Literature DB >> 29042219

Accurate Classification of Diminutive Colorectal Polyps Using Computer-Aided Analysis.

Peng-Jen Chen1, Meng-Chiung Lin2, Mei-Ju Lai3, Jung-Chun Lin4, Henry Horng-Shing Lu5, Vincent S Tseng6.   

Abstract

BACKGROUND & AIMS: Narrow-band imaging is an image-enhanced form of endoscopy used to observed microstructures and capillaries of the mucosal epithelium which allows for real-time prediction of histologic features of colorectal polyps. However, narrow-band imaging expertise is required to differentiate hyperplastic from neoplastic polyps with high levels of accuracy. We developed and tested a system of computer-aided diagnosis with a deep neural network (DNN-CAD) to analyze narrow-band images of diminutive colorectal polyps.
METHODS: We collected 1476 images of neoplastic polyps and 681 images of hyperplastic polyps, obtained from the picture archiving and communications system database in a tertiary hospital in Taiwan. Histologic findings from the polyps were also collected and used as the reference standard. The images and data were used to train the DNN. A test set of images (96 hyperplastic and 188 neoplastic polyps, smaller than 5 mm), obtained from patients who underwent colonoscopies from March 2017 through August 2017, was then used to test the diagnostic ability of the DNN-CAD vs endoscopists (2 expert and 4 novice), who were asked to classify the images of the test set as neoplastic or hyperplastic. Their classifications were compared with findings from histologic analysis. The primary outcome measures were diagnostic accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and diagnostic time. The accuracy, sensitivity, specificity, PPV, NPV, and diagnostic time were compared among DNN-CAD, the novice endoscopists, and the expert endoscopists. The study was designed to detect a difference of 10% in accuracy by a 2-sided McNemar test.
RESULTS: In the test set, the DNN-CAD identified neoplastic or hyperplastic polyps with 96.3% sensitivity, 78.1% specificity, a PPV of 89.6%, and a NPV of 91.5%. Fewer than half of the novice endoscopists classified polyps with a NPV of 90% (their NPVs ranged from 73.9% to 84.0%). DNN-CAD classified polyps as neoplastic or hyperplastic in 0.45 ± 0.07 seconds-shorter than the time required by experts (1.54 ± 1.30 seconds) and nonexperts (1.77 ± 1.37 seconds) (both P < .001). DNN-CAD classified polyps with perfect intra-observer agreement (kappa score of 1). There was a low level of intra-observer and inter-observer agreement in classification among endoscopists.
CONCLUSIONS: We developed a system called DNN-CAD to identify neoplastic or hyperplastic colorectal polyps less than 5 mm. The system classified polyps with a PPV of 89.6%, and a NPV of 91.5%, and in a shorter time than endoscopists. This deep-learning model has potential for not only endoscopic image recognition but for other forms of medical image analysis, including sonography, computed tomography, and magnetic resonance images.
Copyright © 2018 AGA Institute. Published by Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Colon Cancer Detection; Cost-effectiveness; Machine Learning; Magnifying

Mesh:

Year:  2017        PMID: 29042219     DOI: 10.1053/j.gastro.2017.10.010

Source DB:  PubMed          Journal:  Gastroenterology        ISSN: 0016-5085            Impact factor:   22.682


  79 in total

Review 1.  State of the Art: The Impact of Artificial Intelligence in Endoscopy 2020.

Authors:  Jiyoung Lee; Michael B Wallace
Journal:  Curr Gastroenterol Rep       Date:  2021-04-14

2.  Human-machine collaboration: bringing artificial intelligence into colonoscopy.

Authors:  Omer F Ahmad; Danail Stoyanov; Laurence B Lovat
Journal:  Frontline Gastroenterol       Date:  2018-10-15

Review 3.  Designing deep learning studies in cancer diagnostics.

Authors:  Andreas Kleppe; Ole-Johan Skrede; Sepp De Raedt; Knut Liestøl; David J Kerr; Håvard E Danielsen
Journal:  Nat Rev Cancer       Date:  2021-01-29       Impact factor: 60.716

4.  Predictive Narrow-Band Imaging of Colonic Polyps: The Optics Are Good.

Authors:  Silvia Paggi; Cesare Hassan; Franco Radaelli
Journal:  Dig Dis Sci       Date:  2018-10       Impact factor: 3.199

Review 5.  Artificial Intelligence and Polyp Detection.

Authors:  Nicholas Hoerter; Seth A Gross; Peter S Liang
Journal:  Curr Treat Options Gastroenterol       Date:  2020-01-21

Review 6.  Artificial Intelligence in Lower Gastrointestinal Endoscopy: The Current Status and Future Perspective.

Authors:  Sebastian Manuel Milluzzo; Paola Cesaro; Leonardo Minelli Grazioli; Nicola Olivari; Cristiano Spada
Journal:  Clin Endosc       Date:  2021-01-13

Review 7.  Artificial Intelligence in Endoscopy.

Authors:  Yutaka Okagawa; Seiichiro Abe; Masayoshi Yamada; Ichiro Oda; Yutaka Saito
Journal:  Dig Dis Sci       Date:  2021-06-21       Impact factor: 3.199

8.  A Gratifying Step forward for the Application of Artificial Intelligence in the Field of Endoscopy: A Narrative Review.

Authors:  Yixin Xu; Yulin Tan; Yibo Wang; Jie Gao; Dapeng Wu; Xuezhong Xu
Journal:  Surg Laparosc Endosc Percutan Tech       Date:  2020-10-28       Impact factor: 1.719

9.  Application of deep learning to predict advanced neoplasia using big clinical data in colorectal cancer screening of asymptomatic adults.

Authors:  Hyo-Joon Yang; Chang Woo Cho; Jongha Jang; Sang Soo Kim; Kwang-Sung Ahn; Soo-Kyung Park; Dong Il Park
Journal:  Korean J Intern Med       Date:  2020-10-23       Impact factor: 2.884

Review 10.  Application of Artificial Intelligence in the Detection and Characterization of Colorectal Neoplasm.

Authors:  Kyeong Ok Kim; Eun Young Kim
Journal:  Gut Liver       Date:  2021-05-15       Impact factor: 4.519

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.