2022
DOI: 10.5946/ce.2022.005
|View full text |Cite
|
Sign up to set email alerts
|

Real-time semantic segmentation of gastric intestinal metaplasia using a deep learning approach

Abstract: Background/Aims: Previous artificial intelligence (AI) models attempting to segment gastric intestinal metaplasia (GIM) areas have failed to be deployed in real-time endoscopy due to their slow inference speeds. Here, we propose a new GIM segmentation AI model with inference speeds faster than 25 frames per second that maintains a high level of accuracy.Methods: Investigators from Chulalongkorn University obtained 802 histological-proven GIM images for AI model training. Four strategies were proposed to improv… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
11
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 14 publications
(11 citation statements)
references
References 32 publications
0
11
0
Order By: Relevance
“…established a real‐time semantic segmentation model in terms of intestinal metaplasia. 27 Although the diagnostic performance in this study was excellent, this model was not a CADe or CADx model; rather, only gastric intestinal metaplasia could be segmented in real time.…”
Section: Discussionmentioning
confidence: 83%
“…established a real‐time semantic segmentation model in terms of intestinal metaplasia. 27 Although the diagnostic performance in this study was excellent, this model was not a CADe or CADx model; rather, only gastric intestinal metaplasia could be segmented in real time.…”
Section: Discussionmentioning
confidence: 83%
“…Siripoppohn et al [ 42 ] implemented semantic segmentation of GIM by adding three additional preprocessing techniques to the BiSeNet network and compared it with the classical semantic segmentation algorithms, DeepLabV3+ and U-Net. Diagnostic data were extracted from the improved algorithm using a prospective video test set.…”
Section: Resultsmentioning
confidence: 99%
“…Several studies have shown that deep learning models can achieve 87% to 99.18% accuracy in the recognition of IM. 38,40,41 As noted above, most of this research has been focused on image recognition; the clinical value of existing models remains unclear. A few test videos have shown that the models require demanding environmental conditions to achieve the desired recognition effect.…”
Section: Applications Of Ai In Upper Gastrointestinal Tract Lesion De...mentioning
confidence: 99%
“…A few test videos have shown that the models require demanding environmental conditions to achieve the desired recognition effect. 40 Feature extraction and matching are essential for AI image recognition; any factors affecting the clinical presentation will influence AI recognition performance. Such factors include light, lens angle, and distance from the lens to the gastric mucosa.…”
Section: Applications Of Ai In Upper Gastrointestinal Tract Lesion De...mentioning
confidence: 99%