INTRODUCTION: This study aims to construct a real-time deep convolutional neural networks (DCNNs) system to diagnose early esophageal squamous cell carcinoma (ESCC) with white light imaging endoscopy. METHODS: A total of 4,002 images from 1,078 patients were used to train and cross-validate the DCNN model for diagnosing early ESCC. The performance of the model was further tested with independent internal and external validation data sets containing 1,033 images from 243 patients. The performance of the model was then compared with endoscopists. The accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and Cohen kappa coefficient were measured to assess performance. RESULTS: The DCNN model had excellent performance in diagnosing early ESCC with a sensitivity of 0.979, a specificity of 0.886, a positive predictive value of 0.777, a negative predictive value of 0.991, and an area under curve of 0.954 in the internal validation data set. The model also depicted a tremendously generalized performance in 2 external data sets and exhibited superior performance compared with endoscopists. The performance of the endoscopists was markedly elevated after referring to the predictions of the DCNN model. An open-accessed website of the DCNN system was established to facilitate associated research. DISCUSSION: A real-time DCNN system, which was constructed to diagnose early ESCC, showed good performance in validation data sets. However, more prospective validation is needed to understand its true clinical significance in the real world.
Recent studies indicate that the prevalence of reflux esophagitis (RE) in China is increasing. RE is one of the most common esophageal complications associated with gastroesophageal reflux disease (GERD) and RE-Barrett's esophagus-esophageal adenocarcinoma (EAC) sequence has been considered as an histogenesis model for EAC in Western countries. RE is only present in a subset of patients with GERD, suggesting an altered susceptibility to RE may exist in these GERD individuals. However, the genetic changes related with high susceptibility to RE is largely unknown. The polymorphisms in glutathione S-transferases (GSTs) T1, M1 and P1 have been reported with high susceptibity to esophageal cancer in Chinese people. The present case-control study was thus undertaken to characterize the genetic polymorphisms of GSTs and their correlation with susceptibility to RE. One hundred and nine patients with RE, 97 patients with nonerosive reflux disease (NERD) and 97 normal controls were recruited in this study. All the subjects were from Beijing, China, and received endoscopic examination and questionnaires for RE. Genomic DNA was extracted from the lymphocytes of peripheral blood for each subject. Genotypes of the GSTM1 and GSTT1 genes were analyzed by a multiplex PCR method. A-->G polymorphism of codon 104 of the GSTP1 gene was detected using PCR-based restriction fragment length polymorphisms (RFLP). The variant GSTP1 genotypes (*A/*Bomicron*B/*B) was found with a high frequency in the case with RE (40%), and followed by NERD (25%) and normal control (22%). The differences were statistically significant (P < 0.05). The risk for RE increased 2.42-fold [odds ratio (OR); 95% confidence interval (95% CI), 2.42 (1.22-4.80)] in the subjects with variant GSTP1 genotype. The subjects with positive variant GSTP1 genotypes and negative H. pylori infection showed increasing tendency for risk of RE [OR (95% CI), 2.67 (1.06-6.70)]. However, the subjects with GSTT1 and GSTM1 polymorphisms did not show any correlation with high risk for RE or NERD. No significant interactions were identified between the variant GSTs and cigarette smoking, or alcohol drinking and subtype of RE. The present result suggests that GSTP1 genetic polymorphism may be one of the high susceptibility factors involved in the mechanisms of RE. H. pylori infection may play a protective role against RE.
Aims: Early gastric cardiac cancer (EGCC) has a low risk of lymph node metastasis with the potential for endoscopic therapy. We aimed to evaluate the short- and long-term outcomes of endoscopic submucosal dissection (ESD)-resected EGCCs in a large cohort of Chinese patients and compare endoscopic and clinicopathologic features between EGCC and early gastric non-cardiac cancer (EGNC). Methods: We retrospectively studied 512 EGCCs in 499 consecutive patients and 621 EGNCs in 555 consecutive patients between January 2011 and March 2018 at our center. We investigated clinicopathological characteristics of EGCC tumors, ESD treatment results, adverse events, and postresection patient survival. Results: Compared with EGNC patients, EGCC patients were significantly older (average age: 66 years versus 62 years, p < 0.001). The percentage of the gross 0–IIc pattern was higher in EGCCs (46.1%) than in EGNCs (41.5%), while the frequency of the 0–IIa pattern was lower in EGCCs (14.9%) than in EGNCs (22.4%) ( p = 0.001). Compared with EGNCs, EGCCs showed smaller size, deeper invasion, fewer ulcerated or poorly differentiated tumors, but more cases with gastritis cystica profunda. The prevalence of ESD-related complications was higher in EGCCs (6.1%) than in EGNCs (2.3%) ( p = 0.001). In EGCCs, the disease-specific survival rate was significantly higher in patients of the noncurative resection group with surgery (100%), compared with that (93.9%) without surgery ( p < 0.001). Conclusion: Clinicopathological characteristics were significantly different between EGCCs and EGNCs. ESD is a safe and effective treatment option with favorable outcomes for patients with EGCC. Additional surgery improved survival in patients with noncurative ESD resection.
INTRODUCTION: High risk of lymph node metastasis (LNM) in gastric papillary adenocarcinoma causes endoscopists to worry about the suitability of endoscopic resection for early gastric papillary adenocarcinoma (EPAC). We compared risk factors and attempted to establish a scoring system to stratify LNM risk in patients with EPAC. METHODS: A retrospective analysis was performed on 2,513 patients with early gastric carcinoma (EGC) who underwent radical resection in 4 tertiary hospitals in China. Univariate and multivariate analyses were performed to compare the invasiveness in EPAC and other types of EGC and to evaluate potential factors in predicting LNM risk in EPAC groups. RESULTS: Three hundred thirty-five patients with EPAC were enrolled in our study, of which 62 patients were found to have LNM. After comparing clinicopathological characteristics of EPAC with and without LNM, the following factors were included in the risk scoring system: 1 point each for lower stomach location and tumor size >2.0 cm, 3 points for lymphovascular invasion, and 4 points for submucosal invasion; the risk scoring system was validated in a small internal validation set with an area under the curve of 0.844. DISCUSSION: Our results suggested that EPAC was highly invasive compared with other EGCs, especially differentiated EGC types, and need to be treated more rigorously. This proposed risk scoring system could stratify LNM risk in patients with EPAC, and endoscopic resection may only be performed safely on the groups with a low LNM rate.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.