Robustness evaluation of deep neural networks for endoscopic image analysis: Insights and strategies.

Computer-aided detection and diagnosis systems (CADe/CADx) in endoscopy are commonly trained using high-quality imagery, which is not representative for the heterogeneous input typically encountered in clinical practice. In endoscopy, the image quality heavily relies on both the skills and experience of the endoscopist and the specifications of the system used for screening. Factors such as poor illumination, motion blur, and specific post-processing settings can significantly alter the quality and general appearance of these images. This so-called domain gap between the data used for developing the system and the data it encounters after deployment, and the impact it has on the performance of deep neural networks (DNNs) supportive endoscopic CAD systems remains largely unexplored. As many of such systems, for e.g. polyp detection, are already being rolled out in clinical practice, this poses severe patient risks in particularly community hospitals, where both the imaging equipment and experience are subject to considerable variation. Therefore, this study aims to evaluate the impact of this domain gap on the clinical performance of CADe/CADx for various endoscopic applications. For this, we leverage two publicly available data sets (KVASIR-SEG and GIANA) and two in-house data sets. We investigate the performance of commonly-used DNN architectures under synthetic, clinically calibrated image degradations and on a prospectively collected dataset including 342 endoscopic images of lower subjective quality. Additionally, we assess the influence of DNN architecture and complexity, data augmentation, and pretraining techniques for improved robustness. The results reveal a considerable decline in performance of 11.6% (±1.5) as compared to the reference, within the clinically calibrated boundaries of image degradations. Nevertheless, employing more advanced DNN architectures and self-supervised in-domain pre-training effectively mitigate this drop to 7.7% (±2.03). Additionally, these enhancements yield the highest performance on the manually collected test set including images with lower subjective quality. By comprehensively assessing the robustness of popular DNN architectures and training strategies across multiple datasets, this study provides valuable insights into their performance and limitations for endoscopic applications. The findings highlight the importance of including robustness evaluation when developing DNNs for endoscopy applications and propose strategies to mitigate performance loss.

COMPUTER-AIDED DIAGNOSIS IMPROVES CHARACTERIZATION OF BARRETT'S NEOPLASIA BY GENERAL ENDOSCOPISTS.

BACKGROUND & AIMS: Characterization of visible abnormalities in Barrett esophagus (BE) patients can be challenging, especially for unexperienced endoscopists. This results in suboptimal diagnostic accuracy and poor inter-observer agreement. Computer-aided diagnosis (CADx) systems may assist endoscopists. We aimed to develop, validate and benchmark a CADx system for BE neoplasia. METHODS: The CADx system received pretraining with ImageNet with consecutive domain-specific pretraining with GastroNet which includes 5 million endoscopic images. It was subsequently trained and internally validated using 1,758 narrow-band imaging (NBI) images of early BE neoplasia (352 patients) and 1,838 NBI images of non-dysplastic BE (173 patients) from 8 international centers. CADx was tested prospectively on corresponding image and video test sets with 30 cases (20 patients) of BE neoplasia and 60 cases (31 patients) of non-dysplastic BE. The test set was benchmarked by 44 general endoscopists in two phases (phase 1: no CADx assistance; phase 2: with CADx assistance). Ten international BE experts provided additional benchmark performance. RESULTS: Stand-alone sensitivity and specificity of the CADx system were 100% and 98% for images and 93% and 96% for videos, respectively. CADx outperformed general endoscopists without CADx assistance in terms of sensitivity (p=0.04). Sensitivity and specificity of general endoscopist increased from 84% to 96% and 90 to 98% with CAD assistance (p<0.001), respectively. CADx assistance increased endoscopists' confidence in characterization (p<0.001). CADx performance was similar to Barrett experts. CONCLUSION: CADx assistance significantly increased characterization performance of BE neoplasia by general endoscopists to the level of expert endoscopists. The use of this CADx system may thereby improve daily Barrett surveillance.

The use of a real-time computer-aided detection system for visible lesions in the Barrett's esophagus during live endoscopic procedures, a pilot study.

BACKGROUND AND AIMS: In this pilot study we evaluated performance of a recently developed computer-aided detection (CADe) system for Barrett's neoplasia during live endoscopic procedures. METHODS: 15 patients with and 15 without a visible lesion were included in this study. A CAD assisted workflow was employed that included: a slow pullback video recording of the entire Barrett's segment with live CADe assistance, followed by CADe assisted level-based video recordings every 2cm of the Barrett's segment. Outcomes were per patient and per level diagnostic accuracy of the CAD assisted workflow, where the primary outcome was per patient in-vivo CADe sensitivity. RESULTS: In the per patient analyses, the CADe system detected all visible lesions (sensitivity 100%). Per patient CADe specificity was 53%. Per-level sensitivity and specificity of the CADe assisted workflow were 100% and 73%, respectively. CONCLUSION: In this pilot study, the CADe system detected all potentially neoplastic lesions in Barrett's esophagus comparable to an expert endoscopist. Continued refinement of the system may improve specificity. External validation in larger multicenter studies is planned.

Incidence and Prediction of Unrelated Mortality After Successful Endoscopic Eradication Therapy for Barrett's Neoplasia.

BACKGROUND & AIMS: Follow-up (FU) strategies after endoscopic eradication therapy (EET) for Barrett's neoplasia do not consider the risk of mortality from causes other than esophageal adenocarcinoma (EAC). We aimed to evaluate this risk during long-term FU, and to assess whether the Charlson Comorbidity Index (CCI) can predict mortality. METHODS: We included all patients with successful EET from the nationwide Barrett registry in the Netherlands. Data were merged with National Statistics for accurate mortality data. We evaluated annual mortality rates (AMRs, per 1000 person-years) and standardized mortality ratio for other-cause mortality. Performance of the CCI was evaluated by discrimination and calibration. RESULTS: We included 1154 patients with a mean age of 64 years (±9). During median 59 months (p25-p75 37-91; total 6375 person-years), 154 patients (13%) died from other causes than EAC (AMR, 24.1; 95% CI, 20.5-28.2), most commonly non-EAC cancers (n = 58), cardiovascular (n = 31), or pulmonary diseases (n = 26). Four patients died from recurrent EAC (AMR, 0.5; 95% CI, 0.1-1.4). Compared with the general Dutch population, mortality was significantly increased for patients in the lowest 3 age quartiles (ie, age <71 years). Validation of CCI in our population showed good discrimination (Concordance statistic, 0.78; 95% CI, 0.72-0.84) and fair calibration. CONCLUSION: The other-cause mortality risk after successful EET was more than 40 times higher (48; 95% CI, 15-99) than the risk of EAC-related mortality. Our findings reveal that younger post-EET patients exhibit a significantly reduced life expectancy when compared with the general population. Furthermore, they emphasize the strong predictive ability of CCI for long-term mortality after EET. This straightforward scoring system can inform decisions regarding personalized FU, including appropriate cessation timing. (NL7039).

Management of high risk T1 esophageal adenocarcinoma following endoscopic resection.

High-risk T1 esophageal adenocarcinoma (HR-T1 EAC) is defined as T1 cancer, with one or more of the following histological criteria: submucosal invasion, poorly or undifferentiated cancer, and/or presence of lympho-vascular invasion. Esophagectomy has long been the only available treatment for these HR-T1 EACs and was considered necessary because of a presumed high risk of lymph node metastases up to 46%. However, endoscopic submucosal disscection have made it possible to radically remove HR-T1 EAC, irrespective of size, while leaving the esophageal anatomy intact. Parallel to this development, new publications demonstrated that the risk of lymph node metastases for HR-T1 EAC may be even <24%. Therefore, indications for endoscopic treatment of HR-T1 EAC are being reconsidered and current research aims at finding the optimal management strategy for this indication, where watchful waiting may proof to be an acceptable strategy in selected patients. In this review, we will discuss the latest developments in this field.

Endoscopic submucosal dissection for early esophageal squamous cell carcinoma: long-term results from a Western cohort.

BACKGROUND: Although endoscopic submucosal dissection (ESD) is established as first-choice treatment for early esophageal squamous cell carcinoma (ESCC) worldwide, most data are derived from Asian studies. We aimed to evaluate the long-term outcomes of ESD for patients with early ESCC in a Western cohort. METHODS: In this retrospective cohort study, patients with early ESCC amenable to ESD were included from four tertiary referral hospitals in the Netherlands between 2012 and 2017. All ESD procedures were performed by experienced endoscopists, after which the decision for additional treatment was made on a per-patient basis. Outcomes were curative resection rate, ESCC-specific survival, and overall survival. RESULTS: Of 68 included patients (mean age 69 years; 34 males), ESD was technically successful in 66 (97%; 95%CI 93%-100%), with curative resection achieved in 34/66 (52%; 95%CI 39%-64%). Among patients with noncurative resection, 15/32 (47%) underwent additional treatment, mainly esophagectomy (n = 10) or definitive chemoradiation therapy (n = 4). Endoscopic surveillance was preferred in 17/32 patients (53%), based on severe comorbidities or patient choice. Overall, 31/66 patients (47%) died during a median follow-up of 66 months; 8/31 (26%) were ESCC-related deaths. The 5-year overall and ESCC-specific survival probabilities were 62% (95%CI 52%-75%) and 86% (95%CI 77%-96%), respectively. CONCLUSION: In this Western cohort with long-term follow-up, the effectiveness and safety of ESD for early ESCC was confirmed, although the rate of noncurative resections was substantial. Irrespective of curative status, the long-term prognosis of these patients was limited mainly due to competing mortality.

Role of the Intestine and Its Gut Microbiota in Metabolic Syndrome and Obesity.

The metabolic syndrome (MetSyn) is currently one of the biggest global health challenges because of its impact on public health. MetSyn includes the cluster of metabolic disorders including obesity, high blood pressure, hyperglycemia, high triglyceride levels, and hepatic steatosis. Together, these abnormalities increase the cardiovascular risk of individuals and pose a threat to healthcare systems worldwide. To better understand and address this complex issue, recent research has been increasingly focusing on unraveling the delicate interplay between metabolic disorders and the intestines and more specifically our gut microbiome. The gut microbiome entails all microorganisms inhabiting the gastrointestinal tract and plays a pivotal role in metabolic processes and overall health of its host. Emerging evidence proves an association between the gut microbiome composition and aspects of MetSyn, such as obesity. Understanding these relationships is crucial because they offer valuable insights into the mechanisms underlying development and progression of metabolic disorders and possible treatment options. Yet, how should we interpret this relationship? This review focuses on the interplay between the gut and MetSyn. In addition, we have reviewed the existing evidence of the gut microbiome and its association with and impact on metabolic disorders, in an attempt to understand the complex interactions and nature of this association. We also explored potential therapeutic options targeting the gut to modify metabolic disorders and obesity.

Vertical tumor-positive resection margins and the risk of residual neoplasia after endoscopic resection of Barrett's neoplasia: a nationwide cohort with pathology reassessment.

BACKGROUND: This study evaluated the proportion of patients with residual neoplasia after endoscopic resection (ER) for Barrett's neoplasia with confirmed tumor-positive vertical resection margin (R1v). METHODS: This retrospective cohort study included patients undergoing ER for Barrett's neoplasia with histologically documented R1v since 2008 in the Dutch Barrett Expert Centers. We defined R1v as cancer cells touching vertical resection margins and Rx as nonassessable margins. Reassessment of R1v specimens was performed by experienced pathologists until consensus was reached regarding vertical margins. RESULTS: 101/110 included patients had macroscopically complete resections (17 T1a, 84 T1b), and 99/101 (98%) ER specimens were histologically reassessed, with R1v confirmed in 74 patients (75%), Rx in 16%, and R0 in 9%. Presence/absence of residual neoplasia could be assessed in 66/74 patients during endoscopic reassessment (52) and/or in the surgical resection specimen (14), and 33/66 (50%) had residual neoplasia. Residual neoplasia detected during endoscopy was always endoscopically visible and biopsies from a normal-appearing ER scar did not detect additional neoplasia. Of 25 patients who underwent endoscopic follow-up (median 37 months [interquartile range 12-50]), 4 developed local recurrence (16.0%), all detected as visible abnormalities. CONCLUSIONS: After ER with R1v, 50% of patients had no residual neoplasia. Histological evaluation of ER margins appears challenging, as in this study 75% of documented R1v cases were confirmed during reassessment. Endoscopic reassessment 8-12 weeks after ER seems to accurately detect residual neoplasia and can help to determine the most appropriate strategy for patients with R1v.

Insulin sensitivity and beta cell function after Duodenal Mucosal Resurfacing (DMR): An Open-Label, Mechanistic, Pilot Study.

BACKGROUND AND AIMS: The duodenum has been shown to play a key role in glucose homeostasis. Duodenal mucosal resurfacing (DMR) is an endoscopic procedure for patients with type 2 diabetes (T2D) in which the duodenal mucosa is hydrothermally ablated. DMR improves glycemic control, but the underlying mechanisms remain unclear. Here, we report changes in glucoregulatory hormones and indices of insulin sensitivity and beta cell function after DMR. METHODS: We included 28 patients on non-insulin glucose lowering medications who underwent open-label DMR and a mixed meal test (MMT) in Revita-1 or Revita-2. Inclusion criteria were hemoglobin A1c (HbA1c) 7.6-10.4% and BMI 24-40kg/m2. Baseline and 3-months MMT data included plasma glucose, insulin, C-peptide, glucagon-like peptide-1 (GLP-1), and gastric inhibitory polypeptide (GIP) concentrations. Glucoregulatory hormones, insulin sensitivity indices (homeostatic model assessment for insulin resistance [HOMA-IR], Matsuda index [MI] and hepatic insulin resistance [HIR]), and beta cell function (insulinogenic index [IGI], disposition index [DI] and insulin secretion rate [ISR]) were assessed. RESULTS: Fasting insulin, glucagon, and C-peptide decreased significantly. Insulin sensitivity (HOMA-IR, MI, and HIR) and beta cell function (DI and ISR) all improved significantly. Decline in postprandial glucose, mainly driven by a decrease in fasting levels, was observed, as well as a decline in postprandial glucagon whereas GLP-1 and GIP did not change. CONCLUSIONS: Insulin sensitivity and insulin secretion improved 3 months after DMR. It is unlikely that incretin changes are responsible for improved glucose control after DMR. These data add to the growing evidence validating the duodenum as a therapeutic target for patients with T2D.

Western outcomes of circumferential endoscopic submucosal dissection for early esophageal squamous cell carcinoma.

BACKGROUND AND AIMS: Circumferential endoscopic submucosal dissection (cESD) in the esophagus has been reported to be feasible in small Eastern case series. We assessed the outcomes of cESD in the treatment of early esophageal squamous cell carcinoma (ESCC) in Western countries. METHODS: We conducted an international study at 25 referral centers in Europe and Australia using prospective databases. We included all patients with ESCC treated with cESD before November 2022. Our main outcomes were curative resection according to European guidelines and adverse events. RESULTS: A total of 171 cESDs were performed on 165 patients. En bloc and R0 resections rates were 98.2% (95% confidence interval [CI], 95.0-99.4) and 69.6% (95% CI, 62.3-76.0), respectively. Curative resection was achieved in 49.1% (95% CI, 41.7-56.6) of the lesions. The most common reason for noncurative resection was deep submucosal invasion (21.6%). The risk of stricture requiring 6 or more dilations or additional techniques (incisional therapy/stent) was high (71%), despite the use of prophylactic measures in 93% of the procedures. The rates of intraprocedural perforation, delayed bleeding, and adverse cardiorespiratory events were 4.1%, 0.6%, and 4.7%, respectively. Two patients died (1.2%) of a cESD-related adverse event. Overall and disease-free survival rates at 2 years were 91% and 79%. CONCLUSIONS: In Western referral centers, cESD for ESCC is curative in approximately half of the lesions. It can be considered a feasible treatment in selected patients. Our results suggest the need to improve patient selection and to develop more effective therapies to prevent esophageal strictures.

The Tissue Systems Pathology Test Outperforms Pathology Review in Risk Stratifying Patients With Low-Grade Dysplasia.

BACKGROUND & AIMS: Low-grade dysplasia (LGD) is associated with an increased risk of progression in Barrett's esophagus (BE); however, the diagnosis of LGD is limited by substantial interobserver variability. Multiple studies have shown that an objective tissue systems pathology test (TissueCypher Barrett's Esophagus Test, TSP-9), can effectively predict neoplastic progression in patients with BE. This study aimed to compare the risk stratification performance of the TSP-9 test vs benchmarks of generalist and expert pathology. METHODS: A blinded cohort study was conducted in the screening cohort of a randomized controlled trial of patients with BE with community-based LGD. Biopsies from the first endoscopy with LGD were assessed by the TSP-9 test and independently reviewed by 30 pathologists from 5 countries per standard practice. The accuracy of the test and the diagnoses in predicting high-grade dysplasia (HGD) and esophageal adenocarcinoma (EAC) were compared. RESULTS: A total of 154 patients with BE (122 men), mean age 60.9 ± 9.8 years were studied. Twenty-four patients progressed to HGD/EAC within 5 years (median time of 1.7 years) and 130 did not progress to HGD/EAC within 5 years (median 7.8 years follow-up). The TSP-9 test demonstrated higher sensitivity (71% vs mean 63%, range 33%-88% across 30 pathologists), than the pathology review in detecting patients who progressed (P = .01186). CONCLUSIONS: The TSP-9 test outperformed the pathologists in risk stratifying patients with BE with LGD. Care guided by the test can provide an effective solution to variable pathology review of LGD, improving health outcomes by upstaging care to therapeutic intervention for patients at high risk for progression, while reducing unnecessary interventions in low-risk patients.

A Tissue Systems Pathology Test Outperforms the Standard-of-Care Variables in Predicting Progression in Patients With Barrett's Esophagus.

INTRODUCTION: Objective risk stratification is needed for patients with Barrett's esophagus (BE) to enable risk-aligned management to improve health outcomes. This study evaluated the predictive performance of a tissue systems pathology [TSP-9] test (TissueCypher) vs current clinicopathologic variables in a multicenter cohort of patients with BE. METHODS: Data from 699 patients with BE from 5 published studies on the TSP-9 test were evaluated. Five hundred nine patients did not progress during surveillance, 40 were diagnosed with high-grade dysplasia/esophageal adenocarcinoma (HGD/EAC) within 12 months, and 150 progressed to HGD/EAC after 12 months. Age, sex, segment length, hiatal hernia, original and expert pathology review diagnoses, and TSP-9 risk classes were collected. The predictive performance of clinicopathologic variables and the TSP-9 test was compared, and the TSP-9 test was evaluated in clinically relevant patient subsets. RESULTS: The sensitivity of the TSP-9 test in detecting progressors was 62.3% compared with 28.3% for expert-confirmed low-grade dysplasia (LGD), while the original diagnosis abstracted from medical records did not provide any significant risk stratification. The TSP-9 test identified 57% of progressors with nondysplastic Barrett's esophagus (NDBE) ( P < 0.0001). Patients with NDBE who scored TSP-9 high risk progressed at a similar rate (3.2%/yr) to patients with expert-confirmed LGD (3.7%/yr). The TSP-9 test provided significant risk stratification in clinically low-risk patients (NDBE, female, short-segment BE) and clinically high-risk patients (IND/LGD, male, long-segment BE) ( P < 0.0001 for comparison of high-risk classes vs low-risk classes). DISCUSSION: The TSP-9 test predicts risk of progression to HGD/EAC independently of current clinicopathologic variables in patients with BE. The test provides objective risk stratification results that may guide management decisions to improve health outcomes for patients with BE.

An Automated Tissue Systems Pathology Test Can Standardize the Management and Improve Health Outcomes for Patients With Barrett's Esophagus.

INTRODUCTION: Low-grade dysplasia (LGD) in Barrett's esophagus (BE) is associated with an increased risk of progression to high-grade dysplasia or esophageal adenocarcinoma. However, because of substantial interobserver variability in the diagnosis of LGD, a patient's management plan and health outcome depend largely on which pathologist reviews their case. This study evaluated the ability of a tissue systems pathology test that objectively risk stratifies patients with BE (TissueCypher, TSP-9) to standardize management in a manner consistent with improved health outcomes for patients with BE. METHODS: A total of 154 patients with BE with community-based LGD from the prospectively followed screening cohort of the SURF trial were studied. Management decisions were simulated 500 times with varying generalist (n = 16) and expert (n = 14) pathology reviewers to determine the most likely care plan with or without use of the TSP-9 test for guidance. The percentage of patients receiving appropriate management based on the known progression/nonprogression outcomes was calculated. RESULTS: The percentage of patients with 100% of simulations resulting in appropriate management significantly increased from 9.1% for pathology alone, to 58.4% when TSP-9 results were used with pathology, and further increased to 77.3% of patients receiving appropriate management when only TSP-9 results were used. Use of the test results also significantly increased the consistency of management decisions for patients when their slides were reviewed by different pathologists ( P < 0.0001). DISCUSSION: Management guided by the TSP-9 test can standardize care plans by increasing the early detection of progressors who can receive therapeutic interventions, while also increasing the percentage of nonprogressors who can avoid unnecessary therapy and be managed by surveillance alone.

Endoscopic vacuum therapy for anastomotic leakage after upper gastrointestinal surgery.

BACKGROUND: Recently, endoscopic vacuum therapy (EVT) was introduced as treatment for anastomotic leakage after upper gastrointestinal (GI) surgery. The aim of this study was to describe the initial experience with EVT for anastomotic leakage after upper GI surgery in a tertiary referral center. METHODS: Patients treated with EVT for anastomotic leakage after upper GI surgery were included retrospectively (January 2018-June 2021) and prospectively (June 2021-October 2021). The primary end point was the EVT success rate. Secondary end points included mortality and adverse events. RESULTS: 38 patients were included (31 men; mean age 66 years): 27 had undergone an esophagectomy with gastric conduit reconstruction and 11 a total gastrectomy with esophagojejunal anastomosis. EVT was successful in 28 patients (74 %, 95 %CI 57 %-87 %). In 10 patients, EVT failed: deceased owing to radiation pneumonitis (n = 1), EVT-associated complications (n = 2), and defect closure not achieved (n = 7). Mean duration of successful EVT was 33 days, with a median of six EVT-related endoscopies. Median hospital stay was 45 days. CONCLUSION: This initial experience with EVT for anastomotic leakage after upper GI surgery demonstrated a success rate of 74 %. EVT is a promising therapy that could prevent further major surgery. More experience with the technique and its indications will likely improve success rates in the future.

Towards a robust and compact deep learning system for primary detection of early Barrett's neoplasia: Initial image-based results of training on a multi-center retrospectively collected data set.

INTRODUCTION: Endoscopic detection of early neoplasia in Barrett's esophagus is difficult. Computer Aided Detection (CADe) systems may assist in neoplasia detection. The aim of this study was to report the first steps in the development of a CADe system for Barrett's neoplasia and to evaluate its performance when compared with endoscopists. METHODS: This CADe system was developed by a consortium, consisting of the Amsterdam University Medical Center, Eindhoven University of Technology, and 15 international hospitals. After pretraining, the system was trained and validated using 1.713 neoplastic (564 patients) and 2.707 non-dysplastic Barrett's esophagus (NDBE; 665 patients) images. Neoplastic lesions were delineated by 14 experts. The performance of the CADe system was tested on three independent test sets. Test set 1 (50 neoplastic and 150 NDBE images) contained subtle neoplastic lesions representing challenging cases and was benchmarked by 52 general endoscopists. Test set 2 (50 neoplastic and 50 NDBE images) contained a heterogeneous case-mix of neoplastic lesions, representing distribution in clinical practice. Test set 3 (50 neoplastic and 150 NDBE images) contained prospectively collected imagery. The main outcome was correct classification of the images in terms of sensitivity. RESULTS: The sensitivity of the CADe system on test set 1 was 84%. For general endoscopists, sensitivity was 63%, corresponding to a neoplasia miss-rate of one-third of neoplastic lesions and a potential relative increase in neoplasia detection of 33% for CADe-assisted detection. The sensitivity of the CADe system on test sets 2 and 3 was 100% and 88%, respectively. The specificity of the CADe system varied for the three test sets between 64% and 66%. CONCLUSION: This study describes the first steps towards the establishment of an unprecedented data infrastructure for using machine learning to improve the endoscopic detection of Barrett's neoplasia. The CADe system detected neoplasia reliably and outperformed a large group of endoscopists in terms of sensitivity.

Vacuum-stent: A combination of endoscopic vacuum therapy and an intraluminal stent for treatment of esophageal transmural defects.

Introduction: Endoscopic vacuum therapy (EVT) has gained a greater role in management of transmural defects in the upper gastrointestinal (GI) tract, including anastomotic leakage and esophageal perforation (e.g. Boerhaave syndrome and iatrogenic causes). The vacuum-stent is a new treatment modality, combining the benefits of EVT and an intraluminal stent. Patients and methods: This prospective case series describes the first ten cases of a transmural defect in the upper GI tract treated with a vacuum-stent in a tertiary referral center. All patients signed informed consent for prospective registration of relevant data on treatment and outcomes in a specially designed database. Outcome parameters were successful closure of the defect, number of endoscopies, duration of treatment and adverse events. Results: In total, ten patients treated with a vacuum-stent were included. Eight patients had anastomotic leakage after esophageal resection, of whom six were treated with vacuum-sponge and vacuum-stent, and two with vacuum-stent only. One patient had Boerhaave syndrome, treated with vacuum-sponge and vacuum-stent, and one had an iatrogenic perforation during pneumodilation for achalasia, treated with vacuum-stent only. Success rate was 100%, requiring a median of 5 (IQR 3-12) EVT-related endoscopies with a treatment course of median 18 (IQR 12-59) days. One patient developed an esophageal stricture, but no other vacuum-stent related adverse events were observed. Conclusion: The vacuum-stent, which combines benefits of EVT and an intraluminal stent, shows great feasibility and efficacy in treatment of transmural defects in the upper GI tract. Future studies should point out whether this device can prevent major (re-)surgery in these patients.

Feasibility and Safety of Tailored Lymphadenectomy Using Sentinel Node-Navigated Surgery in Patients with High-Risk T1 Esophageal Adenocarcinoma.

BACKGROUND: Selective lymphadenectomy using sentinel node-navigated surgery (SNNS) might offer a less invasive alternative to esophagectomy in patients with high-risk T1 esophageal adenocarcinoma (EAC). The aim of this study was to evaluate the feasibility and safety of a new treatment strategy, consisting of radical endoscopic resection of the tumor followed by SNNS. METHODS: In this multicenter pilot study, ten patients with a radically resected high-risk pT1cN0 EAC underwent SNNS. A hybrid tracer of technetium-99m nanocolloid and indocyanine green was injected endoscopically around the resection scar the day before surgery, followed by preoperative imaging. During surgery, sentinel nodes (SNs) were identified using a thoracolaparoscopic gammaprobe and fluorescence-based detection, and subsequently resected. Endpoints were surgical morbidity and number of detected and resected (tumor-positive) SNs. RESULTS: Localization and dissection of SNs was feasible in all ten patients (median 3 SNs per patient, range 1-6). The concordance between preoperative imaging and intraoperative detection was high. In one patient (10%), dissection was considered incomplete after two SNs were not identified intraoperatively. Additional peritumoral SNs were resected in four patients (40%) after fluorescence-based detection. In two patients (20%), a (micro)metastasis was found in one of the resected SNs. One patient experienced neuropathic thoracic pain related to surgery, while none of the patients developed functional gastroesophageal disorders. CONCLUSIONS: SNNS appears to be a feasible and safe instrument to tailor lymphadenectomy in patients with high-risk T1 EAC. Future research with long-term follow-up is warranted to determine whether this esophageal preserving strategy is justified for high-risk T1 EAC.

Intensive endoscopic therapy for untreated cervical anastomotic strictures after esophagectomy: a pilot study.

BACKGROUND: Cervical anastomotic strictures after esophagectomy cause significant disease burden. We aimed to study the technical feasibility and safety of intensive endoscopic therapy. METHODS: In this pilot study, we included 15 patients with an untreated benign cervical anastomotic stricture after esophagectomy. Intensive endoscopic therapy comprised three endoscopic modalities: in- and excision using a needle-knife, intralesional steroid injections and bougie dilation. In two endoscopic procedures, the stricture was dilated up to a luminal diameter of 18 mm. Patients were followed up to 6 months. RESULTS: A luminal diameter of 18 mm was achieved in 13 of 15 patients (87%) after two endoscopic procedures. No major adverse events related to the investigational treatment occurred. Median dysphagia scores significantly improved from 2 (IQR, interquartile range, 2-3) at baseline to 0 (IQR 0-1) after 14 days (p < 0.001). Eleven (73%) patients developed recurrent symptoms of dysphagia requiring a median of 1 (IQR 0-3) additional endoscopic dilation procedure. CONCLUSIONS: Achieving a luminal diameter of 18 mm in two procedures with intensive endoscopic therapy was technically feasible and effective in reducing dysphagia rapidly in patients with a cervical anastomotic stricture after esophagectomy. No major adverse events related to the investigational treatment were observed.

The course of pain and dysphagia after radiofrequency ablation for Barrett's esophagus-related neoplasia.

BACKGROUND: Radiofrequency ablation (RFA) is effective for eradication of Barrett's esophagus (BE) neoplasia, but little is known on the course of pain and dysphagia after RFA. We aimed to describe the course of post-RFA symptoms and to identify possible associated risk factors. METHODS: In this multicenter, observational cohort study, all RFA procedures registered in a prospective database were included. Patient and treatment characteristics were collected from medical records and patients self-registered post-procedural symptoms in electronic symptom diaries for 14 days. Mixed model regression was used for the analyses. RESULTS: In total, 255 diaries were completed. Post-RFA pain was reported for 95 % (95 %CI 93-98) of procedures (median duration 14 days; 25th-75th percentiles [p25-p75] 11-14) and major pain for 64 % (95 %CI 58-69; median duration 8 days, p25-p75 3-13). Post-procedural pain significantly increased with BE length, younger age, and no prior ablation. Dysphagia was present after 83 % (95 %CI 79-88) of procedures (median duration 13 days, p25-p75 9-14). The risk of dysphagia decreased with age and increased when patients experienced more pain. CONCLUSIONS: RFA treatment for BE-related neoplasia seems a significant burden for patients, and post-procedural symptoms should be taken into account when counseling patients before starting endoscopic eradication therapy.