A Learning Based Microultrasound System for the Detection of Inflammation of the Gastrointestinal Tract

Shufan Yang, Christina Lemke, Benjamin F. Cox, Ian P. Newton, Inke Näthke, Sandy Cochran

Research output: Contribution to journalArticlepeer-review

11 Downloads (Pure)

Abstract

Inflammation of the gastrointestinal (GI) tract accompanies several diseases, including Crohn’s disease. Currently, video capsule endoscopy and deep bowel enteroscopy are the main means for direct visualisation of the bowel surface. However, the use of optical imaging limits visualisation to the luminal surface only, which makes early-stage diagnosis difficult. In this study, we propose a learning enabled microultrasound (μUS) system that aims to classify inflamed and non-inflamed bowel tissues. μUS images of the caecum, small bowel and colon were obtained from mice treated with agents to induce inflammation. Those images were then used to train three deep learning networks and to provide a ground truth of inflammation status. The classification accuracy was evaluated using 10-fold evaluation and additional B-scan images. Our deep learning approach allowed robust differentiation between healthy tissue and tissue with early signs of inflammation that is not detectable by current endoscopic methods or by human inspection of the μUS images. The methods may be a foundation for future early GI disease diagnosis and enhanced management with computer-aided imaging.
Original languageEnglish
Number of pages10
JournalIEEE Transactions on Medical Imaging
Early online date3 Sep 2020
DOIs
Publication statusE-pub ahead of print - 3 Sep 2020

Keywords

  • Computer-aided detection and diagnosis
  • Gastrointestinal tract
  • Ultrasound
  • Neural Network

Fingerprint Dive into the research topics of 'A Learning Based Microultrasound System for the Detection of Inflammation of the Gastrointestinal Tract'. Together they form a unique fingerprint.

Cite this