Computer-Aided Analysis of Gland-Like Subsurface Hyposcattering Structures in Barrett’s Esophagus Using Optical Coherence Tomography

Abstract

(1) Background: Barrett’s esophagus (BE) is a complication of chronic gastroesophageal reflux disease and is a precursor to esophageal adenocarcinoma. The clinical implication of subsurface glandular structures of Barrett’s esophagus is not well understood. Optical coherence tomography (OCT), also known as volumetric laser endomicroscopy (VLE), can assess subsurface glandular structures, which appear as subsurface hyposcattering structures (SHSs). The aim of this study is to develop a computer-aided algorithm and apply it to investigate the characteristics of SHSs in BE using clinical VLE data; (2) Methods: SHSs were identified with an initial detection followed by machine learning. Comprehensive SHS characteristics including the number, volume, depth, size and shape were quantified. Clinical VLE datasets collected from 35 patients with a history of dysplasia undergoing BE surveillance were analyzed to study the general SHS distribution and characteristics in BE. A subset of radiofrequency ablation (RFA) patient data were further analyzed to investigate the pre-RFA SHS characteristics and post-RFA treatment response; (3) Results: SHSs in the BE region were significantly shallower, more vertical, less eccentric, and more regular, as compared with squamous SHSs. SHSs in the BE region which became neosquamous epithelium after RFA were shallower than those in the regions that remained BE. Pre-ablation squamous SHSs with higher eccentricity correlated strongly with larger reduction of post-ablation BE length for less elderly patients; (4) Conclusions: The computer algorithm is potentially a valuable tool for studying the roles of SHSs in BE.

Document Details

Document Type
Pub Defense Publication
Publication Date
Nov 28, 2018
Source ID
10.3390/app8122420

Entities

People

  • Hiroshi Mashimo
  • Hsiang-chieh Lee
  • James Fujimoto
  • Kaicheng Liang
  • Marisa Figueiredo
  • Osman Ahsen
  • Qin Huang
  • Zhao Wang

Organizations

  • Air Force Office of Scientific Research
  • Foundation for the National Institutes of Health

Tags

Readers

  • Aerospace Engineering
  • Analytical Chemistry
  • Oncology and Biomarker-Based Cancer Detection.

Technology Areas

  • AI & ML
  • Directed Energy