Artificial intelligence‐aided diagnostic imaging: A state‐of‐the‐art technique in precancerous screening

Author:

Lu Yang‐Bor12ORCID,Lu Si‐Cun34ORCID,Li Fu‐Dong5ORCID,Le Puo‐Hsien6,Zhang Kai‐Hua7,Sun Zi‐Zheng7,Huang Yung‐Ning12,Weng Yu‐Chieh12,Chen Wei‐Ting6,Fu Yi‐Wei8,Qian Jun‐Bo9,Hu Bin10ORCID,Xu Hong5ORCID,Chiu Cheng‐Tang6,Xu Qin‐Wei11,Gong Wei34ORCID

Affiliation:

1. Department of Digestive Disease, Xiamen Chang Gung Hospital Hua Qiao University Xiamen China

2. Endoscopy Center, Xiamen Chang Gung Hospital Hua Qiao University Xiamen China

3. Departmemt of Gastroenterology, Shenzhen Hospital Southern Medical University Shenzhen China

4. The Third School of Clinical Medicine Southern Medical University Shenzhen China

5. Department of Gastroenterology and Endoscopy Center First Hospital of Jilin University Jilin China

6. Department of Gastroenterology and Hepatology Chang Gung Memorial Hospital, Linkou Branch Taoyuan Taiwan

7. School of Computer Nanjing University of Information Science and Technology Nanjing China

8. Department of Gastroenterology Affiliated Taizhou People's Hospital of Nanjing Medical University Nanjing China

9. Department of Gastroenterology The Second Hospital affiliated to Nantong University Nantong China

10. Department of Gastroenterology, West China Hospital Sichuan University Chengdu China

11. Endoscopy Center, Department of Gastroenterology, Shanghai East Hospital, School of Medicine Tongji University Shanghai China

Abstract

AbstractBackground and AimChromoendoscopy with the use of indigo carmine (IC) dye is a crucial endoscopic technique to identify gastrointestinal neoplasms. However, its performance is limited by the endoscopist's skill, and no standards are available for lesion identification. Thus, we developed an artificial intelligence (AI) model to replace chromoendoscopy.MethodsThis pilot study assessed the feasibility of our novel AI model in the conversion of white‐light images (WLI) into virtual IC‐dyed images based on a generative adversarial network. The predictions of our AI model were evaluated against the assessments of five endoscopic experts who were blinded to the purpose of this study with a staining quality rating from 1 (unacceptable) to 4 (excellent).ResultsThe AI model successfully transformed the WLI of polyps with different morphologies and different types of lesions in the gastrointestinal tract into virtual IC‐dyed images. The quality ratings of the real IC‐dyed and AI images did not significantly differ concerning surface structure (AI vs IC: 3.08 vs 3.00), lesion border (3.04 vs 2.98), and overall contrast (3.14 vs 3.02) from 10 sets of images (10 AI images and 10 real IC‐dyed images). Although the score depended significantly on the evaluator, the staining methods (AI or real IC) and evaluators had no significant interaction (P > 0.05) with each other.ConclusionOur results demonstrated the feasibility of employing AI model's virtual IC staining, increasing the possibility of being employed in daily practice. This novel technology may facilitate gastrointestinal lesion identification in the future.

Funder

National Natural Science Foundation of China

Science, Technology and Innovation Commission of Shenzhen Municipality

Department of Finance of Jilin Province

Science and Technology Commission of Putuo District

Publisher

Wiley

Subject

Gastroenterology,Hepatology

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3