Clinical Endoscopy

Peerapon Vateekul

2 Articles

Performance comparison between two computer-aided detection colonoscopy models by trainees using different false positive thresholds: a cross-sectional study in Thailand: Kasenee Tiankanon, Julalak Karuehardsuwan, Satimai Aniwan, Parit Mekaroonkamol, Panukorn Sunthornwechapong, Huttakan Navadurong, Kittithat Tantitanawat, Krittaya Mekritthikrai, Salin Samutrangsi, Peerapon Vateekul, Rungsun Rerknimitr; Clin Endosc 2024;57(2):217-225. Published online February 7, 2024; DOI: https://doi.org/10.5946/ce.2023.145

Graphical Abstract Abstract PDF Supplementary Material PubReader ePub

Background
/Aims: This study aims to compare polyp detection performance of “Deep-GI,” a newly developed artificial intelligence (AI) model, to a previously validated AI model computer-aided polyp detection (CADe) using various false positive (FP) thresholds and determining the best threshold for each model.
Methods
Colonoscopy videos were collected prospectively and reviewed by three expert endoscopists (gold standard), trainees, CADe (CAD EYE; Fujifilm Corp.), and Deep-GI. Polyp detection sensitivity (PDS), polyp miss rates (PMR), and false-positive alarm rates (FPR) were compared among the three groups using different FP thresholds for the duration of bounding boxes appearing on the screen.
Results
In total, 170 colonoscopy videos were used in this study. Deep-GI showed the highest PDS (99.4% vs. 85.4% vs. 66.7%, p<0.01) and the lowest PMR (0.6% vs. 14.6% vs. 33.3%, p<0.01) when compared to CADe and trainees, respectively. Compared to CADe, Deep-GI demonstrated lower FPR at FP thresholds of ≥0.5 (12.1 vs. 22.4) and ≥1 second (4.4 vs. 6.8) (both p<0.05). However, when the threshold was raised to ≥1.5 seconds, the FPR became comparable (2 vs. 2.4, p=0.3), while the PMR increased from 2% to 10%.
Conclusions
Compared to CADe, Deep-GI demonstrated a higher PDS with significantly lower FPR at ≥0.5- and ≥1-second thresholds. At the ≥1.5-second threshold, both systems showed comparable FPR with increased PMR.

Citations

Citations to this article as recorded by

Effectiveness of a novel artificial intelligence-assisted colonoscopy system for adenoma detection: a prospective, propensity score-matched, non-randomized controlled study in Korea
Jung-Bin Park, Jung Ho Bae
Clinical Endoscopy.2025; 58(1): 112. CrossRef
Understanding the discrepancy in the effectiveness of artificial intelligence-assisted colonoscopy: from randomized controlled trials to clinical reality
Jung Ho Bae
Clinical Endoscopy.2024; 57(6): 765. CrossRef
Edge Artificial Intelligence Device in Real-Time Endoscopy for Classification of Gastric Neoplasms: Development and Validation Study
Eun Jeong Gong, Chang Seok Bang, Jae Jun Lee
Biomimetics.2024; 9(12): 783. CrossRef

3,731 View
178 Download
4 Web of Science
3 Crossref

Real-time semantic segmentation of gastric intestinal metaplasia using a deep learning approach: Vitchaya Siripoppohn, Rapat Pittayanon, Kasenee Tiankanon, Natee Faknak, Anapat Sanpavat, Naruemon Klaikaew, Peerapon Vateekul, Rungsun Rerknimitr; Clin Endosc 2022;55(3):390-400. Published online May 9, 2022; DOI: https://doi.org/10.5946/ce.2022.005

Abstract PDF Supplementary Material PubReader ePub

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 improve the model accuracy. First, transfer learning was employed to the public colon datasets. Second, an image preprocessing technique contrast-limited adaptive histogram equalization was employed to produce clearer GIM areas. Third, data augmentation was applied for a more robust model. Lastly, the bilateral segmentation network model was applied to segment GIM areas in real time. The results were analyzed using different validity values.
Results
From the internal test, our AI model achieved an inference speed of 31.53 frames per second. GIM detection showed sensitivity, specificity, positive predictive, negative predictive, accuracy, and mean intersection over union in GIM segmentation values of 93%, 80%, 82%, 92%, 87%, and 57%, respectively.
Conclusions
The bilateral segmentation network combined with transfer learning, contrast-limited adaptive histogram equalization, and data augmentation can provide high sensitivity and good accuracy for GIM detection and segmentation.

Citations

Citations to this article as recorded by

Role of Artificial Intelligence in the Detection and Management of Premalignant and Malignant Lesions of the Esophagus and Stomach
Piyush Nathani, Prateek Sharma
Gastrointestinal Endoscopy Clinics of North America.2025; 35(2): 319. CrossRef
ViSwNeXtNet Deep Patch-Wise Ensemble of Vision Transformers and ConvNeXt for Robust Binary Histopathology Classification
Özgen Arslan Solmaz, Burak Tasci
Diagnostics.2025; 15(12): 1507. CrossRef
Applications of artificial intelligence in gastroscopy: a narrative review
Hu Chen, Shi-yu Liu, Si-hui Huang, Min Liu, Guang-xia Chen
Journal of International Medical Research.2024;[Epub] CrossRef
Computer‐aided diagnosis in real‐time endoscopy for all stages of gastric carcinogenesis: Development and validation study
Eun Jeong Gong, Chang Seok Bang, Jae Jun Lee
United European Gastroenterology Journal.2024; 12(4): 487. CrossRef
As how artificial intelligence is revolutionizing endoscopy
Jean-Francois Rey
Clinical Endoscopy.2024; 57(3): 302. CrossRef
Accuracy of artificial intelligence-assisted endoscopy in the diagnosis of gastric intestinal metaplasia: A systematic review and meta-analysis
Na Li, Jian Yang, Xiaodong Li, Yanting Shi, Kunhong Wang, Chih-Wei Tseng
PLOS ONE.2024; 19(5): e0303421. CrossRef
Real-time gastric intestinal metaplasia segmentation using a deep neural network designed for multiple imaging modes on high-resolution images
Passin Pornvoraphat, Kasenee Tiankanon, Rapat Pittayanon, Natawut Nupairoj, Peerapon Vateekul, Rungsun Rerknimitr
Knowledge-Based Systems.2024; 300: 112213. CrossRef
A Benchmark Dataset of Endoscopic Images and Novel Deep Learning Method to Detect Intestinal Metaplasia and Gastritis Atrophy
Jie Yang, Yan Ou, Zhiqian Chen, Juan Liao, Wenjian Sun, Yang Luo, Chunbo Luo
IEEE Journal of Biomedical and Health Informatics.2023; 27(1): 7. CrossRef
Real-time gastric intestinal metaplasia diagnosis tailored for bias and noisy-labeled data with multiple endoscopic imaging
Passin Pornvoraphat, Kasenee Tiankanon, Rapat Pittayanon, Phanukorn Sunthornwetchapong, Peerapon Vateekul, Rungsun Rerknimitr
Computers in Biology and Medicine.2023; 154: 106582. CrossRef
Diagnostic value of artificial intelligence-assisted endoscopy for chronic atrophic gastritis: a systematic review and meta-analysis
Yanting Shi, Ning Wei, Kunhong Wang, Tao Tao, Feng Yu, Bing Lv
Frontiers in Medicine.2023;[Epub] CrossRef
Recent Advances in Applying Machine Learning and Deep Learning to Detect Upper Gastrointestinal Tract Lesions
Malinda Vania, Bayu Adhi Tama, Hasan Maulahela, Sunghoon Lim
IEEE Access.2023; 11: 66544. CrossRef
Colon histology slide classification with deep-learning framework using individual and fused features
Venkatesan Rajinikanth, Seifedine Kadry, Ramya Mohan, Arunmozhi Rama, Muhammad Attique Khan, Jungeun Kim
Mathematical Biosciences and Engineering.2023; 20(11): 19454. CrossRef
Clinical Decision Support System for All Stages of Gastric Carcinogenesis in Real-Time Endoscopy: Model Establishment and Validation Study
Eun Jeong Gong, Chang Seok Bang, Jae Jun Lee, Hae Min Jeong, Gwang Ho Baik, Jae Hoon Jeong, Sigmund Dick, Gi Hun Lee
Journal of Medical Internet Research.2023; 25: e50448. CrossRef

5,780 View
222 Download
11 Web of Science
13 Crossref

Author index