Computer-aided diagnostic system with automated deep learning method based on the AutoGluon framework improved the diagnostic accuracy of early esophageal cancer.

Background: There have been studies on the application of computer-aided diagnosis (CAD) in the endoscopic diagnosis of early esophageal cancer (EEC), but there is still a significant gap from clinical application. We developed an endoscopic CAD system for EEC based on the AutoGluon framework, aiming to explore the feasibility of automatic deep learning (DL) in clinical application. Methods: The endoscopic pictures of normal esophagus, esophagitis, and EEC were collected from The First Affiliated Hospital of Soochow University (September 2015 to December 2021) and the Norwegian HyperKvasir database. All images of non-cancerous esophageal lesions and EEC in this study were pathologically examined. There were three tasks: task A was normal vs. lesion classification under non-magnifying endoscopy (n=932 vs. 1,092); task B was non-cancer lesion vs. EEC classification under non-magnifying endoscopy (n=594 vs. 429); and task C was non-cancer lesion vs. EEC classification under magnifying endoscopy (n=505 vs. 824). In all classification tasks, we took 100 pictures as the verification set, and the rest comprised as the training set. The CAD system was established based on the AutoGluon framework. Diagnostic performance of the model was compared with that of endoscopists grouped according to years of experience (senior >15 years; junior <5 years). Model evaluation indicators included accuracy, recall rate, precision, F1 value, interpretation time, and the area under the receiver operating characteristic (ROC) curve (AUC). Results: In tasks A and B, the accuracies of medium-performance CAD and high-performance CAD were lower than those of junior doctors and senior doctors. In task C, the medium-performance and high-performance CAD accuracies were close to those of junior doctors and senior doctors. The high-performance CAD model outperformed the junior doctors in both task A (0.850 vs. 0.830) and task C (0.840 vs. 0.830) in sensitivity comparison, but there was still a large gap between high-performance CAD models and doctors in sensitivity comparison. In task A, with the aid of CAD pre-interpretation, the accuracy of junior and senior physicians were significantly improved (from 0.880 to 0.915 and from 0.920 to 0.945, respectively); the time spent on film reading was significantly shortened (junior: from 11.3 to 8.7 s; senior: from 6.7 to 5.5 s). In task C, with the aid of CAD pre-interpretation, the accuracy of junior and senior physicians were significantly improved (from 0.850 to 0.865 and from 0.915 to 0.935, respectively); the reading time was significantly shortened (junior: from 9.5 to 7.7 s; senior: from 5.6 to 3.0 s). Conclusions: The CAD system based on the AutoGluon framework can assist doctors to improve the diagnostic accuracy and reading time of EEC under endoscopy. This study reveals that automatic DL methods are promising in clinical application.

Efficiency of endoscopic artificial intelligence in the diagnosis of early esophageal cancer.

BACKGROUND: The accuracy of artificial intelligence (AI) and experts in diagnosing early esophageal cancer (EC) and its infiltration depth was summarized and analyzed, thus identifying the advantages of AI over traditional manual diagnosis, with a view to more accurately assisting doctors in evaluating the patients' conditions and improving their cure and survival rates. METHODS: The PubMed, EMBASE, Cochrane, Google, and CNKI databases were searched for relevant literature related to AI diagnosis of early EC and its invasion depth published before August 2023. Summary analysis of pooled sensitivity, specificity, summary receiver operating characteristics (SROC) and area under the curve (AUC) of AI in diagnosing early EC were performed, and Review Manager and Stata were adopted for data analysis. RESULTS: A total of 19 studies were enrolled with a low to moderate total risk of bias. The pooled sensitivity of AI for diagnosing early EC was markedly higher than that of novices and comparable to that of endoscopists. Moreover, AI predicted early EC with markedly higher AUCs than novices and experts (0.93 vs. 0.74 vs. 0.89). In addition, pooled sensitivity and specificity in the diagnosis of invasion depth in early EC were higher than that of experts, with AUCs of 0.97 and 0.92, respectively. CONCLUSION: AI-assistance can diagnose early EC and its infiltration depth more accurately, which can help in its early intervention and the customization of personalized treatment plans. Therefore, AI systems have great potential in the early diagnosis of EC.

Characteristics of the oral and gastric microbiome in patients with early-stage intramucosal esophageal squamous cell carcinoma.

BACKGROUND: Oral microbiome dysbacteriosis has been reported to be associated with the pathogenesis of advanced esophageal cancer. However, few studies investigated the potential role of oral and gastric microbiota in early-stage intramucosal esophageal squamous carcinoma (EIESC). METHOD: A total of 104 samples were collected from 31 patients with EIESC and 21 healthy controls. The compositions of oral and gastric microbiota were analyzed using 16 S rRNA V3-V4 amplicon sequencing. Linear discriminant analysis effect size (LEfSe) analysis was performed to assess taxonomic differences between groups. The correlation between oral microbiota and clinicopathological factors was evaluated using Spearman correlation analysis. Additionally, co-occurrence networks were established and random forest models were utilized to identify significant microbial biomarkers for distinguishing between the EIESC and control groups. RESULTS: A total of 292 oral genera and 223 species were identified in both EIESC and healthy controls. Six oral genera were remarkably enriched in EIESC groups, including the genera Porphyromonas, Shigella, Subdoligranulum, Leptotrichia, Paludibacter, and Odoribacter. LEfSe analysis identified genera Porphyromonas and Leptotrichia with LDA scores > 3. In the random forest model, Porphyromonas endodontalis ranked the top microbial biomarker to differentiate EIESC from controls. The elimination rate of Porphyromonas endodontalis from the oral cavity to the stomach was also dramatically decreased in the EIESC group than controls. In the microbial co-occurrence network, Porphyromonas endodontalis was positively correlated with Prevotella tannerae and Prevotella intermedia and was negatively correlated with Veillonella dispar. CONCLUSION: Our study potentially indicates that the dysbacteriosis of both the oral and gastric microbiome was associated with EIESC. Larger scale studies and experimental animal models are urgently needed to confirm the possible role of microbial dysbacteriosis in the pathogenesis of EIESC. (Chinese Clinical Trial Registry Center, ChiCTR2200063464, Registered 07 September 2022, https://www.chictr.org.cn/showproj.html?proj=178563).

Progress in the treatment and prevention of esophageal stenosis after endoscopic submucosal dissection.

The primary treatment for early esophageal cancer and precancerous lesions is endoscopic submucosal dissection (ESD). However, this approach leads to a high incidence of postoperative esophageal stenosis, which can significantly impact a patient's quality of life. While various methods are available to prevent post-ESD esophageal stenosis, their effectiveness varies. Therefore, this study aims to provide an overview of the currently employed methods for preventing post-ESD esophageal stenosis in clinical practice in view of assisting clinical practitioners.

National adoption of an esophageal cell collection device for Barrett's esophagus surveillance: impact on delay to investigation and pathological findings.

High quality Barrett's esophagus surveillance is crucial to detect early neoplastic changes. An esophageal cell collection device (OCCD) was introduced as a triage tool for Barrett's surveillance. This study aims to evaluate whether the Scottish OCCD program (CytoSCOT) has reduced delays to Barrett's surveillance, and whether delayed surveillance negatively impacts endoscopic pathology. All patients undergoing OCCD testing for Barrett's surveillance across 11 Scottish health boards between 14/9/2020 and 13/9/2022 were identified. Patients were dichotomised into two groups (Year 1 vs. Year 2), with individual records interrogated to record demographics, recommended surveillance interval, time from last endoscopy to OCCD test, and OCCD result. Patients were deemed high-risk if the OCCD demonstrated atypia and/or p53 positivity. Further analysis was performed on patients who underwent endoscopy within 12 months of OCCD testing. A total of 3223 OCCD tests were included in the analysis (1478 in Year 1; 1745 in Year 2). In Year 1 versus Year 2, there was a longer median delay to surveillance (9 vs. 5 months; P < 0.001), increased proportion of patients with delayed surveillance (72.6% vs. 57.0%; P < 0.001), and more high-risk patients (12.0% vs. 5.3%; P < 0.001). 425/3223 patients (13.2%) were further investigated with upper gastrointestinal endoscopy, 57.9% of which were high-risk. As surveillance delay increased beyond 24 months, high-risk patients were significantly more likely to develop dysplasia or malignancy (P = 0.004). Delayed Barrett's esophagus surveillance beyond 24 months is associated with increased risk of pre-cancerous pathology. The CytoSCOT program has reduced delays in surveillance, promoting earlier detection of dysplasia and reducing burden on endoscopy services.

Noniatrogenic Meningitis Caused by Streptococcus salivarius Associated with Early Esophageal Cancer and Early Gastric Cancer.

Streptococcus salivarius is part of the normal oral cavity and gastrointestinal tract microflora and an unusual cause of acute bacterial meningitis. We herein report an 81-year-old man with S. salivarius meningitis, which led to a diagnosis of early esophageal cancer and early gastric cancer. S. salivarius infection may occur through the gastrointestinal mucosa when it is disrupted in association with early gastrointestinal cancer. To our knowledge, this is the first report describing S. salivarius meningitis associated with multiple early gastrointestinal cancers in the absence of other sources of infection.

Risk factors associated with the presence of multiple Lugol-voiding lesions in patients with early esophageal carcinoma / 安徽医科大学学报

Objective @#To investigate the risk factors associated with the presence of multiple Lugol-voiding lesions (LVLs ) in patients with early esophageal cancer and the correlation with alcohol dehy-drogenase 1B(ADH1B) and aldehyde dehydrogenase 2 ( ALDH2) polymorphisms .@*Methods @#Patients who underwent endoscopic submucosal dissection due to early esophageal cancer were divided into group with multiple LVLs and group without multiple LVLs based on their endoscopic features . Their clinical data and the genotype of ADH1B and ALDH2 were collect- ed and SPSS 27 . 0 was used to statistically analyze the above data.@*Results @#A total of 83 subjects were included in the study , 23 had multiple LVLs , most of them were seen in males , alcohol drinkers , and smokers with smoking index≥1 000 , and multivariate analysis showed that alcohol consumption was an independent risk factor for it (OR = 6. 215 , P = 0. 008) . The gene polymorphism of ADH1B and ALDH2 and their interactions did not have any sig- nificant correlation with multiple LVLs . However , among alcohol drinkers , there was a 12 -fold increased risk of multiple LVLs in patients carrying the ALDH2 A allele and drinking ≥50 g per day compared to those carrying the ALDH2 GG genotype and drinking < 50 g per day ( P = 0. 045) .@*Conclusion @#Alcohol consumption is an inde- pendent risk factor of multiple LVLs of the esophageal mucosa in patients with early esophageal cancer , and heavy alcohol consumption in carriers of the ALDH2 A allele will significantly increase the risk of multiple LVLs , and such patients should be closely followed up with endoscopy .

Prediction of lymph node metastasis in early esophageal cancer.

BACKGROUND: Given the poor prognosis of patients with lymph node metastasis, estimating the lymph node status in patients with early esophageal cancer is crucial. Indicators that could be used to predict lymph node metastasis in early esophageal cancer have been reported in many recent studies, but no recent studies have included a review of this subject. AIM: To review indicators predicting lymph node metastasis in early esophageal squamous cell carcinoma (ESCC) and early esophageal adenocarcinoma (EAC). METHODS: We searched PubMed with "[early esophageal cancer (Title/Abstract)] and [lymph node (Title/Abstract)]" or "[early esophageal carcinoma (Title/Abstract)] and [lymph node (Title/Abstract)]" or "[superficial esophageal cancer (Title/Abstract)] and [lymph node (Title/Abstract)]." A total of 29 studies were eligible for analysis. RESULTS: Preoperative imaging (size), serum markers (microRNA-218), postoperative pathology and immunohistochemical analysis (depth of invasion, tumor size, differentiation grade, lymphovascular invasion, neural invasion, expression of PIM-1 < 30%) were predictive factors for lymph node metastasis in both early ESCC and EAC. Serum markers (thymidine kinase 1 ≥ 3.38 pmol/L; cytokeratin 19 fragment antigen 21-1 > 3.30 ng/mL; stathmin-1) and postoperative pathology and immunohistochemical analysis (overexpression of cortactin, mixed-lineage leukaemia 2, and stanniocalcin-1) were predictive for lymph node metastasis in early ESCC. Transcription of CD69, myeloid differentiation protein 88 and toll-like receptor 4 and low expression of olfactomedin 4 were predictive of lymph node metastasis in early EAC. A total of 6 comprehensive models for early ESCC, including logistic regression model, nomogram, and artificial neural network (ANN), were reviewed. The areas under the receiver operating characteristic curve of these models reached 0.789-0.938, and the ANN performed best. As all these models relied on postoperative pathology, further models focusing on serum markers, imaging and immunohistochemical indicators are still needed. CONCLUSION: Various factors were predictive of lymph node metastasis in early esophageal cancer, and present comprehensive models predicting lymph node metastasis in early ESCC mainly relied on postoperative pathology. Further studies focusing on serum markers, imaging and immunohistochemical indicators are still in need.

Magnetic anchor technique assisted endoscopic submucosal dissection for early esophageal cancer.

BACKGROUND: Esophageal cancer has high incidence globally and is often diagnosed at an advanced stage. With the widespread application of endoscopic technologies, the need for early detection and diagnosis of esophageal cancer has gradually been realized. Endoscopic submucosal dissection (ESD) has become the standard of care for managing early tumors of the esophagus, stomach, and colon. However, due to the steep learning curve, difficult operation, and technically demanding nature of the procedure, ESD has currently been committed to the development of various assistive technologies. AIM: To explore the feasibility and applicability of magnetic anchor technique (MAT)-assisted ESD for early esophageal cancer. METHODS: Isolated pig esophagi were used as the experimental model, and the magnetic anchor device was designed by us. The esophagi used were divided into two groups, namely the operational and control groups, and 10 endoscopists completed the procedure. The two groups were evaluated for the following aspects: The total operative time, perforation rate, rate of whole mucosal resection, diameter of the peering mucosa, and scores of endoscopists' feelings with the procedure, including the convenience, mucosal surface exposure degree, and tissue tension. In addition, in the operational group, the soft tissue clip and the target magnet (TM) were connected by a thin wire through a small hole at the tail end of the TM. Under gastroscopic guidance, the soft tissue clip was clamped to the edge of the lesioned mucosa, which was marked in advance. By changing the position of the anchor magnet (AM) outside the esophagus, the pulling force and pulling direction of the TM could be changed, thus exposing the mucosal peeling surface and assisting the ESD. RESULTS: Herein, each of the two groups comprised 10 isolated esophageal putative mucosal lesions. The diameter of the peering mucosa did not significantly differ between the two groups (2.13 ± 0.06 vs 2.15 ± 0.06, P = 0.882). The total operative time was shorter in the operational group than in the control group (17.04 ± 0.22 min vs 21.94 ± 0.23 min, P < 0.001). During the entire experiment, the TM remained firmly connected with the soft tissue clip and did not affect the opening, closing, and release of the soft tissue clip. The interaction between the TM and AM could provide sufficient tissue tension and completely expose the mucosa, which greatly assists the surgeon with the operation. There was no avulsion of the mucosa, and mucosal lesions were intact when peeled. Therefore, the scores of endoscopists' feelings were higher in the operational group than in the control group in terms of the convenience (9.22 ± 0.19 vs 8.34 ± 0.15, P = 0.002), mucosal surface exposure degree (9.11 ± 0.15 vs 8.25 ± 0.12, P < 0.001), and tissue tension (9.35 ± 0.13 vs 8.02 ± 0.17, P < 0.001). The two groups did not significantly differ in the perforation rate and rate of whole mucosal resection. CONCLUSION: We found MAT-assisted ESD safe and feasible for early esophageal cancer. It could greatly improve the endoscopic operation experience and showed good clinical application prospects.

Clinicopathological characteristics of synchronous multiple primary early esophageal cancer and risk factors for multiple lesions.

Background: With the development of endoscopic technology, the detection rate of synchronous multiple primary early esophageal cancer (SMPEEC) is increasing; however, the risk factors remain unclear. We aimed to assess the clinicopathological characteristics of patients with SMPEEC and investigate the risk factors contributing to the development of multiple lesions. Methods: A retrospective cohort study was conducted on 911 consecutive patients who underwent Endoscopic submucosal dissection (ESD) for primary esophageal neoplasms from January 2013 to June 2021. The patients were divided into the SMPEEC group and the solitary early esophageal cancer (SEEC) group. We compared the differences in clinicopathological characteristics between the two groups and investigated the risk factors linked to multiple lesions. Additionally, we investigated the relationship between the main and accessory lesions. Results: A total of 87 SMPEEC patients were included in this study, and the frequency of synchronous multiple lesions was 9.55% in patients with early esophageal cancer. The lesions in the SMPEEC group were mainly located in the lower segment of the esophagus (46[52.9%]), whereas those in the SEEC group were in the middle segment (412[50.0%]). The pathology type, tumor location, and circumferential rate of lesions were independent risk factors(P<0.05) for SMPEEC by logistic regression analysis. Significant positive correlations were observed between the main and accessory lesions in terms of morphologic type (r=0.632, P=0.000), tumor location(r=0.325, P=0.037), pathologic type (r=0.299, P=0.003), and depth of invasion (r=0.562, P=0.000). Conclusion: Pathology type, tumor location, and circumferential rate of lesions were identified as independent risk factors for SMEPPC. Understanding these risk factors and the correlation between the main and accessory lesions could significantly improve the detection rate of SMPEEC.

Management of esophageal neoplasms by endoscopic submucosal dissection: experience over 100 consecutive procedures.

BACKGROUND/AIMS: Endoscopic submucosal dissection (ESD) is currently considered the first-line treatment for the eradication of superficial neoplasms of the esophagus in Eastern countries. However, in the West, particularly in Latin America, the experience with esophageal ESD is still limited because of the high technical complexity required for its execution. This study aimed to present the results of the clinical application of ESD to manage superficial esophageal neoplasms in a Latin American center in over 100 consecutive cases. METHODS: This retrospective study included consecutive patients who underwent endoscopic ESD for superficial esophageal neoplasms between 2009 and 2022. The following clinical outcomes were assessed: en bloc, complete, and curative resection rates, local recurrence, adverse events, and procedure-related mortality. RESULTS: Esophageal ESD was performed mainly for squamous cell carcinoma (66.6%), high-grade intraepithelial neoplasia (17.1%), and adenocarcinoma (11.4%). En bloc and complete resection rates were 96.2% and 81.0%, respectively. The curative resection rate was 64.8%. Adverse events occurred in six cases (5.7%). Endoscopic follow-up was performed for an average period of 29.7 months. CONCLUSION: ESD performed by trained operators is feasible, safe, and clinically effective for managing superficial neoplastic lesions of the esophagus in Latin America.

Combined treatment of refractory benign stricture after esophageal endoscopic mucosal dissection: A case report.

BACKGROUND: Endoscopic submucosal dissection (ESD) post-procedure stricture is a relatively common long-term complication following ESD treatment. A range of approaches has been implemented for the treatment of post-procedural stricture using endoscopic techniques such as endoscopic dilation, self-expandable metallic stent insertion, local steroid injection in the esophagus, oral steroid administration, radial incision and cutting (RIC). The actual efficacy of these different therapeutic options is highly variable, and uniform international standards for the prevention or treatment of stricture. CASE SUMMARY: In this report, we describe the case of a 51-year-old male diagnosed with early esophageal cancer. To protect against esophageal stricture, the patient was administered oral steroids and underwent self-expandable metallic stent insertion for 45 d. Despite these interventions, stricture was detected at the lower edge of the stent following its removal. The patient remained refractory to multiple rounds of endoscopic bougie dilation treatment, and thus suffered from complex refractory benign esophageal stricture. As such, RIC combined with bougie dilation and steroid injection was employed to treat this patient more effectively, ultimately achieving satisfactory therapeutic efficacy. CONCLUSION: Combination of RIC, dilation, and steroid injection can be safely and effectively implemented to treat cases of post-ESD refractory esophageal stricture.

Case report: First case of early adenoid cystic carcinoma and squamous cell carcinoma collision cancer treated by endoscopic submucosal dissection.

Background: Collision cancer, a rare tumor, rarely occurs in the esophagus. Most reported cases of esophageal collision cancers are advanced cancers that can only be treated with surgery or palliative chemoradiotherapy. Here, we report a rare case of collisional squamous cell carcinoma (SqCC) and adenoid cystic carcinoma (AdCC) that was detected in the early stages by endoscopy. Case summary: A 66-year-old man presented with retrosternal pain after swallowing and underwent endoscopy. Pathological biopsy showed high-grade squamous intraepithelial neoplasia. The lesion was removed by endoscopic submucosal dissection (ESD) after magnification and endoscopic ultrasonography. Postoperative pathology proved that the lesion was collision cancer comprising SqCC and AdCC. After six months of postoperative follow-up, there was no recurrence of esophageal cancer. Conclusions: We provided a case report related to the diagnosis and treatment of esophageal collision cancer, especially early collision cancer. More research is needed to provide insights into the management of collision cancers.

Endoscopic treatment of early esophageal cancer with decompensated cirrhosis and successful prevention of postoperative stenosis: A case report.

The management of gastrointestinal tumors with decompensated cirrhosis is extremely challenging. Patients often present with poor basic condition and coagulation function, and nutritional deficiency. Furthermore, postoperative recovery is difficult and so the majority of patients refuse surgery. The present study reports the case of a 73-year-old man with decompensated cirrhosis and early esophageal cancer. At the discretion of the patient and their family, a simultaneous approach was used to treat esophagogastric varices and perform a mucosal dissection of the early esophageal cancer via endoscopy. Post-surgery, multiple polyglycolic acid sheets were attached to the esophageal dissection wound. At >2 months post-surgery, an endoscopic re-examination of the patient showed that the esophageal mucosa had healed well, and there was no resistance detected via ordinary endoscopy. The main objective of the present study was to highlight the feasibility and safety of endoscopic treatment for patients with decompensated liver cirrhosis complicated with early esophageal cancer, and to provide a new treatment strategy for patients at high risk of esophageal stenosis after endoscopic mucosal dissection.

Impact of linked color imaging and blue laser imaging on the diagnosis of esophageal squamous cell carcinoma in iodine unstained areas.

The pink color sign in iodine unstained areas is useful to differentiate esophageal squamous cell carcinoma (ESCC) from other lesions. However, some ESCCs have obscure color findings which affect the ability of endoscopists to differentiate these lesions and determine the resection line. Using white light imaging (WLI), linked color imaging (LCI) and blue laser imaging (BLI), 40 early ESCCs were retrospectively evaluated using images before and after iodine staining. Visibility scores for ESCC by expert and non-expert endoscopists were compared using these three modalities and color differences measured for malignant lesions and surrounding mucosa. BLI had the highest score and color difference without iodine staining. Each determination with iodine was much higher than without iodine regardless of the modality. With iodine, ESCC mainly appeared pink, purple and green using WLI, LCI and BLI, respectively and visibility scores determined by non-experts and experts were significantly higher for LCI (both p < 0.001) and BLI (p = 0.018 and p < 0.001) than for WLI. The score with LCI was significantly higher than with BLI among non-experts (p = 0.035). With iodine, the color difference using LCI was twice that with WLI and one with BLI was significantly larger than with WLI (p < 0.001). These greater tendencies were found regardless of location, depth of cancer or intensity of pink color using WLI. In conclusion, areas of ESCC unstained by iodine were easily recognized using LCI and BLI. Visibility of these lesions is excellent even by non-expert endoscopists, suggesting that this method is useful to diagnose ESCC and determine the resection line.

Mediastinal Thoracic Duct Cyst Infection after Endoscopic Submucosal Dissection for Early Esophageal Cancer.

A mediastinal thoracic duct cyst that originates from the thoracic duct is a very rare disease in the mediastinum. There have been no reports of mediastinal thoracic duct cyst infection caused by endoscopic treatment. This is the first case of mediastinal thoracic duct cyst infection after endoscopic submucosal dissection for early esophageal cancer. We herein report a 75-year-old man with mediastinal thoracic duct cyst infection caused by esophageal endoscopic submucosal dissection. In cases where a mediastinal thoracic duct cyst is found before performing endoscopic esophageal treatment, we should carefully consider the potential risk of post-treatment cyst infection.

Accuracy of endoscopy-based artificial intelligence-assisted diagnostic system in the diagnosis of early esophageal cancer: A systematic review and meta-analysis / 中国胸心血管外科临床杂志

@#Objective     To systematically evaluate the accuracy of endoscopy-based artificial intelligence (AI)-assisted diagnostic systems in the diagnosis of early-stage esophageal cancer and provide a scientific basis for its diagnostic value. Methods    PubMed, EMbase, The Cochrane Library, Web of Science, Wanfang database, VIP database and CNKI database were searched by computer to search for the relevant literature about endoscopy-based AI-assisted diagnostic systems for the diagnosis of early esophageal cancer from inception to March 2022. The QUADAS-2 was used for quality evaluation of included studies. Meta-analysis of the literature was carried out using Stata 16, Meta-Disc 1.4 and RevMan 5.4 softwares. A bivariate mixed effects regression model was utilized to calculate the combined diagnostic efficacy of the AI-assisted system and meta-regression analysis was conducted to explore the sources of heterogeneity. Results    A total of 17 articles were included, which consisted of 13 retrospective cohort studies and 4 prospective cohort studies. The results of the quality evaluation using QUADAS-2 showed that all included literature was of high quality. The obtained meta-analysis results revealed that the AI-assisted system in the diagnosis of esophageal cancer presented a combined sensitivity of 0.94 (95%CI 0.91 to 0.96), a specificity of 0.85 (95%CI 0.74 to 0.92), a positive likelihood ratio of 6.28 (95%CI 3.48 to 11.33), a negative likelihood ratio of 0.07 (95%CI 0.05 to 0.11), a diagnostic odds ratio of 89 (95%CI 38 to 208) and an area under the curve of 0.96 (95%CI 0.94 to 0.98). Conclusion    The AI-assisted diagnostic system has a high diagnostic value for early stage esophageal cancer. However, most of the included studies were retrospective. Therefore, further high-quality prospective studies are needed for validation.

Preliminary study on the process and prognosis of 55 cases of esophageal stricture after circumferential endoscopic submucosal dissection / 中华消化杂志

Objective:To investigate the characteristics, process, and prognosis of esophageal stricture after circumferential endoscopic submucosal dissection (ESD), and to preliminarily analyze the prevention and treatment effects of simple dilation, stent placement, mucosal transplantation, and glucocorticoid (hereinafter referred to as hormone) application in esophageal stricture.Methods:From August 2017 to March 2022, at the First Affiliated Hospital of Zhengzhou University, the clinical and follow-up data of 55 patients who underwent circumferential ESD for early esophageal cancer and precancerous lesions were retrospectively analyzed. According to the prevention and treatment methods for esophageal stricture, the patients were divided into two groups: simple dilation group (23 cases) and combined dilation group (32 cases). The combined dilation group was divided into mucosal transplantation subgroup (9 cases), stent placement subgroup (14 cases), hormone application subgroup (7 cases), and bleomycin subgroup (2 cases, excluded from comparative analysis due to limited cases). Overall prognosis of patients was observed. Treatment efficacy, prognosis, and adverse events were compared among the simple dilation group, mucosal transplantation subgroup, stent placement subgroup, and hormone application subgroup. Independent samples t-test, chi-square test, and Fisher′s exact test were used for statistical analysis. Results:Among the 55 patients, the follow-up time was (894.1±417.7) days. Refractory esophageal stricture (total dilation times ≥ 5) occurred in 33 patients (60.0%). Fifty-two patients (94.5%) achieved clinical remission of the stricture. The total number of dilations was 5.8±4.0, and the average dysphagia-free period was (52.3±37.1) days. The dysphagia-free period of mucosal transplantation subgroup was longer than that of the simple dilation group, stent placement subgroup, and hormone application subgroup ((114.5±50.0) days vs. (40.9±20.0), (39.7±10.0), and (40.9±25.5) days, respectively), and the differences were statistically significant ( t=4.82, 3.77 and 3.14, P<0.001, =0.011, =0.009). There were no statistically significant differences between the simple dilation group and the mucosal transplantation subgroup, stent placement subgroup, and hormone application subgroup in the total number of dilations (6.8±4.8 vs. 3.0±2.5, 5.8±2.2, and 5.7±5.0), stricture remission rate (95.7%, 22/23 vs. 8/9, 13/14, and 7/7), and incidence of adverse events (17.4%, 4/23 vs. 5/9, 5/14, and 2/7; all P>0.05). Conclusions:Esophageal stricture formed after circumferential ESD shows the characteristics of recurrence and intractability. The over all number of dilations is high, and the average dysphagia-free period is short. Most patients can achieve clinical remission of the stricture after multiple times of endoscopic dilation treatment. However mucosal transplantation, stent placement, and hormone application cannot well intervene the natural process of esophageal stricture.

Short-term efficacy of esophageal triamcinolone acetonide filling combined with oral methylprednisolone for prevention of esophageal stenosis after large-area endoscopic submucosal dissection (with video) / 中华消化内镜杂志

Objective:To study the short-term (≤3 months) efficacy and safety of esophageal triamcinolone acetonide filling combined with short-course oral methylprednisolone for the prevention of esophageal stenosis after large-area endoscopic submucosal dissection (ESD) (≥3/4 circumference).Methods:A total of 14 patients with 15 early esophageal lesions who received ESD after evaluation from June 2021 to September 2022 in Jiangsu Province Hospital of Chinese Medicine were enrolled. All received regular esophageal triamcinolone acetonide filling combined with oral methylprednisolone for 7 weeks until the lesions completely recovered by regenerated squamous epithelium (>95%). Patients with esophageal stricture were treated with additional endoscopic dilatation. The stenosis rate, the interval between the first endoscopic dilation and the completion of ESD, the number of esophageal triamcinolone acetonide filling, the healing time after ESD, and the speed and method of squamous epithelium regeneration were observed. The secondary observations were adverse events such as bleeding and perforation after ESD and adverse events related to steroid hormone.Results:No adverse events occurred after ESD in 14 patients. Only 1 patient developed esophageal stenosis, the incidence of stenosis was 7.1% (1/14). The interval between the first dilation and ESD was 39 days. Thirteen patients achieved squamous epithelium regeneration without stenosis or adverse events related to steroid hormone. The median number of esophageal triamcinolone acetonide filling was 6.5 times (4.0-14.0 times), the median healing time was 40 days (32-94 days), and the median healing speed was 0.61 cm2/d (0.30-1.55 cm2/d).Conclusion:Esophageal triamcinolone acetonide filling combined with short-course oral methylprednisolone for the prevention of esophageal stenosis after large-area ESD is effective and safe in the short-term follow-up.

Value of EUS in determining infiltration depth of early carcinoma and associated precancerous lesions in the upper gastrointestinal tract.

Objective: The objective is to evaluate the value of EUS in the determination of infiltration depth of early carcinoma and precancerous lesions in the upper gastrointestinal tract and to analyze the various factors affecting the accuracy of EUS. Methods: One hundred and sixty-three patients diagnosed with early gastric cancer or early esophageal cancer, and associated precancerous lesions, who were seen in our hospital in the recent 10 years were selected. These patients received EUS before endoscopic submucosal dissection or surgery. With a pathological diagnosis as the gold standard, the accuracy, sensitivity, specificity, and misjudgment rate of EUS in determining the invasion depth were evaluated using the pathological stratification (mucosa, M1/2; muscularis mucosa, M3; submucosa, [SM]; and muscularis propria) or TN stratification (mucosa, T1a; SM, T1b), and the possible causes of miscalculation were analyzed. Results: Based on the pathological stratification, the overall accuracy of EUS was 78.5%, and the overestimation and underestimation rates were 17.8% and 3.7%, respectively. Based on the TN stratification, the overall accuracy of EUS was 81%, and the overestimation and underestimation rates were 16.6% and 2.5%, respectively. There was a significant difference between the groups in terms of overestimation and underestimation rates (P < 0.05), indicating that EUS was more likely to overestimate the depth. Univariate analysis showed that the factors affecting accuracy included lesion size, macroscopic features, sunken mucosa, mucosa with granular and nodular changes, and ulceration. Multivariate logistic regression analysis revealed that larger lesions, mucosa with granular and nodular changes, and ulceration were independent risk factors for the overestimation of infiltration depth by EUS. Conclusion: EUS is highly accurate in determining the infiltration depth of early cancer and precancerous lesions in the upper gastrointestinal tract. It also has a good reference value for treatment selection and prognostication. However, attention should be paid to its overestimation, especially accompanied by the aforementioned factors.