Clinical Outcomes of Endoscopic Resection for Low-Grade Dysplasia and High-Grade Dysplasia on Gastric Pretreatment Biopsy: Korea ESD Study Group

Gastric Intestinal Metaplasia: Real Culprit or Innocent Bystander as a Precancerous Condition for Gastric Cancer?

Gastric intestinal metaplasia (GIM), which denotes conversion of gastric mucosa into an intestinal phenotype, can occur in all regions of the stomach, including cardiac, fundic, and pyloric mucosa. Since the earliest description of GIM, its association with gastric cancer of the differentiated (intestinal) type has been a well-recognized concern. Many epidemiologic studies have confirmed GIM to be significantly associated with subsequent gastric cancer development. Helicobacter pylori, the principal etiologic factor for gastric cancer, plays the most important role in predisposing to GIM. Although the role of GIM in the stepwise progression model of gastric carcinogenesis (the so-called "Correa cascade") has come into question recently, we review the scientific evidence that strongly supports this long-standing model and propose a new progression model that builds on the Correa cascade. Eradication of H pylori is the most important method for preventing gastric cancer globally, but the effect of eradication on established GIM, is limited, if any. Endoscopic surveillance for GIM may, therefore, be necessary, especially when there is extensive corpus GIM. Recent advances in image-enhanced endoscopy with integrated artificial intelligence have facilitated the identification of GIM and neoplastic lesions, which will impact preventive strategies in the near future.

Endoscopic resection of early gastric cancer

Endoscopic resection (ER) is an effective treatment for early gastric cancer (EGC) without metastases. Existing endoscopic mucosal resection (EMR) is easy to perform, has few complications, and can be applied when the lesion size is small. However, en bloc and complete resection rates vary depending on the size and severity of the lesion. EMR using the cap-mounted panendoscopic method and EMR after circumferential preamputation of the lesion are useful in the treatment of EGC. However, completely oversized lesions (≥2 cm) and lesions associated with ulcers or submucosal fibrosis are more likely to fail resection. Endoscopic submucosal dissection has been widely used to resect tumors larger than 2 cm in diameter and has a higher acceptable complication rate and en bloc and complete resection rates than EMR. ER for EGC is superior to surgical resection in terms of improving patient quality of life. Additionally, compared to surgery, emergency rooms have a lower rate of treatment-related complications, shorter hospital stays, and lower costs. Accordingly, the indications for ER are expanding in the field of therapeutic endoscopy. Long-term outcomes regarding recurrence are excellent in both absolute and extended criteria for ER in EGC. Close surveillance should be performed after ER to detect early metachronous gastric cancer and precancerous lesions that can be treated with ER. Follow-up gastroscopy and abdominopelvic computed tomography scans every 6 to 12 months are recommended for patients who undergo curative ER for EGC on absolute or extended criteria.

Endoscopic resection of gastric low-grade dysplasia with high risk factors is associated with decreased advanced neoplasia: a single-center retrospective cohort study

BACKGROUND

The natural course of gastric low-grade dysplasia (LGD) remains unclear, and there are inconsistent management recommendations among guidelines and consensus.

OBJECTIVE

This study aimed to investigate the incidence of advanced neoplasia in patients with gastric LGD and identify the related risk factors.

METHODS

Cases of biopsy demonstrated LGD (BD-LGD) at our center from 2010 to 2021 were reviewed retrospectively. Risk factors related to histological progression were identified, and outcomes of patients based on risk stratification were evaluated.

RESULTS

Ninety-seven (23.0%) of 421 included BD-LGD lesions were diagnosed as advanced neoplasia. Among 409 superficial BD-LGD lesions, lesion in the upper third of the stomach, H. pylori infection, larger size, and narrow band imaging (NBI)-positive findings were independent risk factors of progression. NBI-positive lesions and NBI-negative lesions with or without other risk factors had 44.7%, 1.7%, and 0.0% risk of advanced neoplasia, respectively. Invisible lesions, visible lesions (VLs) without a clear margin, and VLs with a clear margin and size ≤ 10 mm, or > 10 mm had 4.8%, 7.9%, 16.7%, and 55.7% risk of advanced neoplasia, respectively. In addition, endoscopic resection decreased the risk of cancer (P < 0.001) and advanced neoplasia (P < 0.001) in patients with NBI-positive lesions, but not in NBI-negative patients. Similar results were found in patients with VLs with clear margin and size > 10 mm. Moreover, NBI-positive lesions had higher sensitivity and lower specificity for predicting advanced neoplasia than VLs with a clear margin and size > 10 mm determined by white-light endoscopy (97.6% vs. 62.7%, P < 0.001; and 63.0% vs. 85.6%, P < 0.001, respectively).

CONCLUSION

Progression of superficial BD-LGD is associated with NBI-positive lesions, as well as with VLs with a clear margin (size > 10 mm) if NBI is unavailable, and selective resection of those lesions offers benefits for patients by decreasing the risk of advanced neoplasia.

Diagnosis and segmentation effect of the ME-NBI-based deep learning model on gastric neoplasms in patients with suspected superficial lesions - a multicenter study

Background

Endoscopically visible gastric neoplastic lesions (GNLs), including early gastric cancer and intraepithelial neoplasia, should be accurately diagnosed and promptly treated. However, a high rate of missed diagnosis of GNLs contributes to the potential risk of the progression of gastric cancer. The aim of this study was to develop a deep learning-based computer-aided diagnosis (CAD) system for the diagnosis and segmentation of GNLs under magnifying endoscopy with narrow-band imaging (ME-NBI) in patients with suspected superficial lesions.

Methods

ME-NBI images of patients with GNLs in two centers were retrospectively analysed. Two convolutional neural network (CNN) modules were developed and trained on these images. CNN1 was trained to diagnose GNLs, and CNN2 was trained for segmentation. An additional internal test set and an external test set from another center were used to evaluate the diagnosis and segmentation performance.

Results

CNN1 showed a diagnostic performance with an accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of 90.8%, 92.5%, 89.0%, 89.4% and 92.2%, respectively, and an area under the curve (AUC) of 0.928 in the internal test set. With CNN1 assistance, all endoscopists had a higher accuracy than for an independent diagnosis. The average intersection over union (IOU) between CNN2 and the ground truth was 0.5837, with a precision, recall and the Dice coefficient of 0.776, 0.983 and 0.867, respectively.

Conclusions

This CAD system can be used as an auxiliary tool to diagnose and segment GNLs, assisting endoscopists in more accurately diagnosing GNLs and delineating their extent to improve the positive rate of lesion biopsy and ensure the integrity of endoscopic resection.

A Prediction Model Based on the Risk Factors Associated with Pathological Upgrading in Patients with Early-Stage Gastric Neoplasms Diagnosed by Endoscopic Forceps Biopsy

Background/Aims

The discrepancies between the diagnosis of preoperative endoscopic forceps biopsy (EFB) and endoscopic submucosal dissection (ESD) in patients with early gastric neoplasm (EGN) exist objectively. Among them, pathological upgrading directly influences the accuracy and appropriateness of clinical decisions. The aims of this study were to investigate the risk factors for the discrepancies, with a particular focus on pathological upgrading and to establish a prediction model for estimating the risk of pathological upgrading after EFB.

Methods

We retrospectively collected the records of 978 patients who underwent ESD from December 1, 2017 to July 31, 2021 and who had a final histopathology determination of EGN. A nomogram to predict the risk of pathological upgrading was constructed after analyzing subgroup differences among the 901 lesions enrolled.

Results

The ratio of pathological upgrading was 510 of 953 (53.5%). Clinical, laboratorial and endoscopic characteristics were analyzed using univariable and binary multivariable logistic regression analyses. A nomogram was constructed by including age, history of chronic atrophic gastritis, symptoms of digestive system, blood high density lipoprotein concentration, macroscopic type, pathological diagnosis of EFB, uneven surface, remarkable redness, and lesion size. The C-statistics were 0.804 (95% confidence interval, 0.774 to 0.834) and 0.748 (95% confidence interval, 0.664 to 0.832) in the training and validation set, respectively. We also built an online webserver based on the proposed nomogram for convenient clinical use.

Conclusions

The clinical value of identifying the preoperative diagnosis of EGN lesions is limited when using EFB separately. We have developed a nomogram that can predict the probability of pathological upgrading with good calibration and discrimination value.

Management of Helicobacter pylori infection: the Maastricht VI/Florence consensus report

Helicobacter pyloriInfection is formally recognised as an infectious disease, an entity that is now included in the International Classification of Diseases 11th Revision. This in principle leads to the recommendation that all infected patients should receive treatment. In the context of the wide clinical spectrum associated with Helicobacter pylori gastritis, specific issues persist and require regular updates for optimised management.The identification of distinct clinical scenarios, proper testing and adoption of effective strategies for prevention of gastric cancer and other complications are addressed. H. pylori treatment is challenged by the continuously rising antibiotic resistance and demands for susceptibility testing with consideration of novel molecular technologies and careful selection of first line and rescue therapies. The role of H. pylori and antibiotic therapies and their impact on the gut microbiota are also considered.Progress made in the management of H. pylori infection is covered in the present sixth edition of the Maastricht/Florence 2021 Consensus Report, key aspects related to the clinical role of H. pylori infection were re-evaluated and updated. Forty-one experts from 29 countries representing a global community, examined the new data related to H. pylori infection in five working groups: (1) indications/associations, (2) diagnosis, (3) treatment, (4) prevention/gastric cancer and (5) H. pylori and the gut microbiota. The results of the individual working groups were presented for a final consensus voting that included all participants. Recommendations are provided on the basis of the best available evidence and relevance to the management of H. pylori infection in various clinical fields.

Deep learning for automatic diagnosis of gastric dysplasia using whole-slide histopathology images in endoscopic specimens

BACKGROUND

Distinguishing gastric epithelial regeneration change from dysplasia and histopathological diagnosis of dysplasia is subject to interobserver disagreement in endoscopic specimens. In this study, we developed a method to distinguish gastric epithelial regeneration change from dysplasia and further subclassify dysplasia. Meanwhile, optimized the cross-hospital diagnosis using domain adaption (DA).

METHODS

897 whole slide images (WSIs) of endoscopic specimens from two hospitals were divided into training, internal validation, and external validation cohorts. We developed a deep learning (DL) with DA (DLDA) model to classify gastric dysplasia and epithelial regeneration change into three categories: negative for dysplasia (NFD), low-grade dysplasia (LGD), and high-grade dysplasia (HGD)/intramucosal invasion neoplasia (IMN). The diagnosis based on the DLDA model was compared to 12 pathologists using 100 gastric biopsy cases.

RESULTS

In the internal validation cohort, the diagnostic performance measured by the macro-averaged area under the receiver operating characteristic curve (AUC) was 0.97. In the independent external validation cohort, our DLDA models increased macro-averaged AUC from 0.67 to 0.82. In terms of the NFD and HGD cases, our model's diagnostic sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were significantly higher than junior and senior pathologists. Our model's diagnostic sensitivity, NPV, was higher than specialist pathologists.

CONCLUSIONS

We demonstrated that our DLDA model could distinguish gastric epithelial regeneration change from dysplasia and further subclassify dysplasia in endoscopic specimens. Meanwhile, achieved significant improvement of diagnosis cross-hospital.