Artificial intelligence in capsule endoscopy: A practical guide to its past and future challenges

Sang Hoon Kim, Yun Jeong Lim

Research output: Contribution to journalReview articlepeer-review

28 Scopus citations

Abstract

Artificial intelligence (AI) has revolutionized the medical diagnostic process of various diseases. Since the manual reading of capsule endoscopy videos is a time-intensive, error-prone process, computerized algorithms have been introduced to automate this process. Over the past decade, the evolution of convolutional neural network (CNN) enabled AI to detect multiple lesions simultaneously with increasing accuracy and sensitivity. Difficulty in validating CNN performance and unique characteristics of capsule endoscopy images make computer-aided reading systems in capsule endoscopy still on a preclinical level. Although AI technology can be used as an auxiliary second observer in capsule endoscopy, it is expected that in the near future, it will effectively reduce the reading time and ultimately become an independent, integrated reading system.

Original languageEnglish
Article number1722
JournalDiagnostics
Volume11
Issue number9
DOIs
StatePublished - Sep 2021

Keywords

  • Artificial intelligence
  • Computer-aided reading
  • Convolutional neural network
  • Small bowel imaging
  • Wireless capsule endoscopy

Fingerprint

Dive into the research topics of 'Artificial intelligence in capsule endoscopy: A practical guide to its past and future challenges'. Together they form a unique fingerprint.

Cite this