Accuracy of artificial intelligence-assisted endoscopy in the diagnosis of gastric intestinal metaplasia: A systematic review and meta-analysis.

BACKGROUND AND AIMS: Gastric intestinal metaplasia is a precancerous disease, and a timely diagnosis is essential to delay or halt cancer progression. Artificial intelligence (AI) has found widespread application in the field of disease diagnosis. This study aimed to conduct a comprehensive evaluation of AI's diagnostic accuracy in detecting gastric intestinal metaplasia in endoscopy, compare it to endoscopists' ability, and explore the main factors affecting AI's performance. METHODS: The study followed the PRISMA-DTA guidelines, and the PubMed, Embase, Web of Science, Cochrane, and IEEE Xplore databases were searched to include relevant studies published by October 2023. We extracted the key features and experimental data of each study and combined the sensitivity and specificity metrics by meta-analysis. We then compared the diagnostic ability of the AI versus the endoscopists using the same test data. RESULTS: Twelve studies with 11,173 patients were included, demonstrating AI models' efficacy in diagnosing gastric intestinal metaplasia. The meta-analysis yielded a pooled sensitivity of 94% (95% confidence interval: 0.92-0.96) and specificity of 93% (95% confidence interval: 0.89-0.95). The combined area under the receiver operating characteristics curve was 0.97. The results of meta-regression and subgroup analysis showed that factors such as study design, endoscopy type, number of training images, and algorithm had a significant effect on the diagnostic performance of AI. The AI exhibited a higher diagnostic capacity than endoscopists (sensitivity: 95% vs. 79%). CONCLUSIONS: AI-aided diagnosis of gastric intestinal metaplasia using endoscopy showed high performance and clinical diagnostic value. However, further prospective studies are required to validate these findings.

Improving Adherence to Clinical Practice Guidelines for Managing Gastric Intestinal Metaplasia Among Gastroenterologists at a US Academic Institution.

BACKGROUND: Clinical guidelines reserve endoscopic surveillance after a gastric intestinal metaplasia (GIM) diagnosis for high-risk patients. However, it is unclear how closely guidelines are followed in clinical practice. We examined the effectiveness of a standardized protocol for the management of GIM among gastroenterologists at a US hospital. METHODS: This was a preintervention and postintervention study, which included developing a protocol and education of gastroenterologists on GIM management. For the preintervention study, 50 patients with GIM were randomly selected from a histopathology database at the Houston VA Hospital between January 2016 and December 2019. For the postintervention study, we assessed change in GIM management in a cohort of 50 patients with GIM between April 2020 and January 2021 and surveyed 10 gastroenterologists. The durability of the intervention was assessed in a cohort of 50 GIM patients diagnosed between April 2021 and July 2021. RESULTS: In the preintervention cohort, GIM location was specified (antrum and corpus separated) in 11 patients (22%), and Helicobacter pylori testing was recommended in 11 of 26 patients (42%) without previous testing. Gastric mapping biopsies were recommended in 14% and surveillance endoscopy in 2%. In the postintervention cohort, gastric biopsy location was specified in 45 patients (90%, P <0.001) and H. pylori testing was recommended in 26 of 27 patients without prior testing (96%, P <0.001). Because gastric biopsy location was known in 90% of patients ( P <0.001), gastric mapping was not necessary, and surveillance endoscopy was recommended in 42% ( P <0.001). One year after the intervention, all metrics remained elevated compared with the preintervention cohort. CONCLUSIONS: GIM management guidelines are not consistently followed. A protocol for GIM management and education of gastroenterologists increased adherence to H. pylori testing and GIM surveillance recommendations.

Pleomorphic adenoma with extensive squamous and mucinous metaplasia and a novel MALAT1::PLAG1 fusion gene.

Cases of metaplastic pleomorphic adenoma can be diagnostically challenging. Many of these cases fall into the Milan system's SUMP category, and some may be misdiagnosed. The author shows a case of pleomorphic adenoma with extensive squamous and mucinous metaplasia and a novel MALAT1::PLAG1 fusion.

Diagnostic validity and learning curve of non-NBI expert endoscopists in gastric intestinal metaplasia diagnosis.

BACKGROUND: Endoscopists' experience influences narrow-band imaging (NBI)-guided gastric intestinal metaplasia (GIM) diagnostic performance. We aimed to evaluate the general gastroenterologists (GE) performance in NBI-guided GIM diagnosis compared to NBI experts (XP) and assess GEs' learning curve. METHODS: A cross-sectional study was conducted between 10/2019 and 2/2022. Histology-proven GIM who underwent esophagogastroduodenoscopy (EGD) were randomly assessed by 2XPs or 3GEs. Endoscopists' performance on NBI-guided diagnoses were compared to the pathological diagnosis (gold standard) in five areas of the stomach according to the Sydney protocol. The primary outcome were GIM diagnosis validity scores of GEs compared to XPs. The secondary outcome was the minimum number of lesions required for GEs to achieve an accuracy of GIM diagnosis ≥ 80%. RESULTS: One thousand one hundred and fifty-five lesions from 189 patients (51.3% male, mean age 66 ± 10 years) were examined. GEs performed EGD in 128 patients with 690 lesions. the GIM diagnosis sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of GEs compared to the XPs, were 91% vs.93%, 73% vs.83%, 79% vs.83%, 89% vs.93%, and 83% vs.88%, respectively. GEs demonstrated lower specificity (mean difference - 9.4%; 95%CI - 16.3, 1.4; p = 0.008) and accuracy (mean difference - 5.1%; 95%CI - 3.3, 6.3; p = 0.006) compared to XPs. After 100 lesions (50% GIM), GEs achieved an accuracy of ≥ 80% and all diagnostic validity scores were comparable to the XPs (p < 0.05 all). CONCLUSIONS: Compared to XPs, GEs had lower specificity and accuracy for GIM diagnosis. The learning curve for a GE to achieve comparable performance to XPs would necessitate at least 50 GIM lesions. Created with BioRender.com.

Appendiceal Endometriosis with Intestinal Metaplasia Mimicking Appendiceal Mucinous Neoplasm - A Case Report and a Concise Review for the Practicing Pathologist.

Appendiceal endometriosis is a rare entity and, when accompanied by intestinal metaplasia, represents a challenging differential diagnosis with low-grade appendiceal mucinous neoplasm (LAMN). We present the case of a 47 years-old woman, with multiple surgical interventions for endometriosis, with persistent symptoms despite chronic hormonal treatment, with imaging showing stage IV endometriosis. Hence, en bloc low rectum resection with total hysterectomy and bilateral adnexectomy was performed, followed by appendectomy. Unexpectedly, despite the gross normal macroscopic appearance of the appendix, microscopy showed multiple endometriosis foci, consisting of endometrial glands embedded in varying amounts of endometrial stroma. As some of these glands were bordered by mucinous-type epithelium containing intestinal cells, Goblet cells, Paneth cells in addition to the presence of mucus-filled microcysts, immunohistochemistry (IHC) was performed in order to differentiate between intestinal-metaplasia and LAMN. IHC showed positivity of the endometrial epithelium for KRT7, estrogen receptor (ER) and progesterone receptor (PR). Both the appendiceal mucosa and the intestinal-type metaplastic epithelium of the glandular structures were positive for KRT20. Additionally, the endometrial stroma enclosing endometrial glands, as well as the stroma surrounding mucinous-type metaplastic epithelium, were positive for CD10, ER and PR. This patient's case draws attention to the rare occurrence of appendiceal endometriosis and the uncommon intestinal metaplasia, which can easily mimic LAMN, emphasizing the paramount importance of the differential diagnosis with this type of neoplasia.

Evaluation and comparison of subjective and objective anterior ocular surface damage in patients with type 2 diabetes mellitus and dry eye disease.

PURPOSE: To evaluate anterior ocular surface damage in patients with type 2 diabetes mellitus and dry eye disease in comparison to non-diabetic controls based on conjunctival impression cytology, objective scales (Efron, Oxford) and OSDI, to correlate vision-related quality of life with grades of squamous metaplasia in T2DM patients suffering from DED. METHODS: All participants underwent complete ophthalmologic examination including Shirmer test, TBUT, conjunctival/corneal staining (Oxford scheme), evaluation of conjunctival redness (Efron grading scale), and conjunctival impression cytology (Nelson's scale). The OSDI questionnaire was completed by both groups of patients to assess severity of DED and QoL. RESULTS: Squamous metaplasia was observed in 94% of the study group and 19.3% of controls (p = 0.0000). Based on the OSDI scores, 73.5% of patients reported mild DED and 26.5% suffered from moderate DED in the study group. The mean OSDI score for the study group with Nelson's grade 2 was 18 ± 3.52 and 20.8 ± 4.68 for Nelson's grade 3, respectively (p = 0.0745). Hence, no significant difference in QoL between grade 2 and grade 3 of squamous metaplasia was observed in patients of the study group. CONCLUSION: Impression cytology is a reliable minimally invasive tool for an accurate evaluation of the ocular surface damage in patients with DED and type 2 diabetes mellitus. Severe squamous metaplasia (Nelson's grade 3) was observed in 29.4% (10/34) of T2DM patients. In contrast, it was not detected in the control group (p = 0.0032). The absence of goblet cells in T2DM patients nether significantly reduces QoL nor contributes to the subjective DED severity (OSDI) due to complex pathways leading to DED. Thus, diagnosis of DED severity should not be solely based on subjective symptoms in this population.

[Helicobacter pylori detection patterns and related injuries through Sydney Protocol in a population of Antioquia, Colombia]. / Patrones de detección de Helicobacter pylori y lesiones relacionadas mediante protocolo Sydney en una población de Antioquia, Colombia.

OBJECTIVES: We sought to determine whether the endoscopies that met the Sydney protocol in a population of Antioquia had a greater detection of H. pylori and their associated lesions than the endoscopies that only took antrum samples. MATERIALS AND METHODS: We carried out a retrospective, cross-sectional and descriptive study. Adult patients undergoing upper endoscopy were included. Patients were divided into two groups depending on Sydney protocol compliance. The detection frequency was measured for H. pylori and premalignant lesions. RESULTS: 261 participants were included, 88 from which biopsies were taken with the Sydney protocol and 173 with biopsies taken exclusively from the gastric antrum. The main endoscopy indication was dyspepsia (35.6%). The detection of H. pylori, atrophic gastritis and intestinal metaplasia was 36.4%, 19.3% and 20.5% respectively in the Sydney group, and 30.1%, 11.6% and 9.8% in the control group. In the Sydney group, the detection of H. pylori was higher in the antrum and body (26.1%) than in antrum (6.8%) or body (3.4%) separately. The detection of atrophic gastritis and intestinal metaplasia was higher in antrum only (10.2% and 11.4% respectively) than in antrum and body or body separately. CONCLUSIONS: The omission of the Sydney protocol reduces the detection of H. pylori, atrophic gastritis and intestinal metaplasia by 9.4%, 29.4% and 27.7% respectively. The protocol must be implemented systematically in every gastrointestinal endoscopy center.

From part to whole, operative link on to endoscopic grading of gastric intestinal metaplasia, pathology to endoscopy: gastric intestinal metaplasia graded by endoscopy.

Objective: To conduct a systematic review and meta-analysis on the prediction of severity of gastric intestinal metaplasia (GIM) in localized and entire gastric mucosa using endoscopy. Methods: The authors searched Web of Science, PubMed, Embase and Cochrane Central Register of Controlled Trials and performed systematic searches on endoscopic grading of GIM of the entire stomach using Meta-DiSc and Stata. Results: Sensitivity and specificity for the stratified prediction of overall GIM were 0.91 (95% CI: 0.85-0.95) and 0.91 (95% CI: 0.88-0.93), respectively. Sensitivity in predicting the different grades of GIM was higher in operative link on GIM assessment grades 0, III and IV but lower in grades I and II. Conclusion: Digital chromoendoscopy is well suited to predicting the severity of localized and overall GIM.

Global variations in diagnostic guidelines for Barrett's esophagus.

Endoscopic diagnosis of gastroesophageal junction and Barrett's esophagus is essential for surveillance and early detection of esophageal adenocarcinoma and esophagogastric junction cancer. Despite its small size, the gastroesophageal junction has many inherent problems, including marked differences in diagnostic methods for Barrett's esophagus in international guidelines. To define Barrett's esophagus, gastroesophageal junction location should be clarified. Although gastric folds and palisade vessels are landmarks for identifying this junction, they are sometimes difficult to observe due to air entry or reflux esophagitis. The possibility of diagnosing a malignancy associated with Barrett's esophagus <1 cm, identified using palisade vessels, should be re-examined. Nontargeted biopsies of Barrett's esophagus are commonly used to detect intestinal metaplasia, dysplasia, and cancer as described in the Seattle protocol. Barrett's esophagus with intestinal metaplasia has a high risk of becoming cancerous. Furthermore, the frequency of cancer in patients with Barrett's esophagus without intestinal metaplasia is high, and the guidelines differ on whether to include the presence of intestinal metaplasia in the diagnosis of Barrett's esophagus. Use of advanced imaging technologies, including narrow-band imaging with magnifying endoscopy and linked color imaging, is reportedly valid for diagnosing Barrett's esophagus. Furthermore, artificial intelligence has facilitated the diagnosis of Barrett's esophagus through its deep learning and image recognition capabilities. However, it is necessary to first use the endoscopic definition of the gastroesophageal junction, which is common in all countries, and then elucidate the characteristics of Barrett's esophagus in each region, for example, length differences in the risk of carcinogenesis with and without intestinal metaplasia.

Quality of upper GI endoscopy: a prospective cohort study on impact of endoscopist education.

BACKGROUND AND AIMS: Guidelines on quality of upper GI (UGI) endoscopy have been proposed by the British Society of Gastroenterology (BSG) and European Society of Gastrointestinal Endoscopy (ESGE). However, these guidelines have not been evaluated in clinical practice. We aimed to measure the impact of endoscopist education on the quality of gastroscopy based on these guidelines and the association between compliance with guidelines and the detection of clinically significant premalignant pathology such as Barrett's esophagus (BE), esophageal squamous dysplasia, gastric intestinal metaplasia (GIM), and Helicobacter pylori. METHODS: Endoscopists participated in a 1-hour education session on recommended performance measures and endoscopic detection of premalignant pathologies. A controlled before and after study was performed, measuring compliance with guidelines and rates of detection of pathology in control and intervention groups. RESULTS: Over 2 years, 2719 procedures were performed: 1412 in the control group and 1307 in the intervention group. The proportion of procedures complying with guidelines was higher in the intervention group. The use of biopsy sampling protocols (eg, management of precancerous conditions of the stomach, 52% vs 91%; P = .007) and standardized terminology (eg, Forrest classification, 24% vs 68%; P < .001) was significantly higher. Detection of H pylori was higher in the intervention group (5.5% vs 9.8%, P = .003). Minimum inspection time of 7 minutes was associated with detection of BE (7.4% vs 2.0%, P < .001). CONCLUSIONS: A simple endoscopist education session enhanced the quality of UGI endoscopy by improving compliance with BSG and ESGE recommendations and increasing the detection of clinically significant pathology. A minimum inspection time of 7 minutes was associated with increased diagnostic yield and may be a feasible quality indicator for clinical practice.

Ethnicity Is an Important Consideration in Screening for Gastric Intestinal Metaplasia.

BACKGROUND: Gastric intestinal metaplasia (GIM) is a precursor to gastric adenocarcinoma, making it an attractive target for early detection by endoscopy. The aim of this study was to determine the prevalence, risk factors, and associated histologic findings of GIM among patients undergoing endoscopy in a diverse US population. METHODS: We conducted a retrospective, cross-sectional study of patients undergoing elective endoscopy with gastric biopsies at 6 academic and community centers in Houston, Texas. GIM prevalence was estimated with a 95% confidence interval (CI), and patient demographic and clinical characteristics were summarized using mean with standard deviation, or frequency with percentage. Generalized estimating equations (GEE) were used to compare characteristics between those with and without GIM. RESULTS: Our final cohort consisted of 2685 patients, including 216 cases with GIM and 2469 controls. The prevalence of GIM in our cohort was 8.04% (95% CI 7.07%, 9.14%). The mean age of GIM cases was higher than in the control group (59.8 vs 54.7 years, p < 0.0001). The prevalence of GIM in Asians, Hispanic, Black and Non-Hispanic Whites (NHW) was 14.7%, 11.7%, 9.8% and 5.8%, respectively. On multivariable analysis, factors associated with GIM include age (adj. OR 1.32 per 10 year increase, p < 0.0001), habitual smoking (adj. OR 1.68, p < 0.0001), and race (compared to NHW: Asian, adj. OR 2.34, p = 0.010; Hispanic, adj. OR 2.15, p < 0.001; Black, adj. OR 1.61, p < 0.001). CONCLUSION: Asians, Hispanics, and African Americans have higher rates of GIM than NHW. Ethnicity should be an important consideration on determining who to screen for GIM in the US.

Cytosponge-TFF3 Testing can Detect Precancerous Mucosal Changes of the Stomach.

Gastric intestinal metaplasia (GIM) and gastric atrophy (GA) are associated with increased risk of gastric cancer and are indications for endoscopic surveillance when affecting the proximal stomach.1 Endoscopic screening is not cost-effective in areas with low-moderate incidence of gastric cancer2; noninvasive methods to detect GIM/GA are currently lacking.3.

Complex Fibroadenoma with Pronounced Squamous Metaplasia: A Rare Case Report, Differential Diagnostic Considerations, and Associated Breast Cancer Risk.

Squamous metaplasia of the breast is a rare and unusual finding. A number of benign and malignant differential entities exist when squamous cells are present in a breast lesion. Our patient was found to have pronounced squamous metaplasia and keratin cysts arising in a complex fibroadenoma. The rare nature of squamous metaplasia arising in such a lesion poses some diagnostic challenges, as squamous epithelium and squamous metaplasia in the breast may raise suspicion for malignancy. Herein we present a unique case and discussion of benign and malignant differential entities. We also retrospectively reviewed a series of complex fibroadenomas in our institution, including the demographic and histologic features, and more importantly the associated breast cancer risk.

Endometrial osseous metaplasia complicated by secondary infertility: a case report.

Endometrial osseous metaplasia is a rare condition in which there is abnormal presence of bone in the endometrium. There is paucity of reported cases of this pathological condition in Africa and it is usually overlooked as a cause of infertility. Pathogenesis is not well understood but mostly occurs following pregnancy. Pathology may be suspected on ultrasound scan where a linear echogenic substance is seen in the endometrium but diagnosis is confirmed by and treated with hysteroscopy. We present a case of a 43-year-old woman with 2 previous miscarriages who presented with secondary infertility. She had an ultrasound scan done which revealed features suggestive of an intra-uterine copper device. She subsequently had hysteroscopy and a bone-like foreign body was found in the endometrium which was removed with the aid of a grasper and later sent for histopathological evaluation for which a subsequent diagnosis of endometrial osseous metaplasia was made. Indeed, endometrial intraosseous metaplasia should be considered an important differential cause of secondary infertility especially in patients with history of previous miscarriage. Confirmatory diagnosis can be made through hysteroscopy and/or histopathologically although the former is now used.

Simultaneous Recognition of Atrophic Gastritis and Intestinal Metaplasia on White Light Endoscopic Images Based on Convolutional Neural Networks: A Multicenter Study.

INTRODUCTION: Patients with atrophic gastritis (AG) or gastric intestinal metaplasia (GIM) have elevated risk of gastric adenocarcinoma. Endoscopic screening and surveillance have been implemented in high incidence countries. The study aimed to evaluate the accuracy of a deep convolutional neural network (CNN) for simultaneous recognition of AG and GIM. METHODS: Archived endoscopic white light images with corresponding gastric biopsies were collected from 14 hospitals located in different regions of China. Corresponding images by anatomic sites containing AG, GIM, and chronic non-AG were categorized using pathology reports. The participants were randomly assigned (8:1:1) to the training cohort for developing the CNN model (TResNet), the validation cohort for fine-tuning, and the test cohort for evaluating the diagnostic accuracy. The area under the curve (AUC), sensitivity, specificity, and accuracy with 95% confidence interval (CI) were calculated. RESULTS: A total of 7,037 endoscopic images from 2,741 participants were used to develop the CNN for recognition of AG and/or GIM. The AUC for recognizing AG was 0.98 (95% CI 0.97-0.99) with sensitivity, specificity, and accuracy of 96.2% (95% CI 94.2%-97.6%), 96.4% (95% CI 94.8%-97.9%), and 96.4% (95% CI 94.4%-97.8%), respectively. The AUC for recognizing GIM was 0.99 (95% CI 0.98-1.00) with sensitivity, specificity, and accuracy of 97.9% (95% CI 96.2%-98.9%), 97.5% (95% CI 95.8%-98.6%), and 97.6% (95% CI 95.8%-98.6%), respectively. DISCUSSION: CNN using endoscopic white light images achieved high diagnostic accuracy in recognizing AG and GIM.

Molecular Alterations in Gastric Preneoplastic Lesions and Early Gastric Cancer.

Prognosis of gastric cancer is dramatically improved by early diagnosis. Correa's cascade correlates the expression of some molecular markers with the progression of preneoplastic lesions toward carcinoma. This article reviews the diagnostic and prognostic values of molecular markers in complete (MUC2) and incomplete (MUC2, MUC5AC, and MUC6) intestinal metaplasia, gastric dysplasia/intra-epithelial neoplasia, and early gastric cancer. In particular, considering preinvasive neoplasia and early gastric cancer, some studies have demonstrated a correlation between molecular alterations and prognosis, for example, mucins phenotype in gastric dysplasia, and GATA6, TP53 mutation/LOH and MUC6 in early gastric cancer. Moreover, this review considers novelties from the literature regarding the (immuno)histochemical characterization of diffuse-type/signet ring cell gastric cancer, with particular attention to clinical outcomes of patients. The aim of this review is the evaluation of the state of the art regarding suitable biomarkers used in the pre-surgical phase, which can distinguish patients with different prognoses and help decide the best therapeutic strategy.