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.

Safety and efficacy of salvage endoscopic submucosal dissection for Barrett's neoplasia recurrence after radiofrequency ablation.

BACKGROUND AND STUDY AIMS: This study evaluated the safety and efficacy of salvage endoscopic submucosal dissection for Barrett's neoplasia recurrence after radiofrequency ablation. PATIENTS AND METHODS: Data from patients at sixteen centers were collected for a multicentric retrospective study. Patients who underwent at least one RFA treatment for Barrett's esophagus and thereafter underwent further esophageal ESD for neoplasia recurrence were included. RESULTS: Data from 56 patients treated by salvage ESD performed between April 2014 and November 2022 were collected. Immediate complications included one muscular tear (1.8%) treated with stent (Agree classification: grade IIIa), two patients had transmural perforations (4%) and five patients had muscular tears (9%) treated with clips and without clinical impact and not considered as adverse event. Seven patients (12.5%) developed strictures, treated by balloon dilation (grade IIIa). Histological analysis showed 36 adenocarcinomas, 17 high-grade dysplasia, and 3 low-grade dysplasia. En-bloc and R0 resection rates were 89% and 66%, respectively. Resections were curative in thirty-three patients (59%), non-curative in 22 patients (39%), including 11 "local risk" (19.5%) and 11 "high risk" resections (19.5%). At the end of follow-up with a median time of 14 [0-75] months after salvage ESD eventually associated with further endoscopic treatment (RFA, argon plasma coagulation, endoscopic mucosal resection, ESD), neoplasia remission ratio was 37/53 (70%) and the median remission time was 13 [1-75] months. CONCLUSION: In expert hands, salvage ESD is a safe and effective treatment for recurrence of Barrett's neoplasia after RFA treatment.

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.

Performance of endoscopic submucosal dissection for undifferentiated early gastric cancer: a multicenter retrospective cohort.

Background and study aims Undifferentiated early gastric cancer (UD-EGC) represents an extended indication for endoscopic submucosal dissection (ESD) based on the existing guidelines. This study evaluated the prevalence of UD-EGC recurrence after ESD, and potentially implicated risk factors. Patients and methods Data from 17 centers were collected retrospectively including demographics, endoscopic and pathological findings, and follow-up data from UD-EGC cases treated by ESD. Patients with incomplete resection or advanced disease were excluded. Descriptive statistics quantified variables and calculated the incidence of recurrence. Chi-square test was applied to assess any link between independent variables and relapse; significantly associated variables were inserted to a multivariable regression model. Results Seventy-one patients were eligible, with 2:1 female to male ratio and age of 65.8 ± 11.8 years. Mean lesion size was 33.5 ± 18.8 mm and the most frequent histological subtype was signet ring-cells UGC (2:1). Patients were followed-up every 5.6 ± 3.7 months with a mean surveillance period of 29.3 ± 15.3 months until data collection. Four patients (5.6%) developed local recurrence 8.8 ± 6.5 months post-ESD, with no lymph node or distal metastases been reported. Lesion size was not associated with recurrence ( P = 0.32), in contrast to lymphovascular and perineural invasion which were independently associated with local recurrence ( P = 0.006 and P < 0.001, respectively). Conclusions ESD could be considered as the initial step to manage UD-EGC, providing at least an "entire-lesion" biopsy to guide therapeutic strategy. When histology confirms absence of lymphovascular and perineural invasion, this modality could be therapeutic, providing low recurrence rates.

Predictors of long-term outcomes of endoscopic submucosal dissection of early gastric neoplasia in the West: a multicenter study.

BACKGROUND: This study aimed to determine long-term outcomes of gastric endoscopic submucosal dissection (ESD) in Western settings based on the latest Japanese indication criteria, and to examine predictors of outcomes and complications. METHODS: Data were collected from consecutive patients undergoing gastric ESD at four participating centers from 2009 to 2021. Retrospective analysis using logistic regression and survival analysis was performed. RESULTS: 415 patients were included (mean age 71.7 years; 56.4 % male). Absolute indication criteria (2018 guideline) were met in 75.3 % of patients. Median follow-up was 52 months. Post-resection histology was adenocarcinoma, high grade dysplasia, and low grade dysplasia in 49.9 %, 22.7 %, and 17.1 %, respectively. Perforation, early and delayed bleeding occurred in 2.4 %, 4.3 %, and 3.4 %, respectively. Rates of en bloc and R0 resection, and recurrence on first endoscopic follow-up were 94.7 %, 83.4 %, and 2.7 %, respectively. Relative indication (2018 guideline) for ESD was associated with R1 outcome (P = 0.02). Distal location (P = 0.002) and increased procedure time (P = 0.04) were associated with bleeding, and scarring (P = 0.009) and increased procedure duration (P = 0.003) were associated with perforation. Recurrence-free survival at 2 and 5 years was 94 % and 83 %, respectively. CONCLUSION: This is the largest Western multicenter cohort and suggests that gastric ESD is safe and effective in the Western setting. A quarter of patients fell outside the new absolute indications for ESD, suggesting that Western practice involves more advanced lesions. We identified the predictors of complications, which should help to inform future Western practice and research.

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.

Endoscopic vacuum therapy for esophageal perforation: a multicenter retrospective cohort study.

BACKGROUND : Endoscopic vacuum therapy (EVT) is a novel treatment for esophageal perforations. This study aimed to describe initial experience with EVT of esophageal perforations due to iatrogenic cause, Boerhaave syndrome, or other perforations not related to prior upper gastrointestinal surgery. METHODS : Data from patients treated with EVT for esophageal perforation at five hospitals in three European countries, between January 2018 and October 2021, were retrospectively collected. The primary end point was successful defect closure by EVT, with or without the use of other endoscopic treatment modalities. Secondary end points included mortality and adverse events. RESULTS : 27 patients were included (median age 71 years). The success rate was 89 % (24/27, 95 %CI 77-100). EVT failed in three patients: two deceased during EVT (septic embolic stroke, pulmonary embolism) and one underwent esophagectomy due to a persisting defect. Two adverse events occurred: one iatrogenic defect expansion during sponge exchange and one hemorrhage during sponge removal. Median treatment duration was 12 days (interquartile range [IQR] 6-16) with 1 sponge exchange (IQR 1-3). CONCLUSION : EVT is a promising organ-preserving treatment for esophageal perforations, with a success rate of 89 %. More experience with the technique and indications will likely improve success rates.

Endoscopic Submucosal Dissection (ESD) Offers a Safer and More Cost-effective Alternative to Transanal Endoscopic Microsurgery (TEM): An International Collaborative Study.

BACKGROUND: Endoscopic submucosal dissection (ESD) and transanal endoscopic microsurgery (TEM) are minimally invasive procedures that treat early rectal cancer (ERC). Both are effective treatments, yet there are very few studies comparing them. The aim of our study was to identify ideal candidates for each procedure. MATERIALS AND METHODS: Between January 2016 and November 2019, 204 ERC patients were managed with either ESD (n=101) or TEM (n=103) at 7 international centers. Data analyzed included clinical success, tumor characteristics, procedure info, and recurrence rates. RESULTS: Median tumor size was 40 mm±23.9 in the ESD group and 56 mm±27.9 in the TEM group, significantly larger in the latter ( P <0.00001). Average procedure time was 131.5±67.9 minutes in ESD group and 104.9±28.4 minutes in TEM group ( P =0.000347). Average hospital stay was 3.3±2.6 days in the ESD group and 4.7±0.7 days in the TEM group ( P <0.00001). Adverse event rate was 6.8% in the ESD group and 24% in the TEM group. There were no significant difference in the rate of en bloc resection, technical success, tumor location, necessity of additional procedures, and tumor recurrence rates. CONCLUSION: Compared with TEM, ESD is a safer procedure with shorter hospital stay and should be offered for patients who have ERC.

Wide-area transepithelial sampling with computer-assisted analysis to detect high grade dysplasia and cancer in Barrett's esophagus: a multicenter randomized study.

BACKGROUND: Current surveillance for Barrett's esophagus (BE), consisting of four-quadrant random forceps biopsies (FBs), has an inherent risk of sampling error. Wide-area transepithelial sampling (WATS) may increase detection of high grade dysplasia (HGD) and esophageal adenocarcinoma (EAC). In this multicenter randomized trial, we aimed to evaluate WATS as a substitute for FB. METHODS: Patients with known BE and a recent history of dysplasia, without visible lesions, at 17 hospitals were randomized to receive either WATS followed by FB or vice versa. All WATS samples were examined, with computer assistance, by at least two experienced pathologists at the CDx Diagnostics laboratory. Similarly, all FBs were examined by two expert pathologists. The primary end point was concordance/discordance for detection of HGD/EAC between the two techniques. RESULTS: 172 patients were included, of whom 21 had HGD/EAC detected by both modalities, 18 had HGD/EAC detected by WATS but missed by FB, and 12 were detected by FB but missed by WATS. The detection rate of HGD/EAC did not differ between WATS and FB (P = 0.36). Using WATS as an adjunct to FB significantly increased the detection of HGD/EAC vs. FB alone (absolute increase 10 % [95 %CI 6 % to 16 %]). Mean procedural times in minutes for FB alone, WATS alone, and the combination were 6.6 (95 %CI 5.9 to 7.1), 4.9 (95 %CI 4.1 to 5.4), and 11.2 (95 %CI 10.5 to 14.0), respectively. CONCLUSIONS: Although the combination of WATS and FB increases dysplasia detection in a population of BE patients enriched for dysplasia, we did not find a statistically significant difference between WATS and FB for the detection of HGD/EAC as single modality.

Dysplastic Recurrence After Successful Treatment for Early Barrett's Neoplasia: Development and Validation of a Prediction Model.

BACKGROUND & AIMS: The combination of endoscopic resection and radiofrequency ablation is the treatment of choice for eradication of Barrett's esophagus (BE) with dysplasia and/or early cancer. Currently, there are no evidence-based recommendations on how to survey patients after successful treatment, and most patients undergo frequent follow-up endoscopies. We aimed to develop and externally validate a prediction model for visible dysplastic recurrence, which can be used to personalize surveillance after treatment. METHODS: We collected data from the Dutch Barrett Expert Center Registry, a nationwide registry that captures outcomes from all patients with BE undergoing endoscopic treatment in the Netherlands in a centralized care setting. We used predictors related to demographics, severity of reflux, histologic status at baseline, and treatment characteristics. We built a Fine and Gray survival model with least absolute shrinkage and selection operator penalization to predict the incidence of visible dysplastic recurrence after initial successful treatment. The model was validated externally in patients with BE treated in Switzerland and Belgium. RESULTS: A total of 1154 patients with complete BE eradication were included for model building. During a mean endoscopic follow-up of 4 years, 38 patients developed recurrent disease (1.0%/person-year). The following characteristics were independently associated with recurrence (strongest to weakest predictor): a new visible lesion during treatment phase, higher number of endoscopic resection treatments, male sex, increasing BE length, high-grade dysplasia or cancer at baseline, and younger age. External validation showed a C-statistic of 0.91 (95% confidence interval, 0.86-0.94) with good calibration. CONCLUSIONS: This is the first externally validated model to predict visible dysplastic recurrence after successful endoscopic eradication treatment of BE with dysplasia or early cancer. On external validation, our model has good discrimination and calibration. This model can help clinicians and patients to determine a personalized follow-up strategy.

Prophylactic endoluminal vacuum therapy after major gastrointestinal surgery: a systematic review.

In the last decade, endoluminal vacuum therapy (eVAC) has emerged as an effective treatment for anastomotic leak (AL); however, little is known regarding its prophylactic use. In this systematic review we evaluated overall outcomes in patients undergoing major gastrointestinal surgery and treated with prophylactic eVAC. A systematic review of English articles on four electronic databases was performed according to the PRISMA statement up until January 2022. References of selected articles were manually screened to identify relevant missing papers. Primary endpoints were AL and mortality rates estimates. Secondary endpoints included analysis of eVAC-associated morbidity, treatment duration, long-term complications, and general indications for the eVAC management in the perioperative period. A total of 11 studies (5 case reports, 5 retrospective case series and a retrospective, case-control study) were included in the analysis. AL ranged from 0 to 25%. No major eVAC-associated complications were observed, except for sponge dislocation or obstruction. Overall mortality ranged between 0 and 12.5%; however, these fatalities were neither related to the use of eVAC, nor to AL-associated complications. The most frequent long-term complication was anastomotic stenosis responsive to endoscopic dilatation in most cases. The operating negative pressure ranged from -25 to -125 mmHg among different papers. In all studies but two, prophylactic eVAC was applied to anastomoses at high risk of dehiscence based on the subjective evaluation of the leading surgeon. In conclusion, prophylactic eVAC is safe and it could lead to potential benefit for prevention of AL, especially in high-risk anastomoses.

Perianastomotic Irrigation With Passive Drainage Dramatically Decreases POPF Rate After High-risk Pancreaticoduodenectomy.

Objective: To assess whether prophylactic irrigation and passive drainage of pancreatico-jejunal anastomosis could reduce leak and mortality rates after high-risk pancreaticoduodenectomies. Background: Postoperative pancreatic fistula (POPF) is a life-threatening complication following pancreaticoduodenectomy. Several risk factors have been proposed likewise potential mitigation strategies. Regarding the latter, surgical drain policy remains a "hot topic." We propose an innovative approach to mitigate POPF and POPF-related mortality following high-risk pancreaticoduodenectomies. Methods: One hundred fifty-seven patients undergoing pancreaticoduodenectomy between January 2012 and November 2021 were included in the study. Subjects with main pancreatic duct ≤ 3 mm and soft parenchyma were classified as high-risk for POPF development. Since August 2015, high-risk patients received prophylactic irrigation and drainage of the perianastomotic area. These patients were compared with risk-matched historical controls. Results: We identified 73 high-risk patients. Of these, the 47 subjects receiving prophylactic perianastomotic irrigation showed significantly lower POPF rates (12.7% vs 69.2%, P < 0.001). Multivariate regression analysis confirmed the significant association between irrigation drainages and POPF (odds ratio 0.014, P = 0.01). Although not significant, mortality was lower in the irrigation group (4.2% vs 13.0%, P = 0.340). However, none of the fatalities in the irrigation-drainage group were POPF-related. No significant difference in length of hospital stay was observed between the 2 groups (18.0 vs 21.0 days, P = 0.091). Conclusions: Irrigation and drainage of the perianastomotic area represents a powerful approach to reduce POPF and, potentially, mortality after high-risk pancreaticoduodenectomies.

Durability of per-oral endoscopic myotomy beyond 6 years.

Background and study aims The aim of this study was to assess long-term clinical outcomes beyond 6 years in patients who underwent per-oral endoscopic myotomy (POEM) for the treatment of achalasia. Patients and methods Patients with achalasia who underwent POEM between 2010 and 2012 and had follow-up of at least 6 years were retrospectively identified at eight tertiary care centers. The primary outcome evaluated was clinical success defined by an Eckardt symptom score (ESS) ≤ 3 for the duration of the follow-up period. The clinical success cohort was compared to failure (ESS > 3 at any time during follow-up) in order to identify characteristics associated with symptom relapse. The incidence of patient-reported gastroesophageal reflux (GER) was also evaluated. Results Seventy-three patients with 6-year follow-up data were identified. Sustained clinical remission was noted in 89 % (65/73) at 6-years. Mean ESS decreased from 7.1 ±â€Š2.3 pre-procedure to 1.1 ±â€Š1.1 at 6 years ( P  < 0.001). Symptomatic reflux was reported by 27 of 72 patients (37.5 %). Type I achalasia (OR 10.8, P  = 0.04) was found to be associated with clinical failure on logistic regression analysis. Conclusions In patients with achalasia, POEM provides high initial clinical success with excellent long-term outcomes. There are high rates of patient-reported gastroesophageal reflux post-procedure which persist at long-term follow-up.

Endoscopic management of superficial nonampullary duodenal tumors: European Society of Gastrointestinal Endoscopy (ESGE) Guideline.

1: ESGE recommends that all duodenal adenomas should be considered for endoscopic resection as progression to invasive carcinoma is highly likely.Strong recommendation, low quality evidence. 2: ESGE recommends performance of a colonoscopy, if that has not yet been done, in cases of duodenal adenoma.Strong recommendation, low quality evidence. 3: ESGE recommends the use of the cap-assisted method when the location of the minor and/or major papilla and their relationship to a duodenal adenoma is not clearly established during forward-viewing endoscopy.Strong recommendation, moderate quality evidence. 4: ESGE recommends the routine use of a side-viewing endoscope when a laterally spreading adenoma with extension to the minor and/or major papilla is suspected.Strong recommendation, low quality evidence. 5: ESGE suggests cold snare polypectomy for small (< 6 mm in size) nonmalignant duodenal adenomas.Weak recommendation, low quality evidence. 6: ESGE recommends endoscopic mucosal resection (EMR) as the first-line endoscopic resection technique for nonmalignant large nonampullary duodenal adenomas.Strong recommendation, moderate quality evidence. 7: ESGE recommends that endoscopic submucosal dissection (ESD) for duodenal adenomas is an effective resection technique only in expert hands.Strong recommendation, low quality evidence. 8: ESGE recommends using techniques that minimize adverse events such as immediate or delayed bleeding or perforation. These may include piecemeal resection, defect closure techniques, noncontact hemostasis, and other emerging techniques, and these should be considered on a case-by-case basis.Strong recommendation, low quality evidence. 9: ESGE recommends endoscopic surveillance 3 months after the index treatment. In cases of no recurrence, a further follow-up endoscopy should be done 1 year later. Thereafter, surveillance intervals should be adapted to the lesion site, en bloc resection status, and initial histological result. Strong recommendation, low quality evidence.

Endoscopic management of ampullary tumors: European Society of Gastrointestinal Endoscopy (ESGE) Guideline.

1: ESGE recommends against diagnostic/therapeutic papillectomy when adenoma is not proven.Strong recommendation, low quality evidence. 2: ESGE recommends endoscopic ultrasound and abdominal magnetic resonance cholangiopancreatography (MRCP) for staging of ampullary tumors.Strong recommendation, low quality evidence. 3: ESGE recommends endoscopic papillectomy in patients with ampullary adenoma without intraductal extension, because of good results regarding outcome (technical and clinical success, morbidity, and recurrence).Strong recommendation, moderate quality evidence. 4: ESGE recommends en bloc resection of ampullary adenomas up to 20-30 mm in diameter to achieve R0 resection, for optimizing the complete resection rate, providing optimal histopathology, and reduction of the recurrence rate after endoscopic papillectomy.Strong recommendation, low quality evidence. 5: ESGE suggests considering surgical treatment of ampullary adenomas when endoscopic resection is not feasible for technical reasons (e. g. diverticulum, size > 4 cm), and in the case of intraductal involvement (of > 20 mm). Surveillance thereafter is still mandatory.Weak recommendation, low quality evidence. 6: ESGE recommends direct snare resection without submucosal injection for endoscopic papillectomy.Strong recommendation, moderate quality evidence. 7: ESGE recommends prophylactic pancreatic duct stenting to reduce the risk of pancreatitis after endoscopic papillectomy.Strong recommendation, moderate quality evidence. 8: ESGE recommends long-term monitoring of patients after endoscopic papillectomy or surgical ampullectomy, based on duodenoscopy with biopsies of the scar and of any abnormal area, within the first 3 months, at 6 and 12 months, and thereafter yearly for at least 5 years.Strong recommendation, low quality evidence.

Salvage endoscopic resection after definitive chemoradiotherapy for esophageal cancer: a Western experience.

BACKGROUND AND AIMS: Definitive chemoradiotherapy (CRT) is increasingly used as a nonsurgical treatment for esophageal cancer. In Japanese studies, salvage endoscopic resection (ER) has emerged as a promising strategy for local failure after definitive CRT. We aimed to evaluate the safety and efficacy of salvage ER in a Western setting. METHODS: Gastroenterologists from Europe and the United States were invited to submit their experience with salvage endoscopic submucosal dissection (ESD) or endoscopic mucosal resection (EMR) after definitive CRT. Participating gastroenterologists completed an anonymized database, including patient demographics, clinicopathologic variables, and follow-up on survival and recurrence. RESULTS: Gastroenterologists from 10 endoscopic units in 6 European countries submitted information on 25 patients. A total of 35 salvage ER procedures were performed, of which 69% were ESD and 31% EMR. Most patients had squamous cell carcinoma (64%) of the middle or lower esophagus (68%) staged as cT2-3 (68%) and cN+ (52%) before definitive CRT. The median time from end of definitive CRT to ER was 22 months (interquartile range, 6-47). The en-bloc resection rate was 92% for ESD and 46% for EMR. During a median of 24 months (interquartile range, 12-59) of follow-up after salvage ER, 52% developed a recurrence (11 locoregional, 2 distant). The 5-year recurrence-free survival, overall survival, and disease-specific survival were 36%, 52%, and 79%, respectively. No major intra- or postprocedural adverse events, such as bleeding or perforation, were reported. CONCLUSIONS: In carefully selected esophageal cancer patients, salvage ER is technically feasible after definitive CRT. Further prospective research is recommended to validate the safety and effectivity of salvage ER for the management of local failure.

Endoscopic prediction of submucosal invasion in Barrett's cancer with the use of artificial intelligence: a pilot study.

BACKGROUND: The accurate differentiation between T1a and T1b Barrett's-related cancer has both therapeutic and prognostic implications but is challenging even for experienced physicians. We trained an artificial intelligence (AI) system on the basis of deep artificial neural networks (deep learning) to differentiate between T1a and T1b Barrett's cancer on white-light images. METHODS: Endoscopic images from three tertiary care centers in Germany were collected retrospectively. A deep learning system was trained and tested using the principles of cross validation. A total of 230 white-light endoscopic images (108 T1a and 122 T1b) were evaluated using the AI system. For comparison, the images were also classified by experts specialized in endoscopic diagnosis and treatment of Barrett's cancer. RESULTS: The sensitivity, specificity, F1 score, and accuracy of the AI system in the differentiation between T1a and T1b cancer lesions was 0.77, 0.64, 0.74, and 0.71, respectively. There was no statistically significant difference between the performance of the AI system and that of experts, who showed sensitivity, specificity, F1, and accuracy of 0.63, 0.78, 0.67, and 0.70, respectively. CONCLUSION: This pilot study demonstrates the first multicenter application of an AI-based system in the prediction of submucosal invasion in endoscopic images of Barrett's cancer. AI scored equally to international experts in the field, but more work is necessary to improve the system and apply it to video sequences and real-life settings. Nevertheless, the correct prediction of submucosal invasion in Barrett's cancer remains challenging for both experts and AI.