Literature DB >> 35132449

Development and validation of a deep learning-based algorithm for colonoscopy quality assessment.

Yuan-Yen Chang1, Pai-Chi Li1, Ruey-Feng Chang1,2,3, Yu-Yao Chang4, Siou-Ping Huang5, Yang-Yuan Chen5, Wen-Yen Chang6, Hsu-Heng Yen7,8,9,10,11.   

Abstract

BACKGROUND: Quality indicators should be assessed and monitored to improve colonoscopy quality in clinical practice. Endoscopists must enter relevant information in the endoscopy reporting system to facilitate data collection, which may be inaccurate. The current study aimed to develop a full deep learning-based algorithm to identify and analyze intra-procedural colonoscopy quality indicators based on endoscopy images obtained during the procedure.
METHODS: A deep learning system for classifying colonoscopy images for quality assurance purposes was developed and its performance was assessed with an independent dataset. The system was utilized to analyze captured images and results were compared with those of real-world reports.
RESULTS: In total, 10,417 images from the hospital endoscopy database and 3157 from Hyper-Kvasir open dataset were utilized to develop the quality assurance algorithm. The overall accuracy of the algorithm was 96.72% and that of the independent test dataset was 94.71%. Moreover, 761 real-world reports and colonoscopy images were analyzed. The accuracy of electronic reports about cecal intubation rate was 99.34% and that of the algorithm was 98.95%. The agreement rate for the assessment of polypectomy rates using the electronic reports and the algorithm was 0.87 (95% confidence interval 0.83-0.90). A good correlation was found between the withdrawal time calculated using the algorithm and that entered by the physician (correlation coefficient r = 0.959, p < 0.0001).
CONCLUSION: We proposed a novel deep learning-based algorithm that used colonoscopy images for quality assurance purposes. This model can be used to automatically assess intra-procedural colonoscopy quality indicators in clinical practice.
© 2022. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

Entities:  

Keywords:  Colon; Colonoscopy quality; Deep learning

Mesh:

Year:  2022        PMID: 35132449     DOI: 10.1007/s00464-021-08993-y

Source DB:  PubMed          Journal:  Surg Endosc        ISSN: 0930-2794            Impact factor:   3.453


  8 in total

1.  Acute lower gastrointestinal bleeding during the COVID-19 pandemic - less is more!

Authors:  Erik A Holzwanger; Mohammad Bilal; Christopher G Stallwood; Mark J Sterling; Robert F Yacavone
Journal:  Endoscopy       Date:  2020-08-26       Impact factor: 10.093

2.  The SAGES MASTERS program presents the 10 seminal articles for Roux-en-Y gastric bypass.

Authors:  Saniea F Majid; Farah A Husain; Yong Choi; Sujata Gill; Bruce Schirmer; Matthew Kroh; Marina Kurian
Journal:  Surg Endosc       Date:  2021-12-02       Impact factor: 4.584

3.  Upper endoscopy photodocumentation quality evaluation with novel deep learning system.

Authors:  Yuan-Yen Chang; Hsu-Heng Yen; Pai-Chi Li; Ruey-Feng Chang; Chia Wei Yang; Yang-Yuan Chen; Wen-Yen Chang
Journal:  Dig Endosc       Date:  2021-12-01       Impact factor: 7.559

4.  Deep learning-based endoscopic anatomy classification: an accelerated approach for data preparation and model validation.

Authors:  Yuan-Yen Chang; Pai-Chi Li; Ruey-Feng Chang; Chih-Da Yao; Yang-Yuan Chen; Wen-Yen Chang; Hsu-Heng Yen
Journal:  Surg Endosc       Date:  2021-09-29       Impact factor: 3.453

Review 5.  Artificial intelligence (AI) real-time detection vs. routine colonoscopy for colorectal neoplasia: a meta-analysis and trial sequential analysis.

Authors:  Smit S Deliwala; Kewan Hamid; Mahmoud Barbarawi; Harini Lakshman; Yazan Zayed; Pujan Kandel; Srikanth Malladi; Adiraj Singh; Ghassan Bachuwa; Grigoriy E Gurvits; Saurabh Chawla
Journal:  Int J Colorectal Dis       Date:  2021-05-01       Impact factor: 2.571

6.  Robotic-assisted radical prostatectomy-impact of a mentorship program on oncological outcomes during the learning curve.

Authors:  James P C Ryan; Olwyn Lynch; Mark P Broe; Niall Swan; Diarmaid Moran; Barry McGuire; David Mulvin
Journal:  Ir J Med Sci       Date:  2021-02-27       Impact factor: 1.568

7.  A novel machine learning-based algorithm to identify and classify lesions and anatomical landmarks in colonoscopy images.

Authors:  Ying-Chun Jheng; Yen-Po Wang; Hung-En Lin; Kuang-Yi Sung; Yuan-Chia Chu; Huann-Sheng Wang; Jeng-Kai Jiang; Ming-Chih Hou; Fa-Yauh Lee; Ching-Liang Lu
Journal:  Surg Endosc       Date:  2021-02-16       Impact factor: 4.584

8.  Long-term effectiveness of faecal immunochemical test screening for proximal and distal colorectal cancers.

Authors:  Han-Mo Chiu; Grace Hsiao-Hsuan Jen; Ying-Wei Wang; Jean Ching-Yuan Fann; Chen-Yang Hsu; Ya-Chung Jeng; Amy Ming-Fang Yen; Sherry Yueh-Hsia Chiu; Sam Li-Sheng Chen; Wen-Feng Hsu; Yi-Chia Lee; Ming-Shiang Wu; Chien-Yuan Wu; Yann-Yuh Jou; Tony Hsiu-Hsi Chen
Journal:  Gut       Date:  2021-01-25       Impact factor: 23.059

  8 in total
  2 in total

1.  Forrest Classification for Bleeding Peptic Ulcer: A New Look at the Old Endoscopic Classification.

Authors:  Hsu-Heng Yen; Ping-Yu Wu; Tung-Lung Wu; Siou-Ping Huang; Yang-Yuan Chen; Mei-Fen Chen; Wen-Chen Lin; Cheng-Lun Tsai; Kang-Ping Lin
Journal:  Diagnostics (Basel)       Date:  2022-04-24

2.  Machine-Learning Algorithm for Predicting Fatty Liver Disease in a Taiwanese Population.

Authors:  Yang-Yuan Chen; Chun-Yu Lin; Hsu-Heng Yen; Pei-Yuan Su; Ya-Huei Zeng; Siou-Ping Huang; I-Ling Liu
Journal:  J Pers Med       Date:  2022-06-23
  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.