE outperformed other widely used neural networks and reduced common topological prediction issues in tissues from healthy patients and from patients with Barrett's esophagus. This is the first end-to-end learning method developed for automatic segmentation of the epithelium in human esophageal OCT images.
光学相干断层扫描（OCT）用于诊断诸如巴雷特食管等食管疾病。鉴于获取的OCT数据量巨大，需要进行自动分析。在此，我们提出一种基于双边连通性的神经网络用于人类食管OCT层分割。我们的方法，即基于连通性的CE-Net（Bicon-CE），将层分割定义为像素连通性建模和逐像素组织分类的结合。Bicon-CE优于其他广泛使用的神经网络，并减少了健康患者和巴雷特食管患者组织中常见的拓扑预测问题。这是首个为自动分割人类食管OCT图像中的上皮而开发的端到端学习方法。
