Diagnostic accuracy of a novel third generation esophageal capsule as a non-invasive detection method for Barrett's esophagus: A pilot study

Feasibility and Safety of a Novel Cable-Transmitted Magnetically Controlled Capsule Endoscopy System for Upper Gastrointestinal Examination

Background

To evaluate the feasibility and safety of a novel cable-transmitted magnetically controlled capsule endoscopy (CT-MCE) system for upper gastrointestinal examination.

Methods

Twenty-six participants (19 healthy volunteers and seven patients with gastrointestinal symptoms) willing to undergo upper gastrointestinal endoscopy were recruited. Each participant underwent CT-MCE followed by conventional gastroscopy within 24 h. Maneuverability and visibility of the CT-MCE capsule in the upper gastrointestinal tract, adverse events, and discomfort during the procedure were evaluated. The sensitivity and specificity of CT-MCE for diagnosing upper gastrointestinal lesions were evaluated using conventional gastroscopy findings as the standard.

Results

Maneuverability was graded as "good" for all segments of the esophagus. The percentage of participants in which maneuverability was good according to gastric region was as follows: cardia (100.00%), pylorus (96.15%), angulus (92.31%), antrum (88.46%), fundus (84.62%), and body (73.08%). In the duodenal bulb and descending duodenum, it was good in only 20.83% and 16.67% of participants, respectively. Visibility was graded as "excellent" or "good" in the esophagus, Z line, and duodenal bulb in all participants; excellent/good visibility was achieved in the stomach and descending duodenum in 96.15% and 79.17% of participants, respectively. Forty-one lesions were detected overall. The sensitivity and specificity of CT-MCE in diagnosing upper gastrointestinal lesions were 85.00% and 98.15%, respectively. The CT-MCE capsule was successfully removed through the mouth in all participants. No serious adverse events or capsule retention occurred.

Conclusions

CT-MCE showed good feasibility and safety for upper gastrointestinal examination. The system was effective in examining the esophagus and stomach with no risk of capsule retention.

Deep Learning and Minimally Invasive Endoscopy: Panendoscopic Detection of Pleomorphic Lesions

Introduction

Capsule endoscopy (CE) is a minimally invasive exam suitable of panendoscopic evaluation of the gastrointestinal (GI) tract. Nevertheless, CE is time-consuming with suboptimal diagnostic yield in the upper GI tract. Convolutional neural networks (CNN) are human brain architecture-based models suitable for image analysis. However, there is no study about their role in capsule panendoscopy.

Methods

Our group developed an artificial intelligence (AI) model for panendoscopic automatic detection of pleomorphic lesions (namely vascular lesions, protuberant lesions, hematic residues, ulcers, and erosions). 355,110 images (6,977 esophageal, 12,918 gastric, 258,443 small bowel, 76,772 colonic) from eight different CE and colon CE (CCE) devices were divided into a training and validation dataset in a patient split design. The model classification was compared to three CE experts' classification. The model's performance was evaluated by its sensitivity, specificity, accuracy, positive predictive value, negative predictive value, and area under the precision-recall curve.

Results

The binary esophagus CNN had a diagnostic accuracy for pleomorphic lesions of 83.6%. The binary gastric CNN identified pleomorphic lesions with a 96.6% accuracy. The undenary small bowel CNN distinguished pleomorphic lesions with different hemorrhagic potentials with 97.6% accuracy. The trinary colonic CNN (detection and differentiation of normal mucosa, pleomorphic lesions, and hematic residues) had 94.9% global accuracy.

Discussion/Conclusion

We developed the first AI model for panendoscopic automatic detection of pleomorphic lesions in both CE and CCE from multiple brands, solving a critical interoperability technological challenge. Deep learning-based tools may change the landscape of minimally invasive capsule panendoscopy.

Early diagnosis of esophageal cancer: How to put "early detection" into effect?

This editorial comments on the article by Qu et al in a recent edition of World Journal of Gastrointestinal Oncology, focusing on the importance of early diagnosis in managing esophageal cancer and strategies for achieving "early detection". The five-year age-standardized net survival for esophageal cancer patients falls short of expectations. Early detection and accurate diagnosis are critical strategies for improving the treatment outcomes of esophageal cancer. While advancements in endoscopic technology have been significant, there seems to be an excessive emphasis on the latest high-end endoscopic devices and various endoscopic resection techniques. Therefore, it is imperative to redirect focus towards proactive early detection strategies for esophageal cancer, investigate the most cost-effective screening methods suitable for different regions, and persistently explore practical solutions to improve the five-year survival rate of patients with esophageal cancer.

Detachable string magnetically controlled capsule endoscopy for the noninvasive diagnosis of esophageal diseases: A prospective, blind clinical study

BACKGROUND

Traditional esophagogastroduodenoscopy (EGD), an invasive examination method, can cause discomfort and pain in patients. In contrast, magnetically controlled capsule endoscopy (MCE), a noninvasive method, is being applied for the detection of stomach and small intestinal diseases, but its application in treating esophageal diseases is not widespread.

AIM

To evaluate the safety and efficacy of detachable string MCE (ds-MCE) for the diagnosis of esophageal diseases.

METHODS

Fifty patients who had been diagnosed with esophageal diseases were prospectively recruited for this clinical study and underwent ds-MCE and conventional EGD. The primary endpoints included the sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of ds-MCE for patients with esophageal diseases. The secondary endpoints consisted of visualizing the esophageal and dentate lines, as well as the subjects' tolerance of the procedure.

RESULTS

Using EGD as the gold standard, the sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of ds-MCE for esophageal disease detection were 85.71%, 86.21%, 81.82%, 89.29%, and 86%, respectively. ds-MCE was more comfortable and convenient than EGD was, with 80% of patients feeling that ds-MCE examination was very comfortable or comfortable and 50% of patients believing that detachable string v examination was very convenient.

CONCLUSION

This study revealed that ds-MCE has the same diagnostic effects as traditional EGD for esophageal diseases and is more comfortable and convenient than EGD, providing a novel noninvasive method for treating esophageal diseases.

In vitro and in vivo evaluation of a novel wired transmission magnetically controlled capsule endoscopy system for upper gastrointestinal examination

BACKGROUND

Magnetically controlled capsule endoscopy (MCCE) has recently increasingly been used for gastric examination. However, the image quality and esophageal observation is suboptimal. We developed a novel wired transmission magnetically controlled capsule endoscopy (WT-MCCE) system and evaluated its feasibility through in vitro and in vivo experiments.

METHODS

A plastic stomach model and a pathological upper gastrointestinal model were used to evaluate the performance of WT-MCCE in vitro experiments. Twice of examination in the two in vitro models by WT-MCCE were performed by 5 endoscopists who were experienced in performing wireless capsule endoscopy. The examination of traditional gastroscopy (Olympus, GIF-HQ290) in the pathological upper gastrointestinal model was set as the control. In vivo experiments were performed in a live canine model by 3 endoscopists, in which WT-MCCE was inserted with the assistance of gastroscopy. Measurements included maneuverability, examination time, visualization of gastric mucosa, image quality and diagnostic accuracy.

RESULTS

WT-MCCE showed good performance in both in vitro and in vivo experiments with excellent visualization of mucosa (75-100%). The mean operation time is 17.6 ± 2.7 min, 22.3 ± 1.9 min and 29.3 ± 3.4 min in three models, respectively. In pathological upper gastrointestinal model, all lesions, including esophageal varices, one polyp, one foreign body, two gastric ulcers and one duodenal ulcer, were detected by both WT-MCCE and traditional gastroscopy by all endoscopists. For the observation of esophagus and stomach in the canine model, WT-MCCE also showed excellent maneuverability and good image quality.

CONCLUSIONS

The novel WT-MCCE system performed well in evaluating upper gastrointestinal landmarks and lesions in two in vitro models, and showed good performance in a canine model. WT-MCCE may be potentially useful for diagnosis of esophageal and gastric diseases.

Expanding beyond endoscopy: A review of non-invasive modalities in Barrett's esophagus screening and surveillance

Barrett's esophagus (BE) is a condition that results from replacement of the damaged normal squamous esophageal mucosa to intestinal columnar mucosa and is the most significant predisposing factor for development of esophageal adenocarcinoma. Current guidelines recommend endoscopic evaluation for screening and surveillance based on various risk factors which has limitations such as invasiveness, availability of a trained specialist, patient logistics and cost. Trans-nasal endoscopy is a less invasive modality but still has similar limitations such as limited availability of trained specialist and costs. Non-endoscopic modalities, in comparison, require minimal intervention, can be done in an office visit and has the potential to be a more ideal choice for mass public screening and surveillance, particularly in patents at low risk for BE. These include newer generations of esophageal capsule endoscopy which provides direct visualization of BE, and tethered capsule endomicroscopy which can obtain high-resolution images of the esophagus. Various cell collection devices coupled with biomarkers have been used for BE screening. Cytosponge, in combination with TFF3, as well as EsophaCap and EsoCheck have shown promising results in various studies when used with various biomarkers. Other modalities including circulatory microRNAs and volatile organic compounds that have demonstrated favorable outcomes. Use of these cell collection methods for BE surveillance is a potential area of future research.

Examination of Entire Gastrointestinal Tract: A Perspective of Mouth to Anus (M2A) Capsule Endoscopy

Capsule endoscopy (CE) is the only non-invasive diagnostic tool that enables the direct visualization of the gastrointestinal (GI) tract. Even though CE was initially developed for small-bowel investigation, its clinical application is expanding, and technological advances continue. The final iteration of CE will be a mouth to anus (M2A) capsule that investigates the entire GI tract by the ingestion of a single capsule. This narrative review describes the current developmental status of CE and discusses the possibility of realizing an M2A capsule and what needs to be overcome in the future.