CASIA OpenIR  > 中国科学院分子影像重点实验室
Diagnosing and grading gastric atrophy and intestinal metaplasia using semi-supervised deep learning on pathological images: development and validation study
Fang, Shuangshuang1; Liu, Zhenyu2,3; Qiu, Qi2,3; Tang, Zhenchao4; Yang, Yang1; Kuang, Zhongsheng5; Du, Xiaohua6; Xiao, Shanshan5; Liu, Yanyan5; Luo, Yuanbin7; Gu, Liping7; Tian, Li7; Liang, Xiaoxia8; Fan, Guiling8; Zhang, Yu8; Zhang, Ping9; Zhou, Weixun10; Liu, Xiuli11; Tian, Jie2,3,4,12; Wei, Wei1
Source PublicationGASTRIC CANCER
ISSN1436-3291
2023-12-14
Pages12
Corresponding AuthorWei, Wei(weiwei3816@mail.cintcm.ac.cn)
AbstractObjectivePatients with gastric atrophy and intestinal metaplasia (IM) were at risk for gastric cancer, necessitating an accurate risk assessment. We aimed to establish and validate a diagnostic approach for gastric biopsy specimens using deep learning and OLGA/OLGIM for individual gastric cancer risk classification.MethodsIn this study, we prospectively enrolled 545 patients suspected of atrophic gastritis during endoscopy from 13 tertiary hospitals between December 22, 2017, to September 25, 2020, with a total of 2725 whole-slide images (WSIs). Patients were randomly divided into a training set (n = 349), an internal validation set (n = 87), and an external validation set (n = 109). Sixty patients from the external validation set were randomly selected and divided into two groups for an observer study, one with the assistance of algorithm results and the other without. We proposed a semi-supervised deep learning algorithm to diagnose and grade IM and atrophy, and we compared it with the assessments of 10 pathologists. The model's performance was evaluated based on the area under the curve (AUC), sensitivity, specificity, and weighted kappa value.ResultsThe algorithm, named GasMIL, was established and demonstrated encouraging performance in diagnosing IM (AUC 0.884, 95% CI 0.862-0.902) and atrophy (AUC 0.877, 95% CI 0.855-0.897) in the external test set. In the observer study, GasMIL achieved an 80% sensitivity, 85% specificity, a weighted kappa value of 0.61, and an AUC of 0.953, surpassing the performance of all ten pathologists in diagnosing atrophy. Among the 10 pathologists, GasMIL's AUC ranked second in OLGA (0.729, 95% CI 0.625-0.833) and fifth in OLGIM (0.792, 95% CI 0.688-0.896). With the assistance of GasMIL, pathologists demonstrated improved AUC (p = 0.013), sensitivity (p = 0.014), and weighted kappa (p = 0.016) in diagnosing IM, and improved specificity (p = 0.007) in diagnosing atrophy compared to pathologists working alone.ConclusionGasMIL shows the best overall performance in diagnosing IM and atrophy when compared to pathologists, significantly enhancing their diagnostic capabilities.
KeywordAtrophic gastritis Semi-supervised deep learning Diagnose The operative link for gastric intestinal metaplasia assessment The operative link for gastritis assessment
DOI10.1007/s10120-023-01451-9
WOS KeywordPROSTATE-CANCER ; CLASSIFICATION ; AGREEMENT ; BIOPSIES ; SYSTEM
Indexed BySCI
Language英语
Funding ProjectNational Traditional Chinese Medicine Inheritance and Innovation Team Project
Funding OrganizationNational Traditional Chinese Medicine Inheritance and Innovation Team Project
WOS Research AreaOncology ; Gastroenterology & Hepatology
WOS SubjectOncology ; Gastroenterology & Hepatology
WOS IDWOS:001126296000001
PublisherSPRINGER
Citation statistics
Cited Times:2[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/55013
Collection中国科学院分子影像重点实验室
Corresponding AuthorWei, Wei
Affiliation1.China Acad Chinese Med Sci, Wangjing Hosp, Dept Med Secur Management, Beijing Key Lab Funct Gastrointestinal Disorders D, 6 Zhonghuan South Rd, Beijing 100102, Peoples R China
2.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China
4.Beihang Univ, Beijing Adv Innovat Ctr Big Data Based Precis Med, Sch Engn Med, Beijing 100191, Peoples R China
5.Guangdong Univ Tradit Chinese Med, Dept Pathol, Affiliated Hosp 1, Guangzhou 510405, Peoples R China
6.Guangdong Prov Hosp Tradit Chinese Med, Dept Pathol, Guangzhou 510120, Peoples R China
7.Gansu Prov Hosp Tradit Chinese Med, Dept Pathol, Lanzhou 730050, Peoples R China
8.Shanxi Prov Hosp Tradit Chinese Med, Dept Pathol, Taiyuan 030012, Peoples R China
9.Wangjing Hosp, China Acad Chinese Med Sci, Dept Pathol, Beijing 100102, Peoples R China
10.Peking Union Med Coll Hosp, Dept Pathol, Beijing 100730, Peoples R China
11.Washington Univ, Dept Pathol & Immunol, St Louis, MO 98195 USA
12.Xidian Univ, Engn Res Ctr Mol & Neuro Imaging, Sch Life Sci & Technol, Minist Educ, Xian 710126, Shaanxi, Peoples R China
Recommended Citation
GB/T 7714
Fang, Shuangshuang,Liu, Zhenyu,Qiu, Qi,et al. Diagnosing and grading gastric atrophy and intestinal metaplasia using semi-supervised deep learning on pathological images: development and validation study[J]. GASTRIC CANCER,2023:12.
APA Fang, Shuangshuang.,Liu, Zhenyu.,Qiu, Qi.,Tang, Zhenchao.,Yang, Yang.,...&Wei, Wei.(2023).Diagnosing and grading gastric atrophy and intestinal metaplasia using semi-supervised deep learning on pathological images: development and validation study.GASTRIC CANCER,12.
MLA Fang, Shuangshuang,et al."Diagnosing and grading gastric atrophy and intestinal metaplasia using semi-supervised deep learning on pathological images: development and validation study".GASTRIC CANCER (2023):12.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Fang, Shuangshuang]'s Articles
[Liu, Zhenyu]'s Articles
[Qiu, Qi]'s Articles
Baidu academic
Similar articles in Baidu academic
[Fang, Shuangshuang]'s Articles
[Liu, Zhenyu]'s Articles
[Qiu, Qi]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Fang, Shuangshuang]'s Articles
[Liu, Zhenyu]'s Articles
[Qiu, Qi]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.