Current status of endoscopic submucosal dissection for the management of early gastric cancer: A Korean perspective

Lightweight deep learning model incorporating an attention mechanism and feature fusion for automatic classification of gastric lesions in gastroscopic images

Accurate diagnosis of various lesions in the formation stage of gastric cancer is an important problem for doctors. Automatic diagnosis tools based on deep learning can help doctors improve the accuracy of gastric lesion diagnosis. Most of the existing deep learning-based methods have been used to detect a limited number of lesions in the formation stage of gastric cancer, and the classification accuracy needs to be improved. To this end, this study proposed an attention mechanism feature fusion deep learning model with only 14 million (M) parameters. Based on that model, the automatic classification of a wide range of lesions covering the stage of gastric cancer formation was investigated, including non-neoplasm(including gastritis and intestinal metaplasia), low-grade intraepithelial neoplasia, and early gastric cancer (including high-grade intraepithelial neoplasia and early gastric cancer). 4455 magnification endoscopy with narrow-band imaging(ME-NBI) images from 1188 patients were collected to train and test the proposed method. The results of the test dataset showed that compared with the advanced gastric lesions classification method with the best performance (overall accuracy = 94.3%, parameters = 23.9 M), the proposed method achieved both higher overall accuracy and a relatively lightweight model (overall accuracy =95.6%, parameter = 14 M). The accuracy, sensitivity, and specificity of low-grade intraepithelial neoplasia were 94.5%, 93.0%, and 96.5%, respectively, achieving state-of-the-art classification performance. In conclusion, our method has demonstrated its potential in diagnosing various lesions at the stage of gastric cancer formation.

Artificial Intelligence in Gastric Cancer: Identifying Gastric Cancer Using Endoscopic Images with Convolutional Neural Network

Simple Summary

Gastric cancer (GC) is one of the most newly diagnosed cancers and the fifth leading cause of death globally. Previous studies reported that the detection rate of gastric cancer (EGC) at an earlier stage is low, and the overall false-negative rate with esophagogastroduodenoscopy (EGD) is up to 25.8%, which often leads to inappropriate treatment. Accurate diagnosis of EGC can reduce unnecessary interventions and benefits treatment planning. Convolutional neural network (CNN) models have recently shown promising performance in analyzing medical images, including endoscopy. This study shows that an automated tool based on the CNN model could improve EGC diagnosis and treatment decision.

Abstract

Gastric cancer (GC) is one of the most newly diagnosed cancers and the fifth leading cause of death globally. Identification of early gastric cancer (EGC) can ensure quick treatment and reduce significant mortality. Therefore, we aimed to conduct a systematic review with a meta-analysis of current literature to evaluate the performance of the CNN model in detecting EGC. We conducted a systematic search in the online databases (e.g., PubMed, Embase, and Web of Science) for all relevant original studies on the subject of CNN in EGC published between 1 January 2010, and 26 March 2021. The Quality Assessment of Diagnostic Accuracy Studies-2 was used to assess the risk of bias. Pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio were calculated. Moreover, a summary receiver operating characteristic curve (SROC) was plotted. Of the 171 studies retrieved, 15 studies met inclusion criteria. The application of the CNN model in the diagnosis of EGC achieved a SROC of 0.95, with corresponding sensitivity of 0.89 (0.88–0.89), and specificity of 0.89 (0.89–0.90). Pooled sensitivity and specificity for experts endoscopists were 0.77 (0.76–0.78), and 0.92 (0.91–0.93), respectively. However, the overall SROC for the CNN model and expert endoscopists was 0.95 and 0.90. The findings of this comprehensive study show that CNN model exhibited comparable performance to endoscopists in the diagnosis of EGC using digital endoscopy images. Given its scalability, the CNN model could enhance the performance of endoscopists to correctly stratify EGC patients and reduce work load.

UR, Jesus VHF, Jr WLC, Prolla G. Brazilian Group of Gastrointestinal Tumours' consensus guidelines for the management of gastric cancer

Gastric cancer is among the ten most common types of cancer worldwide. Most cases and deaths related to the disease occur in developing countries. Local socio-economic, epidemiologic and healthcare particularities led us to create a Brazilian guideline for the management of gastric carcinomas. The Brazilian Group of Gastrointestinal Tumors (GTG) invited 50 physicians with different backgrounds, including radiology, pathology, endoscopy, nuclear medicine, genetics, oncological surgery, radiotherapy and clinical oncology, to collaborate. This document was prepared based on an extensive review of topics related to heredity, diagnosis, staging, pathology, endoscopy, surgery, radiation, systemic therapy and follow-up, which was followed by presentation, discussion, and voting by the panel members. It provides updated evidence-based recommendations to guide clinical management of gastric carcinomas in several scenarios and clinical settings.

Multibending scope use for reduction of perforation risks in endoscopic submucosal dissection

AIMS

To identify areas that are difficult to access by the single scope at the time of endoscopic submucosal dissection (ESD) and examine the effectiveness, en-bloc, R0 resection, and perforation rate after changing to multibending scope at the same site.

MATERIAL AND METHODS

When the direct visualization of the submucosal layer became impossible with Q260J or in the position where the device became vertical and peeling became impossible in parallel, we decided to change to the multibending 2TQ260M scope to record the position where the change was effective and the perforation rate.

RESULTS

A total of 315 lesions were studied. Of the 12 sites, ESD was completed using the Q260J alone at four sites. The 2TQ260M scope was used with greater frequency at the fornix (88.9%) and on the line of the lesser curvature of the stomach (37.1%). In the cases with observed perforations (0.9%), the submucosal layer was not elevated due to the adhesion caused by strong fibrosis. None of the cases involving the change to 2TQ260M was ineffective, nor were perforations observed, and all resected specimens were en-bloc and R0 resections.

CONCLUSIONS

The success rate of this scope may help clinicians perform ESD with greater understanding.

Long-Term Outcome After Endoscopic Submucosal Dissection for Early Gastric Cancer in Non-neoplastic Pathology Results

BACKGROUND

After endoscopic submucosal dissection (ESD) for early gastric cancer (EGC), negative pathological findings cause concern about the adequacy of the procedure and local recurrence after ESD.

AIM

To investigate the incidence of local recurrence in cases with negative pathological findings after ESD for EGC and pathologically complete resection (CR) during long-term follow-up.

METHODS

We reviewed 453 patients who underwent ESD for ECG from January 2007 to December 2010, respectively. Of these patients, in 17 cases the pathology results confirmed no residual tumor (NRT), and in 421 cases they showed CR in the ESD specimen. Finally, 17 NRT and 358 CR cases were followed up during surveillance. Patient characteristics, endoscopic and pathological data were analyzed for risk factors of local recurrence. We also re-evaluated the pathology of the NRT group to identify hidden malignant cells in the previous ESD specimens.

RESULTS

There was no difference between the two groups in terms of recurrence during follow-up surveillance (median 55.7 months). Late local recurrence of EGC was found in two cases (11.8%) in the NRT group, and three early local recurrences (5.6%) were found in the CR group. A review of the pathology in the NRT group revealed hidden malignant cells in five patients (29.4%).

CONCLUSIONS

Even when the pathological report indicates NRT after ESD, it might be necessary to re-evaluate ESD specimens with a width <2 mm, and long-term endoscopic surveillance should be routinely used for detecting local EGC recurrence after ESD.

Risk Factors for Additional Surgery after Iatrogenic Perforations due to Endoscopic Submucosal Dissection

Objectives. Endoscopic resection (ER) is commonly performed to treat gastric epithelial neoplasms and subepithelial tumors. The aim of this study was to predict the risk factors for surgery after ER-induced perforation. Methods. We retrospectively reviewed the data on patients who received gastric endoscopic submucosal dissection (ESD) or endoscopic mucosal resection (EMR) between January 2010 and March 2015. Patients who were confirmed to have perforation were classified into surgery and nonsurgery groups. We aimed to determine the risk factors for surgery in patients who developed iatrogenic gastric perforations. Results. A total of 1183 patients underwent ER. Perforation occurred in 69 (5.8%) patients, and 9 patients (0.8%) required surgery to manage the perforation. In univariate analysis, anterior location of the lesion, a subepithelial lesion, two or more postprocedure pain killers within 24 hrs, and increased heart rate within 24 hrs after the procedure were the factors related to surgery. In logistic regression analysis, the location of the lesion at the anterior wall and using two or more postprocedure pain killers within 24 hrs were risk factors for surgery. Conclusion. Most cases of perforations after ER can be managed conservatively. When a patient requires two or more postprocedure pain killers within 24 hrs and the lesion is located on the anterior wall, early surgery should be considered instead of conservative management.

Therapeutic outcomes of endoscopic submucosal dissection for early gastric cancer: single-center study

OBJECTIVES

Endoscopic submucosal dissection (ESD) has been widely accepted for selected patients with early gastric cancer (EGC). The aim of this study was to assess the therapeutic outcomes after ESD according to the pathological extent.

PATIENTS AND METHODS

From January 2005 to December 2014, a total of 599 patients with 611 lesions were enrolled in this study. The tumors were categorized according to pathological results on the basis of absolute criteria (AC), expanded criteria (EC), EC with undifferentiated histology [(EC-U), mucosal cancer, ulcer (-), ≤20 mm], or beyond EC (BEC). The therapeutic outcomes among the four groups were analyzed retrospectively.

RESULTS

The number of patients in the AC, EC, EC-U, and BEC groups was 447, 91, 19, and 54. The complete resection rates of EGC were 97.8, 84.6, 94.4, and 45.5% (P=0.001) and en bloc resection rates in the AC, EC, EC-U, and BEC groups were 99.1, 98.9, 100, and 98.1% (P=0.833), respectively. The 5-year disease-free survival rate in the AC, EC, EC-U, and BEC groups was 90.6, 88.7, 75.0, and 83.3% (P=0.394). In multivariate analysis, undifferentiated histology (P=0.001) and tumor size (>30 mm, P=0.017) were risk factors related to local recurrence.

CONCLUSION

The efficacy of ESD for EGCs in EC is almost equal to that in AC when complete resection was achieved. However, the indication for ESD should be decided conservatively because the complete resection rate of EGC in the EC group was significantly lower than that in the AC group. Undifferentiated histology and tumor size over 30 mm were risk factors related to local recurrence.

Procedure Time for Gastric Endoscopic Submucosal Dissection according to Location, considering Both Mucosal Circumferential Incision and Submucosal Dissection

Background. Previous assessments of technical difficulty and procedure time for endoscopic submucosal dissection (ESD) of gastric neoplasms did not take into account several critical determinants of these parameters. However, two key phases of ESD determine the total procedure time: the mucosal circumference incision speed (CIS) and submucosal dissection speed (SDS). Methods. We included 302 cases of en bloc and R0 resection of gastric neoplasms performed by 10 operators who had completed the training program at our hospital. Twelve locations were classified based on multiple criteria, such as condition of surrounding mucosa, lesion vascularity, presence of submucosal fat, ulcers, scars, fibrosis, and scope and device maneuverability. Lesions in different locations were classified into three groups based on the length of the procedure: fast, moderate, or late. Results. A significant difference was found in CIS and SDS for each location (p < 0.01), which demonstrates the validity of this classification system. In several locations, CIS and SDS were not consistent with each other. Conclusion. CIS and SDS did not correspond to each other even for lesions in the same location. Consideration of ESD procedure time for gastric neoplasms requires a more elaborate classification system than that previously reported.

Endoscopic submucosal dissection versus surgical resection for early gastric cancer: a retrospective multicenter study on immediate and long-term outcome over 5 years

BACKGROUND

Endoscopic submucosal dissection (ESD) is an alternative to surgical resection for treating early gastric cancer (EGC). However, there have been limited reports on the long-term outcome of ESD compared to that of surgical resection. The aim of this study was to evaluate the immediate and long-term clinical and oncologic outcomes of ESD compared to surgical resection.

METHOD

We retrospectively reviewed data of patients in five centers who were treated with ESD or surgical resection for EGC within expanded criteria for ESD from 2006 to 2008.

RESULT

ESD group had significantly shorter procedure times, shorter fasting period, and shorter hospital stay than the surgical resection group. Immediate complications in the surgical resection group were more common compared to those in the ESD group. Five-year cancer recurrence rate of the ESD group was 12.3 % and significantly higher than 2.1 % of the surgical resection group (P = 0.001). Five-year disease-free survival rate of the surgical resection group was 97 %, which was significantly higher than 85 % of the ESD group (P = 0.001). Metachronous lesions were equally found every year during the follow-up period in the ESD group. Five-year overall survival rates were 100 % for both groups.

CONCLUSION

ESD might be an acceptable and effective treatment for EGC considering overall survival rates with fewer early complication rates and shorter duration of hospital stay compared to surgical resection. However, intensive and persistent endoscopic surveillance should be performed after ESD for early detection of metachronous lesions.

Endoscopic submucosal tunnel dissection salvage technique for ulcerative early gastric cancer

Endoscopic submucosal dissection is an effective treatment modality for early gastric cancer (EGC), though the submucosal fibrosis found in ulcerative EGC is an obstacle for successful treatment. This report presents two cases of ulcerative EGC in two males, 73- and 80-year-old, with severe fibrosis. As endoscopic ultrasonography suggested that the EGCs had invaded the submucosal layer, the endoscopic submucosal tunnel dissection salvage technique was utilized for complete resection of the lesions. Although surgical gastrectomy was originally scheduled, the two patients had severe coronary heart disease, and surgeries were refused because of the risks associated with their heart conditions. The endoscopic submucosal tunnel dissection salvage technique procedures described in these cases were performed under conscious sedation, and were completed within 30 min. The complete en bloc resection of EGC using endoscopic submucosal tunnel dissection salvage technique was possible with a free resection margin, and no other complications were noted during the procedure. This is the first known report concerning the use of the endoscopic submucosal tunnel dissection salvage technique salvage technique for treatment of ulcerative EGC. We demonstrate that endoscopic submucosal tunnel dissection salvage technique it is a feasible method showing several advantages over endoscopic submucosal dissection for cases of EGC with fibrosis.

Impact of tumor location on clinical outcomes of gastric endoscopic submucosal dissection

AIM: To determine whether there is a correlation between the location of the lesion and endoscopic submucosal dissection (ESD) outcome.

METHODS: From January 2008 to December 2010, ESD of 1443 gastric tumors was performed. En bloc resection rate, complete resection rate, procedure time and complication rate were analyzed according to the tumor location.

RESULTS: The rates of en bloc resection and complete resection were 91% (1318/1443) and 89% (1287/1443), respectively. The post-ESD bleeding rate was 4.3%, and perforation rate was 2.7%. Tumors located in the upper third of the stomach were associated with a longer procedure time and significantly higher rates of incomplete resection, piecemeal resection, and perforation than tumors below the upper third of the stomach. Posterior wall lesions had significantly longer procedure times and higher rates of incomplete resection and piecemeal resection than lesions in other locations. In multivariate analysis, posterior wall lesions and upper third lesions were significantly associated with incomplete resection and perforation, respectively. In post-ESD bleeding analysis, location was not a significant related factor.

CONCLUSION: More advanced endoscopic techniques are required during ESD for lesions located in the upper third or posterior wall of the stomach to decrease complications and improve therapeutic outcomes.

Long-term outcomes of endoscopic submucosal dissection for early gastric cancer: a single-center experience

BACKGROUND

In Korea, endoscopic submucosal dissection (ESD) has been widely accepted for the treatment of early gastric cancers (EGCs). However, the understanding of the long-term clinical outcome of ESD for EGC remains insufficient. Therefore, the aim of the present study was to assess the long-term clinical outcome and efficacy of ESD for the treatment of EGCs, including the clinical application of the expanded criteria for ESD.

METHODS

From January 2006 to December 2010, a total of 515 patients with 522 EGCs were treated by ESD in our hospital; study enrollment was based on the expanded criteria. Comparisons of resectability (en bloc or piecemeal resection), curability (curative or non-curative), and complications (bleeding and perforation) between the standard and expanded groups were assessed. Thereafter, 336 patients with 342 EGCs were finally included in a long-term analysis of local tumor recurrence, development of synchronous and metachronous cancers, and overall and disease-specific survival rates.

RESULTS

En bloc and curative resection rates of 96.7 % and 88.3 %, respectively, were achieved. The curative resection rate was significantly lower in the expanded group than in the standard group (82.1 % vs. 91.5 %, p = 0.001). During a median follow-up of 24 months, the local tumor recurrence rate was also higher in the expanded group than in the standard group (7.0 % vs. 1.8 %, p = 0.025). Local recurrence was more frequent in lesions with non-curative resection than in those with curative resection (20.0 % vs. 1.3 %, p < 0.001). The 5-year overall and disease-specific survival rates were 88 % and 100 %, respectively; the difference between the standard and expanded groups was not significant (p = 0.834).

CONCLUSIONS

ESD appears to be a feasible and effective method for treating EGCs, based on the standard and expanded criteria. Close follow-up surveillance, after ESD, should be standard for all patients.

The efficacy of transdermal fentanyl for pain relief after endoscopic submucosal dissection: a prospective, randomised controlled trial

OBJECTIVE

Epigastric pain management following endoscopic submucosal dissection is an important consideration. This study aimed to investigate the utility and safety of fentanyl patches for pain relief after the procedure.

METHODS

Patients who were scheduled to undergo endoscopic submucosal dissection were prospectively randomised to either a transdermal fentanyl patch group or a placebo control group. An additional pethidine was intravenously administered when pain developed and a numerical rating scale was used to evaluate both pre- and post-procedural pain.

RESULTS

One hundred and ten patients were randomly assigned to receive either a 12 mcg/h fentanyl patch or a control patch on the night before the procedure. The fentanyl patch group had significantly lower pain scores immediately following the procedure (mean, 5.17 vs. 4.26, p=0.030). Maximal pain scores during the first 24 h (5.43 vs. 4.46, p=0.038) and pain scores on the day after the procedure (2.98 vs. 1.20, p<0.001) were also lower in the fentanyl patch group. In addition, the fentanyl patch group required a significantly lower dose of pethidine for pain management (24.54 vs. 11.25, p=0.004).

CONCLUSIONS

The application of a transdermal fentanyl patch is an effective, convenient, and safe method to control epigastric pain after endoscopic submucosal dissection.

Endoscopic submucosal dissection--current success and future directions

More than 10 years have passed since endoscopic submucosal dissection (ESD) was first developed in Japan. ESD enables en bloc complete resection of superficial gastrointestinal neoplasms regardless of the size and location of the lesions. With improvements in techniques and devices, excellent therapeutic results have been achieved despite the inherent technical difficulties of this procedure. ESD aiming for curative treatment can be performed for gastrointestinal neoplasms without risk of lymph node metastasis. Accurate histopathologic examination of the resected specimen is required to determine the risk of lymph node metastasis, for which en bloc resection is beneficial. Owing to the high success rate of en bloc complete resection and accurate histopathologic examination, tumour recurrence rates after ESD are reported to be very low in Japan. Excellent results of ESD in a large number of cases have also been reported from other Asian countries such as South Korea, Taiwan and China. Although scepticism exists among Western clinicians regarding the application of ESD, it is developing slowly and reports indicate promising results in some European countries. With further development of technologies, such as endoscopic robotics, ESD could become the worldwide treatment of choice for early gastrointestinal neoplasms.