Two-stage deep-learning-based colonoscopy polyp detection incorporating fisheye and reflection correction.

Journal: Journal of gastroenterology and hepatology
Published Date: Jan 15, 2024

Abstract

BACKGROUND AND AIM: Colonoscopy is a useful method for the diagnosis and management of colorectal diseases. Many computer-aided systems have been developed to assist clinicians in detecting colorectal lesions by analyzing colonoscopy images. However, fisheye-lens distortion and light reflection in colonoscopy images can substantially affect the clarity of these images and their utility in detecting polyps. This study proposed a two-stage deep-learning model to correct distortion and reflections in colonoscopy images and thus facilitate polyp detection.

Authors

  • Chen-Ming Hsu
    Division of Gastroenterology, Department of Gastroenterology and Hepatology, Chang Gung Memorial Hospital, Taoyuan, Taiwan.
  • Tsung-Hsing Chen
    Division of Gastroenterology, Department of Gastroenterology and Hepatology, Chang Gung Memorial Hospital, Taoyuan, Taiwan; Chang Gung University College of Medicine, Taoyuan, Taiwan; GraduateInstitute of Clinical Medical Sciences, Chang Gung University, Taoyuan, Taiwan.
  • Chien-Chang Hsu
    Department of Computer Science and Information Engineering, Fu-Jen Catholic University, 510 Chung Cheng Rd., Hsinchuang Dist., New Taipei City 242, Taiwan.
  • Che-Hao Wu
    Department of Computer Science and Information Engineering, Fu Jen Catholic University, Taipei, Taiwan.
  • Chun-Jung Lin
    Department of Gastroenterology and Hepatology, Chang Gung Memorial Hospital Linkou Main Branch, Taoyuan, Taiwan.
  • Puo-Hsien Le
    Department of Gastroenterology and Hepatology, Chang Gung Memorial Hospital, Linkou Branch, Taoyuan, Taiwan.
  • Cheng-Yu Lin
    Department of Gastroenterology and Hepatology, Chang Gung Memorial Hospital Linkou Main Branch, Taoyuan, Taiwan.
  • Tony Kuo
    Department of Electrical and Computer Engineering, The University of Auckland, Auckland, New Zealand.

Keywords

External Resources

Popular Topics
Recent Journals