Convolutional neural network‐based object detection model to identify gastrointestinal stromal tumors in endoscopic ultrasound images

Oh, Chang Kyo; Kim, Tae‐Wan; Cho, Yu Kyung; Cheung, Dae Young; Lee, Bo‐In; Cho, Young-Seok; Kim, Sang Hyun; Lee, Han Hee; Lee, Seung−Chul

doi:10.1111/jgh.15653

Cited by 27 publications

(23 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One study involved five SELs, including GIST, leiomyomas, schwannomas, NET, and ectopic pancreas ( 24 ). Four studies developed AI only for the differential diagnosis of GIST and leiomyoma ( 22 , 23 , 25 , 26 ), and a subgroup analysis of these four studies was conducted to explore the discriminating ability of the two diseases. The AI model had a pooled AUC of 0.95 (95% CI, 0.93-0.97), sensitivity of 0.93 (95% CI, 0.87-0.97), specificity of 0.88 (95% CI, 0.71-0.96), PLR of 8.04 (95% CI, 2.92-22.18), and NLR of 0.08 (95% CI, 0.04-0.15) ( Supplementary Figures 4 , 5 ).…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Application of artificial intelligence in the diagnosis of subepithelial lesions using endoscopic ultrasonography: a systematic review and meta-analysis

et al. 2022

View full text Add to dashboard Cite

Endoscopic ultrasonography (EUS) is the most common method for diagnosing gastrointestinal subepithelial lesions (SELs); however, it usually requires histopathological confirmation using invasive methods. Artificial intelligence (AI) algorithms have made significant progress in medical imaging diagnosis. The purpose of our research was to explore the application of AI in the diagnosis of SELs using EUS and to evaluate the diagnostic performance of AI-assisted EUS. Three databases, PubMed, EMBASE, and the Cochrane Library, were comprehensively searched for relevant literature. RevMan 5.4.1 and Stata 17.0, were used to calculate and analyze the combined sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and summary receiver-operating characteristic curve (SROC). Eight studies were selected from 380 potentially relevant studies for the meta-analysis of AI-aided EUS diagnosis of SELs. The combined sensitivity, specificity, and DOR of AI-aided EUS were 0.92 (95% CI, 0.85-0.96), 0.80 (95% CI, 0.70-0.87), and 46.27 (95% CI, 19.36-110.59), respectively). The area under the curve (AUC) was 0.92 (95% CI, 0.90-0.94). The AI model in differentiating GIST from leiomyoma had a pooled AUC of 0.95, sensitivity of 0.93, specificity of 0.88, PLR of 8.04, and NLR of 0.08. The combined sensitivity, specificity, and AUC of the AI-aided EUS diagnosis in the convolutional neural network (CNN) model were 0.93, 0.81, and 0.94, respectively. AI-aided EUS diagnosis using conventional brightness mode (B-mode) EUS images had a combined sensitivity of 0.92, specificity of 0.79, and AUC of 0.92. AI-aided EUS diagnosis based on patients had a combined sensitivity, specificity, and AUC of 0.95, 0.83, and 0.96, respectively. Additionally, AI-aided EUS was superior to EUS by experts in terms of sensitivity (0.93 vs. 0.71), specificity (0.81 vs. 0.69), and AUC (0.94 vs. 0.75). In conclusion, AI-assisted EUS is a promising and reliable method for distinguishing SELs, with excellent diagnostic performance. More multicenter cohort and prospective studies are expected to be conducted to further develop AI-assisted real-time diagnostic systems and validate the superiority of AI systems.Systematic Review Registration:PROSPERO (https://www.crd.york.ac.uk/PROSPERO/), identifier CRD42022303990.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Although there are many types of SELs, most studies classified SELs into two categories: GIST and non-GIST, to explore the accuracy of AI-assisted EUS. In four studies, the non-GISTs only referred to leiomyoma, and we performed a subgroup analysis ( 22 , 23 , 25 , 26 ). Nguyen et al.…”

Section: Discussionmentioning

confidence: 99%

Application of artificial intelligence in the diagnosis of subepithelial lesions using endoscopic ultrasonography: a systematic review and meta-analysis

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Therefore, subgroup analyses were performed according to the classification of lesions (binary: GIST vs leiomyoma; multicategory: GIST vs non‐GIST). For binary classification (GIST vs leiomyoma), the pooled sensitivity and specificity were 0.93 (95% CI 0.89–0.96; I 2 = 68.9%) and 0.84 (95% CI 0.65–0.93; I 2 = 85.5%), with the AUROC of 0.94 29,31–33 . With respect to multicategory classification (GIST vs non‐GIST), the diagnostic performance of AI‐based EUS for differentiating GISTs remained acceptable (sensitivity 0.90; specificity 0.73; AUROC 0.83) 27,28,30 …”

Section: Resultsmentioning

confidence: 99%

“…F I G U R E 6 Funnel plot assessing bias for diagnostic accuracy of artificial intelligence-based endoscopic ultrasound for gastrointestinal stromal tumors (95% CI 0.65-0.93; I 2 = 85.5%), with the AUROC of 0.94. 29,[31][32][33] With respect to multicategory classification (GIST vs non-GIST), the diagnostic performance of AI-based EUS for differentiating GISTs remained acceptable (sensitivity 0.90; specificity 0.73; AUROC 0.83). 27,28,30 To successfully implement AI-based EUS in real-world scenarios, performance of the established AI-based system must be verified in an independent data set.…”

Section: Subgroup Analysesmentioning

confidence: 99%

See 1 more Smart Citation

Diagnostic accuracy of endoscopic ultrasound with artificial intelligence for gastrointestinal stromal tumors: A meta‐analysis

Zhao

Wang

2022

J of Digest Diseases

View full text Add to dashboard Cite

Objectives: Gastrointestinal stromal tumors (GISTs) are thought to have a malignant potential. However, utilizing endoscopic ultrasound (EUS) to differentiate GISTs from other types of subepithelial lesions (SELs) remains challenging. Artificial intelligence (AI)-based diagnostic systems for EUS have been reported to have a promising performance, although the results of the previous studies remain controversial. In this meta-analysis, we aimed to assess the diagnostic accuracy of AI-based EUS in distinguishing GISTs from other SELs.Methods: A literature search was conducted on MEDLINE and EMBASE databases to identify relevant articles. The sensitivity, specificity, and area under the summary receiver operating characteristic curve (AUROC) of eligible studies were analyzed.Results: Seven studies were eligible for the final analysis. The combined sensitivity and specificity of AI-based EUS were 0.93 (95% confidence interval [CI] 0.88-0.96) and 0.78 (95% CI 0.67-0.87), respectively. The overall diagnostic odds ratio of AI-based EUS for GISTs was ) with an AUROC of 0.94.Conclusions: AI-based EUS showed high diagnostic ability and might help better differentiate GISTs from other SELs. More prospective studies on the diagnosis of GISTs using AI-based EUS are warranted in clinical setting.

show abstract

A combined radiomic model distinguishing GISTs from leiomyomas and schwannomas in the stomach based on endoscopic ultrasonography images

Zhang

Gong

et al. 2023

J Applied Clin Med Phys

View full text Add to dashboard Cite

Background Endoscopic ultrasonography (EUS) is recommended as the best tool for evaluating gastric subepithelial lesions (SELs); nonetheless, it has difficulty distinguishing gastrointestinal stromal tumors (GISTs) from leiomyomas and schwannomas. GISTs have malignant potential, whereas leiomyomas and schwannomas are considered benign. Purpose This study aimed to establish a combined radiomic model based on EUS images for distinguishing GISTs from leiomyomas and schwannomas in the stomach. Methods EUS images of pathologically confirmed GISTs, leiomyomas, and schwannomas were collected from five centers. Gastric SELs were divided into training and testing datasets based on random split‐sample method (7:3). Radiomic features were extracted from the tumor and muscularis propria regions. Principal component analysis, least absolute shrinkage, and selection operator were used for feature selection. Support vector machine was used to construct radiomic models. Two radiomic models were built: the conventional radiomic model included tumor features alone, whereas the combined radiomic model incorporated features from the tumor and muscularis propria regions. Results A total of 3933 EUS images from 485 cases were included. For the differential diagnosis of GISTs from leiomyomas and schwannomas, the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve were 74.5%, 72.2%, 78.7%, and 0.754, respectively, for the EUS experts; 76.8%, 74.4%, 81.0%, and 0.830, respectively, for the conventional radiomic model; and 90.9%, 91.0%, 90.6%, and 0.953, respectively, for the combined radiomic model. For gastric SELs <20 mm, the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve of the combined radiomic model were 91.4%, 91.6%, 91.1%, and 0.960, respectively. Conclusions We developed and validated a combined radiomic model to distinguish gastric GISTs from leiomyomas and schwannomas. The combined radiomic model showed better diagnostic performance than the conventional radiomic model and could assist EUS experts in non‐invasively diagnosing gastric SELs, particularly gastric SELs <20 mm.

show abstract

Convolutional neural network‐based object detection model to identify gastrointestinal stromal tumors in endoscopic ultrasound images

Cited by 27 publications

References 33 publications

Application of artificial intelligence in the diagnosis of subepithelial lesions using endoscopic ultrasonography: a systematic review and meta-analysis

Application of artificial intelligence in the diagnosis of subepithelial lesions using endoscopic ultrasonography: a systematic review and meta-analysis

Diagnostic accuracy of endoscopic ultrasound with artificial intelligence for gastrointestinal stromal tumors: A meta‐analysis

A combined radiomic model distinguishing GISTs from leiomyomas and schwannomas in the stomach based on endoscopic ultrasonography images

Contact Info

Product

Resources

About