Two‐stage deep‐learning‐based colonoscopy polyp detection incorporating fisheye and reflection correction
Journal of Gastroenterology and Hepatology · 2024-04 · 39 (4) · 733-739
DOI: 10.1111/jgh.16470 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Gastroenterology and Hepatology, online erschienen am 15.01.2024. Verfasst von Chen-Ming Hsu und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Gastroenterology and Hepatology, Chang Gung Memorial Hospital Taoyuan Branch, Taoyuan, Taiwan. Hauptthemen laut MEDLINE: Colonic Polyps, Deep Learning, Colorectal Neoplasms. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: National Science and Technology Council.
Abstract (Originalsprache)
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.
Methods
Images were collected from the PolypSet dataset, the Kvasir‐SEG dataset, and one medical center's patient archiving and communication system. The training, validation, and testing datasets comprised 808, 202, and 1100 images, respectively. The first stage involved the correction of fisheye‐related distortion in colonoscopy images and polyp detection, which was performed using a convolutional neural network. The second stage involved the use of generative and adversarial networks for correcting reflective colonoscopy images before the convolutional neural network was used for polyp detection.
Results
The model had higher accuracy when it was validated using corrected images than when it was validated using uncorrected images (96.8% vs 90.8%, P < 0.001). The model's accuracy in detecting polyps in the Kvasir‐SEG dataset reached 96%, and the area under the receiver operating characteristic curve was 0.94.
Conclusion
The proposed model can facilitate the clinical diagnosis of colorectal polyps and improve the quality of colonoscopy.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Gastroenterology and Hepatology, Chang Gung Memorial Hospital Taoyuan Branch, Taoyuan, Taiwan.
- Department of Gastroenterology and Hepatology, Chang Gung Memorial Hospital Linkou Main Branch, Taoyuan, Taiwan.
- Chang Gung University College of Medicine, Taoyuan, Taiwan.
- Department of Computer Science and Information Engineering, Fu Jen Catholic University, Taipei, Taiwan.
ORCID-Profile: Chen-Ming Hsu
Förderung
- National Science and Technology Council
Zitieren
APA
Hsu, C. M., Chen, T. H., Hsu, C. C., Wu, C. H., Lin, C. J., Le, P. H., Lin, C. Y., & Kuo, T. (2024). Two‐stage deep‐learning‐based colonoscopy polyp detection incorporating fisheye and reflection correction. Journal of Gastroenterology and Hepatology, 39(4), 733-739. https://doi.org/10.1111/jgh.16470
Vancouver
Hsu CM, Chen TH, Hsu CC, Wu CH, Lin CJ, Le PH, et al. Two‐stage deep‐learning‐based colonoscopy polyp detection incorporating fisheye and reflection correction. Journal of Gastroenterology and Hepatology. 2024;39(4):733-739. doi:10.1111/jgh.16470
BibTeX
@article{Hsu2024,
author = {Hsu, Chen-Ming and Chen, Tsung-Hsing and Hsu, Chien-Chang and Wu, Che-Hao and Lin, Chun-Jung and Le, Puo-Hsien and Lin, Cheng-Yu and Kuo, Tony},
title = {Two‐stage deep‐learning‐based colonoscopy polyp detection incorporating fisheye and reflection correction},
journal = {Journal of Gastroenterology and Hepatology},
year = {2024},
volume = {39},
number = {4},
pages = {733--739},
doi = {10.1111/jgh.16470}
}
EUVIMED