한빛사논문
- 조회750
Eun Hyo Jin1*, Dongheon Lee2*, Jung Ho Bae1, Hae Yeon Kang1, Min-Sun Kwak1, Ji Yeon Seo1, Jong In Yang1, Sun Young Yang1, Seon Hee Lim1, Jeong Yoon Yim1, Joo Hyun Lim1, Goh Eun Chung1, Su Jin Chung1, Ji Min Choi1, Yoo Min Han1, Seung Joo Kang1, Jooyoung Lee5, Hee Chan Kim2,3,4† and Joo Sung Kim1,5†
1Department of Internal Medicine, Healthcare Research Institute, Seoul National University Hospital Healthcare System Gangnam Center, Seoul, Korea
2Interdisciplinary Program in Bioengineering, Graduate School, Seoul National University, Seoul, Korea
3Department of Biomedical Engineering College of Medicine, Seoul National University, Seoul, Korea
4Institute of Medical & Biological Engineering, Medical Research Center, Seoul National University, Seoul, Korea
5Department of Internal Medicine, Liver Research Institute, Seoul National University College of Medicine, Seoul, Korea
†Co-corresponding authors
*Author names in bold designate shared co-first authorship
Abstract
Background & Aims
Narrow-band imaging (NBI) can be used to determine whether colorectal polyps are adenomatous or hyperplastic. We investigated whether an artificial intelligence (AI) system can increase the accuracy of characterizations of polyps by endoscopists of different skill levels.
Methods
We developed convolutional neural networks (CNNs) for evaluation of diminutive colorectal polyps, based on efficient neural architecture searches via parameter sharing with augmentation using narrow-band images of diminutive (≤5 mm) polyps, collected from October 2015 through October 2017 at the Seoul National University Hospital, Healthcare System Gangnam Center (training set). We trained the CNN using images from 1100 adenomatous polyps and 1050 hyperplastic polyps from 1379 patients. We then tested the system using 300 images of 180 adenomatous polyps and 120 hyperplastic polyps, obtained from January 2018 to May 2019. We compared the accuracy of 22 endoscopists of different skill levels (7 novices, 4 experts, and 11 NBI-trained experts) vs the CNN in evaluation of images (adenomatous vs hyperplastic) from 180 adenomatous and 120 hyperplastic polyps. The endoscopists then evaluated the polyp images with knowledge of the CNN-processed results. We conducted mixed-effect logistic and linear regression analyses to determine the effects of AI assistance on the accuracy of analysis of diminutive colorectal polyps by endoscopists (primary outcome).
Results
The CNN distinguished adenomatous vs hyperplastic diminutive polyps with 86.7% accuracy, based on histologic analysis as the reference standard. Endoscopists distinguished adenomatous vs hyperplastic diminutive polyps with 82.5% overall accuracy (novices, 73.8% accuracy; experts, 83.8% accuracy; and NBI-trained experts, 87.6% accuracy). With knowledge of the CNN-processed results, the overall accuracy of the endoscopists increased to 88.5% (P < .05). With knowledge of the CNN-processed results, the accuracy of novice endoscopists increased to 85.6% (P < .05). The CNN-processed results significantly reduced endoscopist time of diagnosis (from 3.92 to 3.37 seconds per polyp, P = .042).
Conclusions
We developed a CNN that significantly increases the accuracy of evaluation of diminutive colorectal polyps (as adenomatous vs hyperplastic) and reduces the time of diagnosis by endoscopists. This AI assistance system significantly increased the accuracy of analysis by novice endoscopists, who achieved nearexpert levels of accuracy without extra training. The CNN assistance system can reduce the skill-level dependence of endoscopists and costs.
관련 Webinar
대장 용종의 광학 진단을 위한 딥러닝 알고리즘의 개발과 적용
진은효/이동헌 (서울대학교병원/서울대학교) 발표일자: 2020-05-26
논문정보
- Research article
- 2020년 02월 (BRIC 등록일 2020-03-16)
- 국내 연구진
- 의약학 > 응용의학
댓글 작성 로그인
팝업 닫기관련 링크
연구자 키워드
연구자 ID
관련분야 연구자보기
소속기관 논문보기
관련분야 논문보기
해당논문 저자보기
