Automatically optimized radiomics modeling system for small gastric submucosal tumor (<2 cm) discrimination based on EUS images.

Journal

Gastrointestinal endoscopy
ISSN: 1097-6779
Titre abrégé: Gastrointest Endosc
Pays: United States
ID NLM: 0010505

Informations de publication

Date de publication:
Apr 2024
Historique:
received: 20 05 2023
revised: 14 10 2023
accepted: 06 11 2023
pubmed: 14 11 2023
medline: 14 11 2023
entrez: 13 11 2023
Statut: ppublish

Résumé

The clinical management of small gastric submucosal tumors (SMTs) (<2 cm) faces a non-negligible challenge because of the lack of guideline consensus and effective diagnostic tools. This article develops an automatically optimized radiomics modeling system (AORMS) based on EUS images to diagnose and evaluate SMTs. A total of 205 patients with EUS images of small gastric SMTs (<2 cm) were retrospectively enrolled in the development phase of AORMS for the diagnosis and the risk stratification of GI stromal tumor (GIST). A total of 178 patients with images from different centers were prospectively enrolled in the independent testing phase. The performance of AORMS was compared to that of endoscopists in the development set and evaluated in the independent testing set. AORMS demonstrated an area under the curve (AUC) of 0.762 for the diagnosis of GIST and 0.734 for the risk stratification of GIST, respectively. In the independent testing set, AORMS achieved an AUC of 0.770 and 0.750 for the diagnosis and risk stratification of small GISTs, respectively. In comparison, the AUCs of 5 experienced endoscopists ranged from 0.501 to 0.608 for diagnosing GIST and from 0.562 to 0.748 for risk stratification. AORMS outperformed experienced endoscopists by more than 20% in diagnosing GIST. AORMS implements automatic parameter selection, which enhances its robustness and clinical applicability. It has demonstrated good performance in the diagnosis and risk stratification of GISTs, which could aid endoscopists in the diagnosis of small gastric SMTs (<2 cm).

Sections du résumé

BACKGROUND AND AIMS OBJECTIVE
The clinical management of small gastric submucosal tumors (SMTs) (<2 cm) faces a non-negligible challenge because of the lack of guideline consensus and effective diagnostic tools. This article develops an automatically optimized radiomics modeling system (AORMS) based on EUS images to diagnose and evaluate SMTs.
METHODS METHODS
A total of 205 patients with EUS images of small gastric SMTs (<2 cm) were retrospectively enrolled in the development phase of AORMS for the diagnosis and the risk stratification of GI stromal tumor (GIST). A total of 178 patients with images from different centers were prospectively enrolled in the independent testing phase. The performance of AORMS was compared to that of endoscopists in the development set and evaluated in the independent testing set.
RESULTS RESULTS
AORMS demonstrated an area under the curve (AUC) of 0.762 for the diagnosis of GIST and 0.734 for the risk stratification of GIST, respectively. In the independent testing set, AORMS achieved an AUC of 0.770 and 0.750 for the diagnosis and risk stratification of small GISTs, respectively. In comparison, the AUCs of 5 experienced endoscopists ranged from 0.501 to 0.608 for diagnosing GIST and from 0.562 to 0.748 for risk stratification. AORMS outperformed experienced endoscopists by more than 20% in diagnosing GIST.
CONCLUSIONS CONCLUSIONS
AORMS implements automatic parameter selection, which enhances its robustness and clinical applicability. It has demonstrated good performance in the diagnosis and risk stratification of GISTs, which could aid endoscopists in the diagnosis of small gastric SMTs (<2 cm).

Identifiants

DOI: 10.1016/j.gie.2023.11.006 PMID: 37956896
pubmed: 37956896
pii: S0016-5107(23)03042-0
doi: 10.1016/j.gie.2023.11.006
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

537-547.e4

Informations de copyright

Copyright © 2024. Published by Elsevier Inc.

Déclaration de conflit d'intérêts

Disclosure All authors disclosed no financial relationships.

Auteurs

Mingyan Cai (M)

Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Endoscopic Minimally Invasive Collaborative Innovation Center, Shanghai, China.

Baohui Song (B)

Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Endoscopic Minimally Invasive Collaborative Innovation Center, Shanghai, China.

Yinhui Deng (Y)

MingGe Research, Fudan University Science Park, Shanghai, China; Biomedical Engineering Center, School of Information Science and Technology, Fudan University, Shanghai, China.

Pingting Gao (P)

Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Endoscopic Minimally Invasive Collaborative Innovation Center, Shanghai, China.

Shilun Cai (S)

Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Endoscopic Minimally Invasive Collaborative Innovation Center, Shanghai, China.

Ayimukedisi Yalikong (A)

Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Endoscopic Minimally Invasive Collaborative Innovation Center, Shanghai, China.

Enpan Xu (E)

Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Endoscopic Minimally Invasive Collaborative Innovation Center, Shanghai, China.

Yunshi Zhong (Y)

Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Endoscopic Minimally Invasive Collaborative Innovation Center, Shanghai, China; Department of Endoscopy, Zhongshan Hospital Xuhui Branch, Fudan University, Shanghai, China. Electronic address: zhong.yunshi@zs-hospital.sh.cn.

Jinhua Yu (J)

Biomedical Engineering Center, School of Information Science and Technology, Fudan University, Shanghai, China. Electronic address: jhyu@fudan.edu.cn.

Pinghong Zhou (P)

Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Endoscopic Minimally Invasive Collaborative Innovation Center, Shanghai, China. Electronic address: zhou.pinghong@zs-hospital.sh.cn.

Classifications MeSH