Artificial Intelligence-Based Colorectal Polyp Histology Prediction by Using Narrow-Band Image-Magnifying Colonoscopy
1
조회
0
다운로드
5
인용
0
참고문헌
키워드
초록
Background/Aims: We have been developing artificial intelligence based polyp histology prediction (AIPHP) method to classifyNarrow Band Imaging (NBI) magnifying colonoscopy images to predict the hyperplastic or neoplastic histology of polyps. Our aimwas to analyze the accuracy of AIPHP and narrow-band imaging international colorectal endoscopic (NICE) classification basedhistology predictions and also to compare the results of the two methods. Methods: We studied 373 colorectal polyp samples taken by polypectomy from 279 patients. The documented NBI still imageswere analyzed by the AIPHP method and by the NICE classification parallel. The AIPHP software was created by machine learningmethod. The software measures five geometrical and color features on the endoscopic image. Results: The accuracy of AIPHP was 86.6% (323/373) in total of polyps. We compared the AIPHP accuracy results for diminutiveand non-diminutive polyps (82.1% vs. 92.2%; p=0.0032). The accuracy of the hyperplastic histology prediction was significantlybetter by NICE compared to AIPHP method both in the diminutive polyps (n=207) (95.2% vs. 82.1%) (p<0.001) and also in allevaluated polyps (n=373) (97.1% vs. 86.6%) (p<0.001)Conclusions: Our artificial intelligence based polyp histology prediction software could predict histology with high accuracy only inthe large size polyp subgroup.
Abstract
Background/Aims: We have been developing artificial intelligence based polyp histology prediction (AIPHP) method to classifyNarrow Band Imaging (NBI) magnifying colonoscopy images to predict the hyperplastic or neoplastic histology of polyps. Our aimwas to analyze the accuracy of AIPHP and narrow-band imaging international colorectal endoscopic (NICE) classification basedhistology predictions and also to compare the results of the two methods. Methods: We studied 373 colorectal polyp samples taken by polypectomy from 279 patients. The documented NBI still imageswere analyzed by the AIPHP method and by the NICE classification parallel. The AIPHP software was created by machine learningmethod. The software measures five geometrical and color features on the endoscopic image. Results: The accuracy of AIPHP was 86.6% (323/373) in total of polyps. We compared the AIPHP accuracy results for diminutiveand non-diminutive polyps (82.1% vs. 92.2%; p=0.0032). The accuracy of the hyperplastic histology prediction was significantlybetter by NICE compared to AIPHP method both in the diminutive polyps (n=207) (95.2% vs. 82.1%) (p<0.001) and also in allevaluated polyps (n=373) (97.1% vs. 86.6%) (p<0.001)Conclusions: Our artificial intelligence based polyp histology prediction software could predict histology with high accuracy only inthe large size polyp subgroup.
참고문헌 (27)
- McGill SK, "Narrow band imaging to differentiate neoplastic and non-neoplastic colorectal polyps in real time : a meta-analysis of diagnostic operating characteristics", Gut, 62, pp.1704~1713 (2013)
- Ignjatovic A, "Optical diagnosis of small colorectal polyps at routine colonoscopy(Detect InSpect ChAracterise Resect and Discard; DISCARD trial) : a prospective cohort study", Lancet Oncol, 10, pp.1171~1178 (2009)
- Ignjatovic A, "Development and validation of a training module on the use of narrow-band imaging in differentiation of small adenomas from hyperplastic colorectal polyps", Gastrointest Endosc, 73, pp.128~133 (2011)
- Hewett DG, "Validation of a simple classification system for endoscopic diagnosis of small colorectal polyps using narrow-band imaging", Gastroenterology, 143, pp.599~607 (2012)
- Hewett DG, "Leaving distal colorectal hyperplastic polyps in place can be achieved with high accuracy by using narrow-band imaging : an observational study", Gastrointest Endosc, 76, pp.374~380 (2012)
- Rastogi A, "Impact of a computer-based teaching module on characterization of diminutive colon polyps by using narrow-band imaging by non-experts in academic and community practice : a video-based study", Gastrointest Endosc, 79, pp.390~398 (2014)
- van den Broek FJC, "Systematic review of narrow-band imaging for the detection and differentiation of neoplastic and nonneoplastic lesions in the colon(with videos)", Gastrointest Endosc, 69, pp.124~135 (2009)
- Ahadi M, "The 2019 World health organization classification of appendiceal, colorectal and anal canal tumours : an update and critical assessment", Pathology, 53, pp.454~461 (2021)
- Horváth A, "Preprocessing endoscopic images of colorectal polyps", Acta Technica Jaurinensis, 9, pp.65~82 (2016)
- Neumann H, "Learning curve of virtual chromoendoscopy for the prediction of hyperplastic and adenomatous colorectal lesions : a prospective 2-center study", Gastrointest Endosc, 78, pp.115~120 (2013)
- Tischendorf JJW, "Computer-aided classification of colorectal polyps based on vascular patterns : a pilot study", Endoscopy, 42, pp.203~207 (2010)
- Gross S, "Computer-based classification of small colorectal polyps by using narrow-band imaging with optical magnification", Gastrointest Endosc, 74, pp.1354~1359 (2011)
- Takemura Y, "Quantitative analysis and development of a computer-aided system for identification of regular pit patterns of colorectal lesions", Gastrointest Endosc, 72, pp.1047~1051 (2010)
- Alagappan M, "Artificial intelligence in gastrointestinal endoscopy : the future is almost here", World J Gastrointest Endosc, 10, pp.239~249 (2018)
- Hassan C, "Predictive rules for optical diagnosis of < 10-mm colorectal polyps based on a dedicated software", Endoscopy, 52, pp.52~60 (2020)
- Le Berre C, "Application of artificial intelligence to gastroenterology and hepatology", Gastroenterology, 158, pp.76~94 (2020)
- Hassan C, "Performance of artificial intelligence in colonoscopy for adenoma and polyp detection : a systematic review and meta-analysis", Gastrointest Endosc, 93, pp.77~85 (2021)
- Rácz I, "Sa1556 digital image processing software for predicting the histology of small colorectal polyps by using narrow-band imaging magnifying colonoscopy", Gastrointestinal Endoscopy, 81, pp.AB259~ (2015)
- Rex DK, "The american society for gastrointestinal endoscopy PIVI(preservation and incorporation of valuable endoscopic innovations)on real-time endoscopic assessment of the histology of diminutive colorectal polyps", Gastrointest Endosc, 73, pp.419~422 (2011)
- ASGE Technology Committee, "ASGE technology committee systematic review and meta-analysis assessing the ASGE PIVI thresholds for adopting real-time endoscopic assessment of the histology of diminutive colorectal polyps", Gastrointest Endosc, 81, pp.502~ (2015)
- Cohen J, "Preservation and incorporation of valuable endoscopic innovations(PIVI)on the use of endoscopy simulators for training and assessing skill", Gastrointest Endosc, 76, pp.471~475 (2012)
- Tanaka S, "High-magnification colonoscopy(with videos)", Gastrointest Endosc, 64, pp.604~613 (2006)
- Kanao H, "Narrow-band imaging magnification predicts the histology and invasion depth of colorectal tumors", Gastrointest Endosc, 69, pp.631~636 (2009)
- Tanaka S, "Aim to unify the narrow band imaging(NBI)magnifying classification for colorectal tumors : current status in Japan from a summary of the consensus symposium in the 79th annual meeting of the Japan gastroenterological endoscopy society", Dig Endosc, 23(Suppl 1), pp.131~139 (2011)
- Oba S, "Current status of narrow-band imaging magnifying colonoscopy for colorectal neoplasia in Japan", Digestion, 83, pp.167~172 (2011)
- Takemura Y, "Computer-aided system for predicting the histology of colorectal tumors by using narrow-band imaging magnifying colonoscopy(with video)", Gastrointest Endosc, 75, pp.179~185 (2012)
- Kominami Y, "Computer-aided diagnosis of colorectal polyp histology by using a real-time image recognition system and narrow-band imaging magnifying colonoscopy", Gastrointest Endosc, 83, pp.643~649 (2016)
