Esophagitis and Barrett esophagus: unifying the definitions and diagnostic approaches, with special reference to esophageal atresia

Ensembled CNN with artificial bee colony optimization method for esophageal cancer stage classification using SVM classifier

BACKGROUND

Esophageal cancer (EC) is aggressive cancer with a high fatality rate and a rapid rise of the incidence globally. However, early diagnosis of EC remains a challenging task for clinicians.

OBJECTIVE

To help address and overcome this challenge, this study aims to develop and test a new computer-aided diagnosis (CAD) network that combines several machine learning models and optimization methods to detect EC and classify cancer stages.

METHODS

The study develops a new deep learning network for the classification of the various stages of EC and the premalignant stage, Barrett's Esophagus from endoscopic images. The proposed model uses a multi-convolution neural network (CNN) model combined with Xception, Mobilenetv2, GoogLeNet, and Darknet53 for feature extraction. The extracted features are blended and are then applied on to wrapper based Artificial Bee Colony (ABC) optimization technique to grade the most accurate and relevant attributes. A multi-class support vector machine (SVM) classifies the selected feature set into the various stages. A study dataset involving 523 Barrett's Esophagus images, 217 ESCC images and 288 EAC images is used to train the proposed network and test its classification performance.

RESULTS

The proposed network combining Xception, mobilenetv2, GoogLeNet, and Darknet53 outperforms all the existing methods with an overall classification accuracy of 97.76% using a 3-fold cross-validation method.

CONCLUSION

This study demonstrates that a new deep learning network that combines a multi-CNN model with ABC and a multi-SVM is more efficient than those with individual pre-trained networks for the EC analysis and stage classification.

Recommendations for endoscopic surveillance after esophageal atresia repair in adults

BACKGROUND

Endoscopic surveillance of adults with esophageal atresia is advocated, but the optimal surveillance strategy remains uncertain. This study aimed to provide recommendations on appropriate starting age and intervals of endoscopic surveillance in adults with esophageal atresia.

METHODS

Participants underwent standardized upper endoscopies with biopsies. Surveillance intervals of 3-5 years were applied, depending on age and histopathological results. Patient's age and time to development of (pre)malignant lesions were calculated.

RESULTS

A total of 271 patients with esophageal atresia (55% male; median age at baseline endoscopy 26.7 (range 15.6-68.5) years; colon interposition n = 17) were included. Barrett's esophagus was found in 19 (7%) patients (median age 32.3 (17.8-56.0) years at diagnosis). Youngest patient with a clinically relevant Barrett's esophagus was 20.9 years. Follow-up endoscopies were performed in 108 patients (40%; median follow-up time 4.6 years). During surveillance, four patients developed Barrett's esophagus but no dysplasia or cancer was found. One 45-year-old woman with a colon interposition developed an adenoma with high-grade dysplasia which was radically removed. Two new cases of esophageal carcinoma were diagnosed in patients (55 and 66 years old) who were not under surveillance. One of them had been curatively treated for esophageal carcinoma 13 years ago.

CONCLUSIONS

This study shows that endoscopic screening of patients with esophageal atresia, including those with a colon interposition, can be started at 20 years of age. Up to the age of 40 years a surveillance interval of 10 years appeared to be safe. Endoscopic surveillance may also be warranted for patients after curative esophageal cancer treatment.

Endoscopic Surveillance After Repair of Oesophageal Atresia: Longitudinal Study in 209 Patients

AIM

After repair of oesophageal atresia (OA), the need for endoscopic follow-up (EFU) remains unclear. To end this, we assessed the trends of oesophageal mucosal changes in successive follow-up biopsies.

METHODS

EFU records of 264 patients including histological grades of oesophagitis (from 0 to III), gastric (GM) or intestinal (IM) metaplasia and dysplasia (mild to severe) at 1, 3, 5 10, 15, and >15 years after repair of OA were reviewed.

RESULTS

Included were 209 patients with 616 biopsies. A total of 60 patients had undergone antireflux surgery and 24 had long-gap OA (LG). Median follow-up was 12 (range 1-17) years with 3 (1-6) endoscopies per patient. Highest grade of oesophagitis was Gr 0 (no oesophagitis) in 47%, Gr I in 37%, and Gr II or III in 16%. Metaplasia, GM (n = 31), IM (n = 4), occurred in 17% of patients and reached 15% prevalence by 15 years. Dysplasia and cancer were not found. From 1 to 15 years after repair grade of histological oesophagitis often fluctuated between Gr 0 and Gr I, but further progression was unlikely, hazard ratio = 0.2-3.4 (95% confidence interval 0.0-29), P = 0.06-0.87. LG and antireflux surgery predicted early detection of metaplasia (P < 0.001). Only 9% of patients with metaplasia and 32% with Gr II oesophagitis were symptomatic. A total of 6 (3%) patients had a symptomatic anastomotic stenosis at 1 year.

CONCLUSIONS

EFU revealed frequent oesophagitis and metaplasia, but no dysplasia or cancer. Routine endoscopic surveillance had limited benefit and seems unnecessary during childhood after repair of OA.

Long-term maintenance treatment with omeprazole in children with healed erosive oesophagitis: a prospective study

BACKGROUND

Short-term studies show that PPIs heal erosive esophagitis in children. There are no prospective studies that examine long-term maintenance therapy of erosive esophagitis in children with and without underlying GERD-predisposing disorders.

AIM

To determine prospectively the dose of omeprazole needed to maintain remission of erosive oesophagitis and reflux symptoms in children.

METHODS

Patients aged 1-16 years with healed erosive reflux oesophagitis after omeprazole treatment (0.7-3.5 mg/kg/day) entered a 21-month maintenance phase where they initially received half the dose of omeprazole required to heal. Endoscopy was performed after 3, 12 and 21 months. The omeprazole dose was increased if erosive oesophagitis or reflux symptoms recurred.

RESULTS

A total of 46 patients entered the study and 32 completed it. Of these, 17 (53%) remained on the maintenance dose, 12 (38%) returned to their healing dose and 3 (9%) ended the study on a dose higher than their healing dose. Three-quarters of the completers (24/32) had no erosive oesophagitis relapse. Four patients (13%) had relapse of only erosive oesophagitis, 4 (13%) had relapse of erosive oesophagitis and symptoms, and 10 (31%) had only symptomatic relapse. Of the 46 patients, 48% had GERD-predisposing disorders (neurological impairment or oesophageal atresia). Overall, 62.5% (5/8) of patients who had an erosive oesophagitis relapse had a GERD-predisposing disorder versus 33.3% (8/24) of those who did not.

CONCLUSIONS

Remission of erosive oesophagitis is maintained with omeprazole treatment for at least 21 months in most children aged 1-16 years, and the drug is well tolerated. To maintain remission, some 60% of patients require more than half the dose required for healing. In children with GERD-predisposing conditions, GERD is often chronic and relapsing, and requires long-term management.