Connectivity-based deep learning approach for segmentation of the epithelium in in vivo human esophageal OCT images.

Journal Article (Journal Article)

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 in vivo 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 in vivo human esophageal OCT images.

Full Text

Duke Authors

Cited Authors

  • Yang, Z; Soltanian-Zadeh, S; Chu, KK; Zhang, H; Moussa, L; Watts, AE; Shaheen, NJ; Wax, A; Farsiu, S

Published Date

  • October 2021

Published In

Volume / Issue

  • 12 / 10

Start / End Page

  • 6326 - 6340

PubMed ID

  • 34745740

Pubmed Central ID

  • PMC8547995

Electronic International Standard Serial Number (EISSN)

  • 2156-7085

International Standard Serial Number (ISSN)

  • 2156-7085

Digital Object Identifier (DOI)

  • 10.1364/boe.434775

Language

  • eng