Artificial Intelligence and Device-Assisted Enteroscopy: Automatic Detection of Enteric Protruding Lesions Using a Convolutional Neural Network

INTRODUCTION

Device-assisted enteroscopy (DAE) plays a major role in the investigation and endoscopic treatment of small bowel diseases. Recently, the implementation of artificial intelligence (AI) algorithms to gastroenterology has been the focus of great interest. Our aim was to develop an AI model for the automatic detection of protruding lesions in DAE images.

METHODS

A deep learning algorithm based on a convolutional neural network was designed. Each frame was evaluated for the presence of enteric protruding lesions. The area under the curve, sensitivity, specificity, and positive and negative predictive values were used to assess the performance of the convolutional neural network.

RESULTS

A total of 7,925 images from 72 patients were included. Our model had a sensitivity and specificity of 97.0% and 97.4%, respectively. The area under the curve was 1.00.

DISCUSSION

Our model was able to efficiently detect enteric protruding lesions. The development of AI tools may enhance the diagnostic capacity of deep enteroscopy techniques.

Exosomal glypican-1 discriminates pancreatic ductal adenocarcinoma from chronic pancreatitis

BACKGROUND AND AIMS

Pancreatic ductal adenocarcinoma (PDAC) diagnosis can be difficult in a chronic pancreatitis (CP) background, especially in its mass forming presentation. We aimed to assess the accuracy of glypican-1-positive circulating exosomes (GPC1+crExos) to distinguish PDAC from CP versus the state-of-the-art CA 19-9 biomarker.

METHODS

This was a unicentric prospective cohort. Endoscopic ultrasound with fine-needle aspiration or biopsy and blood tests (GPC1+crExos and serum CA 19-9) were performed.

RESULTS

The cohort comprised 60 PDAC and 29 CP (7 of which mass forming - MF) patients. Median levels of GPC1+crExos were significantly higher in PDAC (99.7%) versus CP (28.4%; p<0.0001) with an AUROC of 0.96 with 98.3% sensitivity and 86.2% specificity for a cut-off of 45.0% (p<0.0001); this outperforms CA 19-9 AUROC of 0.82 with 78.3% sensitivity and 65.5% specificity at a cut-off of 37 U/mL (p<0.0001). The superiority of% GPC1+crExos over CA 19-99 in differentiating PDAC from CP was observed in both early (stage I) and advanced tumors (stages II-IV).

CONCLUSION

Levels of GPC1+crExos coupled to beads enable differential diagnosis between PDAC and CP including its mass-forming presentation.

Real-world effectiveness of sofosbuvir/velpatasvir for the treatment of hepatitis C virus in prison settings

Background: People in prison are at high risk of hepatitis C virus (HCV) infection and often have a history of injection drug use and mental health disorders. Simple test-and-treat regimens which require minimal monitoring are critical. Methods: This integrated real-world analysis evaluated the effectiveness of once daily sofosbuvir/velpatasvir (SOF/VEL) in 20 prison cohorts across Europe and Canada. The primary outcome was sustained virological response (SVR) in the effectiveness population (EP), defined as patients with a valid SVR status. Secondary outcomes were reasons for not achieving SVR, adherence and time between HCV RNA diagnosis and SOF/VEL treatment. Results: Overall, 526 people in prison were included with 98.9% SVR achieved in the EP (n = 442). Cure rates were not compromised by drug use or existence of mental health disorders. Conclusion: SOF/VEL for 12 weeks is highly successful in prison settings and enables the implementation of a simple treatment algorithm in line with guideline recommendations and test-and-treat strategies.

Solid Pseudopapillary Neoplasm of the Pancreas: Unfolding an Intriguing Condition

Pancreatic cancer is one of the most lethal malignant neoplasms, with a 1-year survival rate after diagnosis of 24%, and a 5-year survival rate of only 9%. While this illustrates the behavior of its main histologic type - ductal adenocarcinoma, there are other histologic subtypes of pancreatic cancer that can harbor excellent prognosis. Solid pseudopapillary neoplasm, described as a rare low-grade malignant neoplasm by the World Health Organization, is the best example of that, having an overall 5-year survival rate of about 97%. Not only the prognosis, but everything about this entity is unique: its histogenesis, epidemiology, presentation, imaging characteristics, cytology features, immunohistochemical profile, and treatment. This explains the urge to improve our understanding about this entity and thus our ability to accurately recognize and manage it. Having this in mind, this article aims to summarize the most relevant topics regarding this entity.

Not all liver tumors are alike — an accidentally discovered primary hepatic leiomyosarcoma: A case report

BACKGROUND

Primary hepatic leiomyosarcoma is a very rare entity that originates from smooth muscle. Preoperative diagnosis requires a high degree of suspicion due to atypical clinical presentation and non-specific imaging features.

CASE SUMMARY

We report the case of a 42-year-old man, with no relevant past medical history, accidentally diagnosed with a nodular liver lesion on a routine abdominal ultrasound. Liver function tests and hematology parameters as well as tumor markers were normal. A contrast-enhanced abdominal computed tomography scan revealed a heterogenous hepatic lesion measuring 40 mm 30 mm, adjacent to the left branch of the portal vein and the round ligament. Due to the unclear diagnosis, the patient underwent surgical resection. Histopathological and immunohistochemical examinations confirmed complete (R0) resection of a hepatic leiomyosarcoma. The patient remains without any signs of tumor recurrence for more than 2 years.

CONCLUSION

We report a rare case of accidentally diagnosed primary hepatic leiomyosarcoma originating from the portal vein or the round ligament. Although this tumor has aggressive metastatic potential, a tumor-free resection margin is essential to improve survival.

Deep Learning for Automatic Identification and Characterization of the Bleeding Potential of Enteric Protruding Lesions in Capsule Endoscopy

Background and Aims

Capsule endoscopy (CE) revolutionized the study of the small intestine, overcoming the limitations of conventional endoscopy. Nevertheless, reviewing CE images is time-consuming. Convolutional Neural Networks (CNNs) are an artificial intelligence architecture with high performance levels for image analysis. Protruding lesions of the small intestine exhibit enormous morphologic diversity in CE images. We aimed to develop a CNN-based algorithm for automatic detection of varied small-bowel protruding lesions.

Methods

A CNN was developed using a pool of CE images containing protruding lesions or normal mucosa/other findings. A total of 2565 patients were included. These images were inserted into a CNN model with transfer learning. We evaluated the performance of the network by calculating its sensitivity, specificity, accuracy, positive predictive value, and negative predictive value.

Results

A CNN was developed based on a total of 21,320 CE images. Training and validation data sets comprising 80% and 20% of the total pool of images, respectively, were constructed for development and testing of the network. The algorithm automatically detected small-bowel protruding lesions with an accuracy of 97.1%. Our CNN had a sensitivity, specificity, positive, and negative predictive values of 95.9%, 97.1%, 83.0%, and 95.7%, respectively. The CNN operated at a rate of approximately 355 frames per second.

Conclusion

We developed an accurate CNN for automatic detection of enteric protruding lesions with a wide range of morphologies. The development of these tools may enhance the diagnostic efficiency of CE.

Small Bowel Adenocarcinoma in a Patient with Crohn’s Disease: The Role of Balloon-Assisted Enteroscopy

<b><i>Introduction:</i></b> Small bowel adenocarcinoma is a rare but well-known complication of Crohn’s disease. Diagnosis can be challenging, as clinical presentation may mimic an exacerbation of Crohn’s disease and imaging findings may be indistinguishable from benign strictures. The result is that the majority of cases are diagnosed at the time of operation or postoperatively at an advanced stage. <b><i>Case Presentation:</i></b> A 48-year-old male with a previous 20-year history of ileal stenosing Crohn’s disease presented with iron deficiency anemia. The patient reported melena approximately 1 month earlier but was currently asymptomatic. There were no other laboratory abnormalities. Anemia was refractory to intravenous iron replacement. The patient underwent computerized tomography enterography, which revealed multiple ileal strictures with features suggesting underlying inflammation and an area of sacculation with circumferential thickening of adjacent bowel loops. Therefore, the patient underwent retrograde balloon-assisted small bowel enteroscopy, where an area of irregular mucosa and ulceration was found at the region of ileo-ileal anastomosis. Biopsies were performed and histopathological examination revealed tubular adenocarcinoma infiltrating the muscularis mucosae. The patient underwent right hemicolectomy plus segmental enterectomy of the anastomotic region where the neoplasia was located. After 2 months, he is asymptomatic and there is no evidence of recurrence. <b><i>Discussion:</i></b> This case demonstrates that small bowel adenocarcinoma may have a subtle clinical presentation and that computed tomography enterography may not be accurate enough to distinguish benign from malignant strictures. Clinicians must, therefore, maintain a high index of suspicion for this complication in patients with long-standing small bowel Crohn’s disease. In this setting, balloon-assisted enteroscopy may be a useful tool when there is raised concern for malignancy, and it is expected that its more widespread use could contribute to an earlier diagnosis of this severe complication.

Automatic detection of tumor vessels in indeterminate biliary strictures in digital single-operator cholangioscopy

Background and study aims  Indeterminate biliary strictures pose a significative clinical challenge. Dilated, irregular, and tortuous vessels, often described as tumor vessels, are frequently reported in biliary strictures with high malignancy potential during digital single-operator cholangioscopy (D-SOC). In recent years, the development of artificial intelligence (AI) algorithms for application to endoscopic practice has been intensely studied. We aimed to develop an AI algorithm for automatic detection of tumor vessels (TVs) in D-SOC images. Patients and methods  A convolutional neural network (CNN) was developed. A total of 6475 images from 85 patients who underwent D-SOC (Spyglass, Boston Scientific, Marlborough, Massachusetts, United States) were included. Each frame was evaluated for the presence of TVs. The performance of the CNN was measured by calculating the area under the curve (AUC), sensitivity, specificity, positive and negative predictive values. Results  The sensitivity, specificity, positive predictive value, and negative predictive value were 99.3 %, 99.4 %, 99.6% and 98.7 %, respectively. The AUC was 1.00. Conclusions  Our CNN was able to detect TVs with high accuracy. Development of AI algorithms may enhance the detection of macroscopic characteristics associated with high probability of biliary malignancy, thus optimizing the diagnostic workup of patients with indeterminate biliary strictures.

Primary Myelofibrosis in the Prefibrotic Stage Presenting as Portal, Splenic, and Superior Mesenteric Vein Thrombosis: A Case Report and Review of the Literature

INTRODUCTION

Myeloproliferative neoplasms are the most common cause of splanchnic vein thrombosis in the absence of cirrhosis or nearby malignancy.

CASE PRESENTATION

A 31-year-old male presented to the emergency department with epigastric pain associated with mild thrombocytosis and elevated levels of aminotransferases, lactate dehydrogenase, and C-reactive protein. Contrast-enhanced abdominal computed tomography revealed splanchnic venous thrombosis that involved the portal, splenic, and superior mesenteric veins, without signs of chronic liver disease. Anticoagulation with warfarin was immediately started. Diagnostic work-up was remarkable for the presence of the JAK2 V617T mutation and hypercellular bone marrow, with increased myeloid cells and atypical megakaryocytes, consistent with primary myelofibrosis in a prefibrotic stage. No other hypercoagulable conditions were identified.

DISCUSSION

We present a rare case of primary myelofibrosis in the prefibrotic stage presenting as portal-splenic-superior mesenteric vein thrombosis. This demonstrates that extensive splanchnic vein thrombosis may be the onset manifestation of myeloproliferative neoplasms, even in early stages and in the absence of concomitant hypercoagulable conditions. The presence of the JAK2 mutation is an important prothrombotic risk factor that can, per se, contribute to large venous thrombosis.

Wilson disease in Northern Portugal: a long-term follow-up study

Introduction

Wilson disease is an autosomal recessive disease of liver copper metabolism with predominant hepatic and neurological manifestations. Long-term data on the clinical follow-up and treatment efficacy are limited due to the low frequency of the disease. We evaluated a large cohort of Wilson disease patients from Northern Portugal during a 20-year follow-up period.

Methods

Twenty-four patients, diagnosed from 1975 to 2020 in a tertiary care center in Portugal, were retrospectively evaluated according to their clinical presentation, therapies and outcomes.

Results

Most of the patients were males (54%), with a median age at diagnosis of 19 years old (interquartile range 15–25). The main manifestations of Wilson disease were hepatic (71%) and neurological (25%). Family history was positive in 5 (21%) patients. Four patients (17%) presented with acute liver failure and fifteen (63%) individuals had cirrhosis at diagnosis. Penicillamine therapy was used by 11 (46%) patients, while trientine and zinc were given to 8 (33%) and 1 (4%) patient, respectively. Ten (42%) individuals underwent liver transplantation. The majority of patients (83%) had stable disease or improved outcomes during follow-up.

Conclusion

This is the largest cohort of adult patients with Wilson disease reported in Northern Portugal. We show that Wilson disease has favorable outcomes with long overall survival, assuming adherence to therapy and lack of other insults to their liver.

Deep learning and colon capsule endoscopy: automatic detection of blood and colonic mucosal lesions using a convolutional neural network

Background and study aims  Colon capsule endoscopy (CCE) is a minimally invasive alternative to conventional colonoscopy. However, CCE produces long videos, making its analysis time-consuming and prone to errors. Convolutional neural networks (CNN) are artificial intelligence (AI) algorithms with high performance levels in image analysis. We aimed to develop a deep learning model for automatic identification and differentiation of significant colonic mucosal lesions and blood in CCE images. Patients and methods  A retrospective multicenter study including 124 CCE examinations was conducted for development of a CNN model, using a database of CCE images including anonymized images of patients with normal colon mucosa, several mucosal lesions (erosions, ulcers, vascular lesions and protruding lesions) and luminal blood. For CNN development, 9005 images (3,075 normal mucosa, 3,115 blood and 2,815 mucosal lesions) were ultimately extracted. Two image datasets were created and used for CNN training and validation. Results  The mean (standard deviation) sensitivity and specificity of the CNN were 96.3 % (3.9 %) and 98.2 % (1.8 %) Mucosal lesions were detected with a sensitivity of 92.0 % and a specificity of 98.5 %. Blood was detected with a sensitivity and specificity of 97.2 % and 99.9 %, respectively. The algorithm was 99.2 % sensitive and 99.6 % specific in distinguishing blood from mucosal lesions. The CNN processed 65 frames per second. Conclusions  This is the first CNN-based algorithm to accurately detect and distinguish colonic mucosal lesions and luminal blood in CCE images. AI may improve diagnostic and time efficiency of CCE exams, thus facilitating CCE adoption to routine clinical practice.

Clinical and endoscopic findings in gastrointestinal amyloidosis: a single-center experience

Gastrointestinal involvement occurs in approximately 4% of cases of systemic amyloidosis. The most common site of amyloid deposition is small bowel, followed by stomach, colorectum and esophagus. Although rare, gastrointestinal amyloidosis may be associated with severe complications including gastrointestinal bleeding or perforation and may be mistaken for malignancy.

Hepatobiliary phenotypes of adults with alpha-1 antitrypsin deficiency

OBJECTIVE

Alpha-1 antitrypsin deficiency (AATD) is a common, potentially lethal inborn disorder caused by mutations in alpha-1 antitrypsin (AAT). Homozygosity for the 'Pi*Z' variant of AAT (Pi*ZZ genotype) causes lung and liver disease, whereas heterozygous 'Pi*Z' carriage (Pi*MZ genotype) predisposes to gallstones and liver fibrosis. The clinical significance of the more common 'Pi*S' variant remains largely undefined and no robust data exist on the prevalence of liver tumours in AATD.

DESIGN

Baseline phenotypes of AATD individuals and non-carriers were analysed in 482 380 participants in the UK Biobank. 1104 participants of a multinational cohort (586 Pi*ZZ, 239 Pi*SZ, 279 non-carriers) underwent a comprehensive clinical assessment. Associations were adjusted for age, sex, body mass index, diabetes and alcohol consumption.

RESULTS

Among UK Biobank participants, Pi*ZZ individuals displayed the highest liver enzyme values, the highest occurrence of liver fibrosis/cirrhosis (adjusted OR (aOR)=21.7 (8.8-53.7)) and primary liver cancer (aOR=44.5 (10.8-183.6)). Subjects with Pi*MZ genotype had slightly elevated liver enzymes and moderately increased odds for liver fibrosis/cirrhosis (aOR=1.7 (1.2-2.2)) and cholelithiasis (aOR=1.3 (1.2-1.4)). Individuals with homozygous Pi*S mutation (Pi*SS genotype) harboured minimally elevated alanine aminotransferase values, but no other hepatobiliary abnormalities. Pi*SZ participants displayed higher liver enzymes, more frequent liver fibrosis/cirrhosis (aOR=3.1 (1.1-8.2)) and primary liver cancer (aOR=6.6 (1.6-26.9)). The higher fibrosis burden was confirmed in a multinational cohort. Male sex, age ≥50 years, obesity and the presence of diabetes were associated with significant liver fibrosis.

CONCLUSION

Our study defines the hepatobiliary phenotype of individuals with the most relevant AATD genotypes including their predisposition to liver tumours, thereby allowing evidence-based advice and individualised hepatological surveillance.

Artificial intelligence for automatic diagnosis of biliary stricture malignancy status in single-operator cholangioscopy: a pilot study

BACKGROUND AND AIMS

The diagnosis and characterization of biliary strictures (BSs) is challenging. The introduction of digital single-operator cholangioscopy (DSOC) that allows direct visual inspection of the lesion and targeted biopsy sampling significantly improved the diagnostic yield in patients with indeterminate BSs. However, the diagnostic efficiency of DSOC remains suboptimal. Convolutional neural networks (CNNs) have shown great potential for the interpretation of medical images. We aimed to develop a CNN-based system for automatic detection of malignant BSs in DSOC images.

METHODS

We developed, trained, and validated a CNN-based on DSOC images. Each frame was labeled as a normal/benign finding or as a malignant lesion if histopathologic evidence of biliary malignancy was available. The entire dataset was split for 5-fold cross-validation. In addition, the image dataset was split for constitution of training and validation datasets. The performance of the CNN was measured by calculating the area under the receiving operating characteristic curve (AUC), sensitivity, specificity, and positive and negative predictive values.

RESULTS

A total of 11,855 images from 85 patients were included (9695 malignant strictures and 2160 benign findings). The model had an overall accuracy of 94.9%, sensitivity of 94.7%, specificity of 92.1%, and AUC of .988 in cross-validation analysis. The image processing speed of the CNN was 7 ms per frame.

CONCLUSIONS

The developed deep learning algorithm accurately detected and differentiated malignant strictures from benign biliary conditions. The introduction of artificial intelligence algorithms to DSOC systems may significantly increase its diagnostic yield for malignant strictures.

New Endoscopic Solutions in Managing Phlegmonous Esophagitis

A 48-year-old woman was admitted in the emergency department due to epigastric pain, nausea, vomiting, and cough. She presented with fever and increased inflammatory parameters. A thoracoabdominal computed tomography (CT) was performed and revealed thickening of the gastric fundus and esophagus, with an apparent laceration in esophageal mucosa and associated dissection of esophageal wall. In upper endoscopy (UE), a bulging of esophageal and gastric walls was observed, with an ulceration in proximal esophagus, suggestive of a perforation. After multidisciplinary discussion, a minimally invasive endoscopic approach was decided. Internal esophageal drainage (IED) was assured with performance of some incisions with Dual-knife® (Olympus, Tokyo) along the mucosal and submucosal layers in the esophagus. During the incision, extravasation of pus was evident. One week later, due to clinical worsening and evidence of esophageal perforation in CT scan, UE was repeated. We confirmed esophageal perforation with visualization of two millimetric defects in the proximal esophagus. Significant bulging of the gastric fundus and body was also observed. IED was repeated with mucosal incision of the gastric bulging using Needle-Cut 3V® (Olympus, Tokyo), with extravasation of a significant quantity of pus. We decided to proceed to endoscopic vacuum therapy that was performed with sponge placement in the esophageal lumen (Endosponge®, B. Braun, Melsungen, Germany). UE was repeated 1 week later with sponge removal and confirmation of resolution of esophageal perforation. An improvement of the thickening of gastric fundus and body was also seen. One month later after admission, the patient was discharged home, eating normally, and remains well in the follow-up.

Trastuzumab Emtansine-Induced Nodular Regenerative Hyperplasia: Is Dose Reduction Enough as a Preventable Measure?

INTRODUCTION

Trastuzumab emtansine (T-DM1) is a novel antibody-drug conjugate targeting the human epidermal growth factor receptor 2, used in some recurrent metastatic cancers. It was linked to modest increases in serum aminotransferase elevations and bilirubin. More recently, some cases of noncirrhotic portal hypertension have been described in patients on long-term T-DM1. The underlying liver condition is usually nodular regenerative hyperplasia (NRH) with elements of sinusoidal obstruction.

CASE REPORT

We report the case of a 52-year-old woman who started T-DM1 therapy for recurrent metastatic lung adenocarcinoma. Although a progressive reduction in lung nodules was noticed, there was a new-onset cytocholestasis and elevation in bilirubin. A reduction in platelet count was also apparent over several months during the T-DM1 therapy. Liver biopsy revealed NRH and so the dose of T-DM1 was reduced. Thereafter, the patient had normalization of liver tests and platelet count. T-DM1 was continued for more than 9 months with no signs of portal hypertension or cancer progression.

CONCLUSIONS

We presented a rare case of NRH induced by T-DM1 in a patient with lung adenocarcinoma. A high index of suspicion for liver injury and NRH must be maintained for patients who develop liver test abnormalities and/or signs of portal hypertension during treatment with T-DM1. This is the first report of a successful dose reduction in a patient with NRH induced by T-DM1, suggesting that it is possible to maintain the drug while it is being effective for lung cancer treatment.

Gastric ulcer with liver penetration

A 54-year-old male with previous history of chronic hepatitis C complained of postprandial epigastric discomfort and weight loss. Esophagogastroduodenoscopy revealed a large gastric ulcer on the lesser antral curvature, with biopsies showing granulation tissue and inflammatory activity without other significant changes. Despite therapy with double-dose proton pump inhibitor, the ulcer had not healed or diminished in size at reevaluation endoscopy eight weeks later. Biopsies were repeated and again only revealed granulation tissue and inflammation. The patient undergone partial gastrectomy where fibrotic adhesions to liver and peritoneum were noted. Remarkably, macroscopical analysis of the surgical specimen revealed an hepatic fragment adherent to the ulcer and histopathological examination was consistent with liver penetration. Liver penetration is a rare but important complication that must be considered in the differential diagnosis of medically refractory gastric ulcers, even in the absence of hepatic tissue in endoscopic biopsies.

Extracellular Vesicles from Pancreatic Cancer Stem Cells Lead an Intratumor Communication Network (EVNet) to fuel tumour progression

OBJECTIVE

Intratumor heterogeneity drives cancer progression and therapy resistance. However, it has yet to be determined whether and how subpopulations of cancer cells interact and how this interaction affects the tumour.

DESIGN

We have studied the spontaneous flow of extracellular vesicles (EVs) between subpopulations of cancer cells: cancer stem cells (CSC) and non-stem cancer cells (NSCC). To determine the biological significance of the most frequent communication route, we used pancreatic ductal adenocarcinoma (PDAC) orthotopic models, patient-derived xenografts (PDXs) and genetically engineered mouse models (GEMMs).

RESULTS

We demonstrate that PDAC tumours establish an organised communication network between subpopulations of cancer cells using EVs called the EVNet). The EVNet is plastic and reshapes in response to its environment. Communication within the EVNet occurs preferentially from CSC to NSCC. Inhibition of this communication route by impairing Rab27a function in orthotopic xenographs, GEMMs and PDXs is sufficient to hamper tumour growth and phenocopies the inhibition of communication in the whole tumour. Mechanistically, we provide evidence that CSC EVs use agrin protein to promote Yes1 associated transcriptional regulator (YAP) activation via LDL receptor related protein 4 (LRP-4). Ex vivo treatment of PDXs with antiagrin significantly impairs proliferation and decreases the levels of activated YAP.Patients with high levels of agrin and low inactive YAP show worse disease-free survival. In addition, patients with a higher number of circulating agrin+ EVs show a significant increased risk of disease progression.

CONCLUSION

PDAC tumours establish a cooperation network mediated by EVs that is led by CSC and agrin, which allows tumours to adapt and thrive. Targeting agrin could make targeted therapy possible for patients with PDAC and has a significant impact on CSC that feeds the tumour and is at the centre of therapy resistance.

Endoscopic management of esophageal and gastric lesions with underlying varices

Recent developments in endoscopic techniques have contributed to establishing endoscopy as an essential tool in the management of different types of esophageal and gastric lesions. However, management of these lesions with underlying varices is challenging, considering the technical difficulties and increased risk of bleeding it entails with current endoscopic techniques. Consequently, most endoscopists are hesitant to use this technically challenging procedure. Nevertheless, rare cases of successful endoscopic resection of superficial lesions on or adjacent to varices have been reported. Several endoscopic techniques, including endoscopic mucosal resection, endoscopic submucosal dissection or radiofrequency ablation, have demonstrated safety and feasibility in this setting, sometimes with technical modifications, or in combination with previous variceal eradication procedures that aim to decrease the risk of bleeding. In this review, we summarize the current evidence regarding endoscopic management of gastroesophageal lesions in patients with portal hypertension and underlying varices. It appears that liver cirrhosis, portal hypertension and gastroesophageal varices are not absolute contraindications in selected patients at specialized referral centers. Nevertheless, specific recommendations are lacking and further studies are needed to define the most appropriate endoscopic techniques and to determine which patients may be the best candidates.