Introduction

Although diagnosis of gastric intestinal metaplasia (IM) using image-enhanced endoscopy is spreading, it has the disadvantage that special training is required and the accuracy depends on individual ability and experience. Therefore, we developed and validated an artificial intelligence (AI) model for diagnosing IM, and subsequently, compared its diagnostic accuracy with that of endoscopists.

Aims & Methods

This study included 6,487 white-light endoscopic (WLE) images from 1,454 patients with histologically confirmed IM from a single tertiary referral center in Korea between 2016 and 2020 (training/validation/test set, n=5,764/650/91, respectively). Histopathological diagnoses, including the presence and grade of IM, were set as the gold standard. The performance parameters of the AI-assisted IM diagnostic (AI-IM) model were compared with those of visual diagnoses by independent endoscopists (11 experts and 20 non-experts).

Results

The AI-IM model showed an accuracy of 0.813 (95% confidence interval (CI), 0.718–0.887), sensitivity of 0.891 (95% CI, 0.788–0.955), specificity of 0.630 (95% CI, 0.424–0.806), area under the curve of 0.760 (95% CI, 0.659–0.843), and weighted average F1-score of 0.809 (95% CI, 0.680–0.897). On comparative analysis, the diagnostic accuracy of the AI-IM model was superior to both experts (0.711 [95% CI, 0.702–0.720], P=0.017) and non-experts (0.664 [95% CI, 0.654–0.673], P<0.001). Other parameters of performance were also found to be significantly better.

Conclusion

The AI-IM model shows favorable diagnostic accuracy compared to both experts and non-experts in diagnosing gastric IM based on WLE images.

Introduction

Recently, artificial intelligence (AI)-based diagnostic support tools for early gastric cancer have been developed and reported to be superior to endoscopists (accuracy: 70% and sensitivity: 85%).¹ However, These tools could not guarantee reliable diagnostic accuracy in clinical practice. In previous reports, magnifying endoscopy has been recognized as superior to white-light imaging endoscopy for endoscopic diagnosis of early gastric cancers. Therefore, we developed an AI-based diagnostic support system using magnifying endoscopy with narrow band imaging (M-NBI) for early gastric cancers² and improved its application in clinical practice using nondegraded images obtained from selective depth inspection (SDI) output for real-time diagnosis. This study is the first to create an AI-based diagnostic support system using non-degraded M-NBI images obtained from SDI output, as several previous papers have analyzed damaged M-NBI images that were converted from various recording devices.^3,4

Aims & Methods

We built a new AI system (M-NBI AI) which was assembled using four different image recognition models with non-degraded M-NBI images (normal mucosa:1776 images, gastric cancers: 1947 images, and non-neoplastic lesions: 2451 images). We evaluated the performance of this M-NBI AI for diagnosis of early gastric cancer. The diagnostic performances of M-NBI AI and endoscopists (five specialists and five non-specialists) were compared using non-degraded M-NBI images (three images per lesion) of 50 early gastric cancer and 50 non-cancerous lesions. Early gastric cancers included histopathological types of well, moderately, and poorly differentiated adenocarcinomas and signet-ring cell adenocarcinomas. The primary outcome was the superiority of the M-NBI AI (based on accuracy) over the endoscopists. The secondary outcome was the superiority of the M-NBI AI (based on sensitivity) over the endoscopists.

Results

	M-NBI AI	Endoscopists
		Specialists	Non-specialists
Accuracy, % (95% CI)	87.0 (0.80–0.94)	80.0 (0.72–0.88)	71.0 (0.62–0.79)
Sensitivity, % (95% CI)	86.3 (0.77–0.96)	74.2 (0.63–0.85)	70.6 (0.58–0.83)
Specificity, % (95% CI)	88.0 (0.79–0.97)	89.0 (0.80–0.99)	71.0 (0.59–0.84)
PPV, % (95% CI)	88.0 (0.79–0.97)	92.0 (0.84–0.99)	72.0 (0.60–0.84)
NPV, % (95% CI)	86.0 (0.76–0.96)	68.0 (0.55–0.81)	70.0 (0.57–0.83)
PPV, positive predictive value; NPV, negative predictive value

The M-NBI AI was superior to the non-specialists based on accuracy (87.0%, 95%CI: 0.80–0.94 versus 71.0 %, 95%CI: 0.62–0.79; p<0.01), without being superior to the specialists (87.0%, 95%CI: 0.80–0.94 versus 80.0%, 95%CI: 0.72–0.88; p=0.18). The M-NBI AI was superior to the specialists and non-specialists based on sensitivity (86.3%, 95%CI: 0.77–0.96 versus 74.2%, 95%CI: 0.63–0.85 and 70.6%, 95%CI: 0.58–0.83; p<0.05, respectively).

Conclusion

The M-NBI AI was created as a new AI system that could be implemented for current endoscopy systems as a real-time diagnostic support tool for early gastric cancers. It demonstrated a robust performance and may indicate equalization of diagnostic accuracy and superadded effect over the white-light endoscopy for diagnosis of early gastric cancers in clinical practice.

References

1. Ishioka M et al. Dig Endosc. 2022. doi: 10.1111/den.14455.
2. Ueyama H et al. J Gastroenterol Hepatol. 2021;36(2):482-489.
3. Horiuchi Y et al. Dig. Dis. Sci. 2020;65:1355–1363.
4. He X et al. Gastrointest Endosc. 2022;95(4):671-678.

Introduction

The extent of gastric atrophy(GA) is closely related to the incidence of Intestinal-type gastric cancer (GC). According to the Kimura-Takemoto classification, determining whether the atrophy extends beyond the cardia is key to assess the extent of GA. However, there is significant difficulty in determining whether the cardia is atrophied under endoscopy.

Aims & Methods

This study developed a novel artificial intelligence (AI)-assisted white light endoscopy system for identifying the cardia part and diagnosing cardia atrophy . In this multicenter study, patients undergoing upper gastrointestinal endoscopy at 5 hospitals in China were prospectively included between November 2022 and December 2024. Among them, a total of 895 patients from 2 units were assigned to the training and validation sets (292 with cardia atrophy and 603 without cardia atrophy) to establish a cardia atrophy diagnostic model. 220 patients from our unit (84 with cardia atrophy and 136 without cardia atrophy) were included in the internal test set. Additionally, a total of 354 patients from 3 other units were included in the external test set (106 with cardia atrophy and 248 without cardia atrophy). In the internal and external test sets, 3 senior and 3 junior endoscopists made online diagnoses, comparing the performance differences between physicians with different levles of experience and the AI-assisted cardia atrophy detection system.

Results

This study established a AI-assisted cardia atrophy diagnostic model and tested its diagnostic performance with multicenter image data in internal and external tests. In the internal test dataset, the accuracy, sensitivity, and specificity of the AI-assisted system were 0.927, 0.941, and 0.919, respectively, with a PPV of 0.878, NPV of 0.962, and AUC of 0.967. In the external test dataset, the accuracy, sensitivity, and specificity were 0.918, 0.894, and 0.931 respectively, with a PPV of 0.874, NPV of 0.943, and AUC of 0.953. Further comparison of the diagnostic efficiency of the AI-assisted system with endoscopists of different levels of experience revealed that both in the internal and external test set, the diagnosis accuracy, sensitivity, specificity, PPV, and NPV of the AI-assisted system were all higher than those of senior endoscopists. TheAI-assisted cardia atrophy diagnostic ROC curve area (AUC) was 0.967 and 0.953 in the internal and external test sets, respectively. Heat map analysis further showed a high consistency between theAI-assisted system and endoscopists in cardia atrophy diagnosis.

Conclusion

Our newly developed AI-assisted cardia atrophy diagnostic system shows superior performance in identifying cardia atrophy compared to senior endoscopists, and can be used to guide white light endoscopic judgment and targeted biopsies for cardia atrophy.

Introduction

AI diagnosis is used in several medical fields; however, machine learning using deep learning methods is particularly effective in diagnostic imaging and shows high diagnostic capability even in the field of endoscopy. In Japan, endoscopes manufactured by Companies A and B are generally used, and there is a possibility that differences in the image quality will affect AI diagnosis. However, there is no report of studies comparing the AI diagnostic capabilities on images taken by endoscopes of two companies.

Aims & Methods

In endoscopic AI diagnosis of early gastric cancer, the AI diagnostic capabilities were compared using images obtained by endoscopes of Companies A and B for the purpose of clarifying whether there is a need to consider the differences between the endoscopes used. For 30 lesions of 27 patients who underwent endoscopic submucosal dissection for early gastric cancer from April 2019 to March 2022 at our hospital, 356 and 338 endoscopic images of Companies A and B were the target of analysis, respectively.The images were white light (WLI), chromoendoscopy (indigo carmine) and image-enhanced endoscopy, Company A used narrow band imaging (NBI), and Company B used blue laser imaging (BLI).The images were analyzed by AI Medical Systems Inc. using an AI diagnostic system constructed by having UNET learn images taken by either Company A or B's endoscopes as training images. The diagnostic capability was assessed by comparing the specialist-marked correct range of early gastric cancer with an AI-diagnosed range of early gastric cancer, and using a DiceScore of 1.0 for a complete match and 0.0 for no match based on the area of the match.

Results

There was no significant difference in the DiceScore between the endoscopes of both companies in WLI; however, in indigo, Company B scored significantly higher than Company A. There was no significant difference between NBI and BLI. A stratification analysis by macroscopic examination of the lesions showed that in 0-IIc, Company A scored significantly higher in WLI than Company B, while in indigo, Company B scored significantly higher than Company A. In 0-IIa+IIc, Company B scored significantly higher than Company A in WLI; however, there was no difference between the two companies in indigo. In comparison by macroscopic examination of the lesions, 0-IIa+IIc lesions scored significantly higher than 0-IIc lesions in indigo for Company A, and in WLI for Company B. When the lesions were divided into a maximum diameter of <2 cm, 2–3 cm, and ≥3 cm, lesions ≥3 cm scored lower than lesions in the other groups.

Conclusion

Endoscopic images of Company B tended to have higher sharpness and stronger bluish color compared to endoscopic images of Company A. This might be the reason why the diagnostic capability improved after indigo-carmine scattering. Therefore, proactive scattering of indigo carmine was considered preferable when observing with the Company B endoscope. Presumably, the reason 0-IIa+IIc lesions had higher diagnostic performance than 0-IIc lesions was due to differences in the elevation of the lesions. The Company A endoscope was considered significantly superior for 0-IIc lesions, which are easily overlooked in clinical practice. The complexity of the morphology of the lesion increases in large lesions, which widens the gap between the AI diagnostic range and correct range. There are lesions wherein the AI diagnostic performance increased with both endoscopes of Company A and that of Company B. Therefore, it is preferable to use the endoscopes in AI diagnosis taking these facts into consideration.

References

Hirasawa T, Aoyama K, Tanimoto T, et al: Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images. Gastric Cancer 21; 653-660: 2018
Ikenoyama Y, Hirasawa T, Ishioka M, et al: Detecting early gastric cancer; Comparison between the diagnostic ability of convolutional neural networks and endoscopists. Dig Endosc 33; 141-150: 2021
Miyaki R, Yoshida S, Tanaka S, et al: A computer system to be used with laser-based endoscopy for quantitative diagnosis of early gastric cancer. J Clin Gastroenterol 49; 108-115: 2015
Horiuchi Y, Aoyama K, Tokai Y, et al: Convolutional neural network for differentiating gastric cancer from gastritis using magnified endoscopy with narrow band imaging. Dig Dis Sci 65; 1355-1363: 2020
Ling T, Wu L, Fu Y, et al: A deep learning-based system for identifying differentiation status and delineating the margins of early gastric cancer in magnifying narrow-band imaging endoscopy. Endoscopy 53; 469-477: 2021
Hamada K, Kawahara Y, Tanimoto T, et al: Application of convolutional neural networks for evaluating the depth of invasion of early gastric cancer based on endoscopic images. J Gastroenterol Hepatol 37; 352-357: 2022

Introduction

Gastric intestinal metaplasia (GIM) is a well-established precursor to gastric adenocarcinoma, with optimal management involving accurate endoscopic recognition, histopathological characterisation and appropriate follow-up planning. While international guidelines, such as MAPS II and III, have reinforced these quality indicators, the extent to which they are reflected in routine clinical practice remains uncertain in the Australian setting (1,2).

Aims & Methods

This study aimed to evaluate longitudinal trends in GIM diagnosis and management over a 13-year period at a tertiary Australian centre. We retrospectively reviewed all patients who underwent index gastroscopy with biopsy at a single centre between 1 January 2010 and 1 April 2023. Data collected included GIM detection method, Helicobacter pylori (H. pylori) testing and eradication status and histological reporting of GIM extent and subtype. Outcomes were compared before and after 1 January 2020 to reflect timing of the publication of the MAPS II guidelines. Categorical and continuous variables were analysed using Chi-square and t-tests, respectively.

Results

Among 13,987 patients, GIM was identified in 1,722 procedures involving 1,318 individuals. Of these, 1,149 procedures occurred pre-2020 and 573 post-2020 (mean age 66.4 ± 14.1 vs 66.2 ± 13.7 years; p = 0.832; 47.2% vs 46.6% male; p = 0.486). Endoscopic and histological recognition occurred in 15.9% of procedures, increasing from 10.4% pre-2020 to 27.1% post-2020 (p < 0.001), and from 6.5% to 15.6% when GIM screening procedures were excluded (p < 0.001). Dysplasia was detected in 3.7% of cases, with similar rates pre- and post-2020 (4.1% vs 2.8%; p = 0.176). The proportion of visible dysplasia also increased post-2020 (55.3% to 75.0%), but this was not significant (p = 0.165). Histological extent was reported in 64.1% of cases, with no significant difference between time periods (65.2% vs 62.0%; p = 0.188). Reporting of histological subtype increased from 5.1% to 21.6% (p < 0.001), though remained low overall (10.6%). Mean procedure duration was 11.2 ± 8.4 minutes, with no significant difference post-2020 (11.0 ± 6.9 vs 11.7 ± 11.2; p = 0.136), while the number of images captured increased significantly from 4.9 ± 2.6 to 7.1 ± 3.4 (p < 0.001). Specific H. pylori testing beyond histology was performed in 27.0% of patients, increasing slightly post-2020 (27.0% to 29.5%; p < 0.001). Eradication was confirmed in 54.2% of patients with a positive H. pylori diagnosis, rising from 48.9% pre-2020 to 61.7% post-2020 (p = 0.007). Follow-up within three years (excluding referrals for advanced therapy) increased from 15.7% to 38.7% (p < 0.001), and any follow-up recommendation documented rose from 30.5% to 58.6% (p < 0.001).

Conclusion

Post-2020, improvements were seen in GIM recognition, follow-up documentation and H. pylori eradication confirmation, though overall adherence remained suboptimal. A follow-up survey of endoscopists is underway to assess whether changes in practice are attributable to MAPS II or other factors. These findings reflect ongoing heterogeneity in clinical practice and highlight the need for further education efforts for endoscopists and pathologists alike.

References

1. Pimentel-Nunes P, Libânio D, Marcos-Pinto R, Areia M, Esposito G, Garrido M, et al. Management of epithelial precancerous conditions and lesions in the stomach (MAPS II): ESGE, EHMSG and ESP guidelines. Endoscopy. 2019;51(4):365–388. doi:10.1055/a-0859-1883.
2. Dinis-Ribeiro M, Libânio D, Uchima H, et al. Management of epithelial precancerous conditions and early neoplasia of the stomach (MAPS III): ESGE, EHMSG and ESP guideline update 2025. Endoscopy. Published online March 20, 2025. doi:10.1055/a-2529-5025.

Introduction

There are several reports about the diagnosis of early gastric cancers (EGCs) using artificial intelligence (AI) systems, but satisfactory data for sensitivity and specificity are not yet available. Linked color imaging (LCI) produces high color contrast between malignant lesions and surrounding mucosa compared to white light imaging (WLI). Therefore, LCI combined with AI (LCI-AI) has the potential to further improve the diagnosis of gastric cancer compared with WLI combined with AI (WLI-AI). We developed three new LCI-AI models to determine their sensitivity and specificity for the diagnosis of EGCs.

Aims & Methods

Three models including a convolutional neural network (CNN) model (high resolution net (HRNet)), a transformer model (Segformer) and a hybrid (combined CNN and transformer) model (Uniformer), were based on MMSegmentation. When each model recognized a gastric cancer lesion from test image data, it was shown with the existing position as a blue area on WLI images and green area on LCI images. Non-neoplastic mucosa was shown as a black area on both images. Endoscopic images using WLI and LCI (LASEREO 7000 system series and scopes of EG-L600ZW and EG-L600ZW7, Fujifilm Corporation, Tokyo, Japan) were collected from patients with EGCs from January 2015 to December 2018 at Jichi Medical University Hospital. A total of 1970 images including 1179 WLI and 791 LCI images of 236 EGCs were used for training the three LCI-AI models. Another set of 414 EGC images was selected for validation from 43 cases. Primary and secondary endpoints were the sensitivity and specificity of each AI model, respectively.
The image-based performance metric was based on Dice loss, calculated by subtracting the mean Dice similarity score. A Dice score >20% was defined as the correct diagnosis of cancer because EGCs sometimes have unclear demarcation lines. The correct diagnosis of a non-malignant lesion was defined as no reactive black areas in surrounding mucosae. Each case had from four to 21 images. Therefore, the median Dice score was used as a representative value in each case to evaluate performance. All three models’ programming and data analysis were supported by AI Medical Service Inc. (Tokyo, Japan).

Results

Analysis of lesions in all EGC images showed both sensitivity (82.8%) and specificity (83.4%) with LCI-AI to be high and similar to those with WLI-AI (83.1% and 84.3%, respectively). Sensitivities of LCI-AI/ WLI-AI among HRNet, SegFormer and UniFormer were 80.9%/81.6% (p=0.625), 83.8%/83.8% (p=0.224) and 83.8%/83.8% (p=0.450), respectively and specificities were 80.0%/86.0% (p=0.120), 86.4%/84.8% (p=0.672) and 86.8%82.0%/ (p=0.214), respectively. Representative Dice values among cases with EGCs showed sensitivities for LCI-AI using HRNet, SegFormer and UniFormer to be extremely high, at 92.7% 90.9% and 93.0%, respectively, although not significantly different when compared to those using WLI-AI, 84.6% (p=0.67), 85.4% (p=0.15) and 80.5% (p=0.19), respectively. Higher sensitivities were found regardless of lesion size, morphology, and Helicobacter pylori status. All sensitivities using LCI-AI were higher than 80% whereas those using WLI-AI varied from 64% to 89%.

Conclusion

LCI-AI showed high sensitivity and specificity for the diagnosis of EGCs using all three models tested, suggesting potential for practical clinical use in the near future.

Disclosure

Hiroyuki Osawa and Hironori Yamamoto have consultant relationships with Fujifilm Corporation and have received honoraria, grants and royalties from the company. Hiroyuki Osawa has a consultant relationship with AI Medical survice inc. and has recieved honoraria.This study received no funding from Fujifilm Corporation and AI Medical survice inc. nor any other funding source.