Automatic captioning of early gastric cancer using magnification endoscopy with narrow-band imaging

doi:10.1016/j.gie.2022.07.019

	Automatic captioning of early gastric cancer using magnification endoscopy with narrow-band imaging
	Gong, Lixin 1,2,3; Wang, Min4 ; Shu, Lei 5; He, Jie 6,7; Bin Qin 8; Xu, Jiacheng 9,10,11; Su, Wei 9,10,11; Dong, Di3 ; Hu, Hao 9,10,11,12; Tian, Jie 1,2,3,13; Zhou, Pinghong 9,10,11
发表期刊	GASTROINTESTINAL ENDOSCOPY
ISSN	0016-5107
	2022-12-01
卷号	96 期号:6 页码:929-+
通讯作者	Hu, Hao()
摘要	Background and Aims: The detection rate for early gastric cancer (EGC) is unsatisfactory, and mastering the diagnostic skills of magnifying endoscopy with narrow-band imaging (ME-NBI) requires rich expertise and experience. We aimed to develop an EGC captioning model (EGCCap) to automatically describe the visual character Methods: ME-NBI images (n = 1886) from 294 cases were enrolled from multiple centers, and corresponding 5658 text data were designed following the simple EGC diagnostic algorithm. An EGCCap was developed using the multiscale meshed-memory transformer. We conducted comprehensive evaluations for EGCCap including the quantitative and quality of performance, generalization, robustness, interpretability, and assistant value analyses. The commonly used metrics were BLEUs, CIDEr, METEOR, ROUGE, SPICE, accuracy, sensitivity, and specificity. Two-sided statistical tests were conducted, and statistical significance was determined when P < .05. Results: EGCCap acquired satisfying captioning performance by outputting correctly and coherently clinically meaningful sentences in the internal test cohort (BLEU1 = 52.434, CIDEr = 36.734, METEOR = 27.823, ROUGE = 49.949, SPICE = 35.548) and maintained over 80% performance when applied to other centers or corrupted data. The diagnostic ability of endoscopists improved with the assistance of EGCCap, which was especially significant (P < .05) for junior endoscopists. Endoscopists gave EGCCap an average remarkable score of 7.182, showing acceptance of EGCCap. Conclusions: EGCCap exhibited promising captioning performance and was proven with satisfying generalization, robustness, and interpretability. Our study showed potential value in aiding and improving the diagnosis of EGC and facilitating the development of automated reporting in the future. (Gastrointest Endosc 2022;96:929-42.)
DOI	10.1016/j.gie.2022.07.019
关键词[WOS]	DIAGNOSIS ; BURDEN ; CHINA
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[81900548] ; National Natural Science Foundation of China[82022036] ; National Natural Science Foundation of China[91959130] ; National Natural Science Foundation of China[81971776] ; National Natural Science Foundation of China[62027901] ; National Natural Science Foundation of China[81771924] ; National Natural Science Foundation of China[81930053] ; Smart Medical Program of Shanghai Municipal Health Commission[2018ZHYL0204] ; Natural Science Foundation of Shanghai[22015831400] ; Natural Science Foundation of Shanghai[22Y11907500] ; Natural Science Foundation of Shanghai[20DZ1100102] ; Shanghai Municipal Human Resources Development Program for Outstanding Young Talents in Medical and Health Sciences[2018YQ33] ; National Key R&D Program of China[2017YFA0700401] ; National Key R&D Program of China[2017YFA0205200] ; National Key R&D Program of China[2017YFC1309100] ; National Key R&D Program of China[2017YFC1308700] ; Beijing Natural Science Foundation[L182061] ; Beijing Natural Science Foundation[Z20J00105] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB38040200] ; Project of High-Level Talents Team Introduction in Zhuhai City (Zhuhai)[HLHPTP201703] ; Youth Innovation Promotion Association CAS[Y2021049] ; Youth Innovation Promotion Association CAS[2017175]
项目资助者	National Natural Science Foundation of China ; Smart Medical Program of Shanghai Municipal Health Commission ; Natural Science Foundation of Shanghai ; Shanghai Municipal Human Resources Development Program for Outstanding Young Talents in Medical and Health Sciences ; National Key R&D Program of China ; Beijing Natural Science Foundation ; Strategic Priority Research Program of the Chinese Academy of Sciences ; Project of High-Level Talents Team Introduction in Zhuhai City (Zhuhai) ; Youth Innovation Promotion Association CAS
WOS研究方向	Gastroenterology & Hepatology
WOS类目	Gastroenterology & Hepatology
WOS记录号	WOS:000919644000008
出版者	MOSBY-ELSEVIER
引用统计	被引频次：5[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/51420
专题	中国科学院分子影像重点实验室
通讯作者	Hu, Hao
作者单位	1.Northeastern Univ, Coll Med, Shenyang, Peoples R China 2.Northeastern Univ, Biol Informat Engn Sch, Shenyang, Peoples R China 3.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing Key Lab Mol Imaging,State Key Lab Managem, Beijing, Peoples R China 4.Shanghai Jiao Tong Univ, Shanghai Childrens Hosp, Dept Gastroenterol Hepatol & Nutr, Shanghai, Peoples R China 5.1 Hosp Wuhan, Dept Gastroenterol, Wuhan, Peoples R China 6.Fudan Univ, Zhongshan Hosp, Xiamen Branch, Endoscopy Ctr, Xiamen, Peoples R China 7.Xiamen Univ, Affiliated Dongnan Hosp, Dept Gastroenterol, Zhangzhou, Peoples R China 8.Xi An Jiao Tong Univ, Affiliated Hosp 2, Dept Gastroenterol, Zhangzhou, Peoples R China 9.Fudan Univ, Zhongshan Hosp, Endoscopy Ctr, 180 Fenglin Rd, Shanghai 200032, Peoples R China 10.Fudan Univ, Zhongshan Hosp, Endoscopy Res Inst, 180 Fenglin Rd, Shanghai 200032, Peoples R China 11.Shanghai Collaborat Innovat Ctr Endoscopy, Shanghai, Peoples R China 12.Shigatse Peoples Hosp, Dept Gastroenterol, Shigatse, Peoples R China 13.Beihang Univ, Beijing Adv Innovat Ctr Big Data Based Precis Med, Sch Med & Engn, Beijing, Peoples R China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Gong, Lixin,Wang, Min,Shu, Lei,et al. Automatic captioning of early gastric cancer using magnification endoscopy with narrow-band imaging[J]. GASTROINTESTINAL ENDOSCOPY,2022,96(6):929-+.
APA	Gong, Lixin.,Wang, Min.,Shu, Lei.,He, Jie.,Bin Qin.,...&Zhou, Pinghong.(2022).Automatic captioning of early gastric cancer using magnification endoscopy with narrow-band imaging.GASTROINTESTINAL ENDOSCOPY,96(6),929-+.
MLA	Gong, Lixin,et al."Automatic captioning of early gastric cancer using magnification endoscopy with narrow-band imaging".GASTROINTESTINAL ENDOSCOPY 96.6(2022):929-+.