Capsule Endoscopy for Gastric Evaluation

S2P-Matching: Self-Supervised Patch-Based Matching Using Transformer for Capsule Endoscopic Images Stitching

The Magnetically Controlled Capsule Endoscopy (MCCE) has a limited shooting range, resulting in capturing numerous fragmented images and an inability to precisely locate and examine the region of interest (ROI) as traditional endoscopy can. Addressing this issue, image stitching around the ROI can be employed to aid in the diagnosis of gastrointestinal (GI) tract conditions. However, MCCE images possess unique characteristics, such as weak texture, close-up shooting, and large angle rotation, presenting challenges to current image-matching methods. In this context, a method named S2P-Matching is proposed for self-supervised patch-based matching in MCCE image stitching. The method involves augmenting the raw data by simulating the capsule endoscopic camera's behavior around the GI tract's ROI. Subsequently, an improved contrast learning encoder is utilized to extract local features, represented as deep feature descriptors. This encoder comprises two branches that extract distinct scale features, which are combined over the channel without manual labeling. The data-driven descriptors are then input into a Transformer model to obtain patch-level matches by learning the globally consented matching priors in the pseudo-ground-truth match pairs. Finally, the patch-level matching is refined and filtered to the pixel-level. The experimental results on real-world MCCE images demonstrate that S2P-Matching provides enhanced accuracy in addressing challenging issues in the GI tract environment with image parallax. The performance improvement can reach up to 203 and 55.8% in terms of NCM (Number of Correct Matches) and SR (Success Rate), respectively. This approach is expected to facilitate the wide adoption of MCCE-based gastrointestinal screening.

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.

A novel method of cardia visualization and comfort level enhancement during magnetic capsule gastroscopy via sugar-glued tether-assisted technique: a randomized pilot study inspired by a Chinese snack-making process (with video)

BACKGROUND

Magnetic capsule gastroscopy (MCG) is a non-invasive diagnostic method for the digestive tract. However, its efficiency in visualizing the gastric cardia is often compromised due to the capsule's rapid passage. This study introduces a novel sugar-glued tether-assisted technique inspired by a traditional Chinese snack-making process to enhance cardia visualization and patient comfort during MCG.

METHODS

This pilot, open-label, single-center, randomized controlled, non-inferiority study was conducted at Binzhou Medical University Hospital. Seventy-eight patients were enrolled and divided into three groups: conventional MCG, suction cup tether-assisted MCG, and sugar-glued tether-assisted MCG. The primary outcomes included safety, comfort level, and gastric cardia visualization quality. Secondary outcomes assessed technique-associated performance and clinical factors.

RESULTS

The sugar-glued tether-assisted MCG demonstrated comparable cardia visualization quality to the suction cup method, with significantly better results than conventional MCG. Comfort levels were significantly higher in the sugar-glued group compared to the suction cup group. The number of swallow attempts was significantly lower in the sugar-glued group, with no adverse events reported. Secondary outcomes showed no significant differences in MCG assembly time and ingestion-to-detachment period between the suction cup and sugar-glued groups.

CONCLUSION

The sugar-glued tether-assisted MCG is a feasible and safe modification that enhances gastric cardia visualization while improving patient comfort. This technique provides a cost-effective alternative to the suction cup method, warranting further investigation in larger, multi-center studies.

The Future of Minimally Invasive Capsule Panendoscopy: Robotic Precision, Wireless Imaging and AI-Driven Insights

In the early 2000s, the introduction of single-camera wireless capsule endoscopy (CE) redefined small bowel study. Progress continued with the development of double-camera devices, first for the colon and rectum, and then, for panenteric assessment. Advancements continued with magnetic capsule endoscopy (MCE), particularly when assisted by a robotic arm, designed to enhance gastric evaluation. Indeed, as CE provides full visualization of the entire gastrointestinal (GI) tract, a minimally invasive capsule panendoscopy (CPE) could be a feasible alternative, despite its time-consuming nature and learning curve, assuming appropriate bowel cleansing has been carried out. Recent progress in artificial intelligence (AI), particularly in the development of convolutional neural networks (CNN) for CE auxiliary reading (detecting and diagnosing), may provide the missing link in fulfilling the goal of establishing the use of panendoscopy, although prospective studies are still needed to validate these models in actual clinical scenarios. Recent CE advancements will be discussed, focusing on the current evidence on CNN developments, and their real-life implementation potential and associated ethical challenges.

Deep Learning and Minimally Invasive Endoscopy: Automatic Classification of Pleomorphic Gastric Lesions in Capsule Endoscopy

INTRODUCTION

Capsule endoscopy (CE) is a minimally invasive examination for evaluating the gastrointestinal tract. However, its diagnostic yield for detecting gastric lesions is suboptimal. Convolutional neural networks (CNNs) are artificial intelligence models with great performance for image analysis. Nonetheless, their role in gastric evaluation by wireless CE (WCE) has not been explored.

METHODS

Our group developed a CNN-based algorithm for the automatic classification of pleomorphic gastric lesions, including vascular lesions (angiectasia, varices, and red spots), protruding lesions, ulcers, and erosions. A total of 12,918 gastric images from 3 different CE devices (PillCam Crohn's; PillCam SB3; OMOM HD CE system) were used from the construction of the CNN: 1,407 from protruding lesions; 994 from ulcers and erosions; 822 from vascular lesions; and 2,851 from hematic residues and the remaining images from normal mucosa. The images were divided into a training (split for three-fold cross-validation) and validation data set. The model's output was compared with a consensus classification by 2 WCE-experienced gastroenterologists. The network's performance was evaluated by its sensitivity, specificity, accuracy, positive predictive value and negative predictive value, and area under the precision-recall curve.

RESULTS

The trained CNN had a 97.4% sensitivity; 95.9% specificity; and positive predictive value and negative predictive value of 95.0% and 97.8%, respectively, for gastric lesions, with 96.6% overall accuracy. The CNN had an image processing time of 115 images per second.

DISCUSSION

Our group developed, for the first time, a CNN capable of automatically detecting pleomorphic gastric lesions in both small bowel and colon CE devices.

A Magnetic Bio-Inspired Soft Carrier as a Temperature-Controlled Gastrointestinal Drug Delivery System

Currently, gastrointestinal bleeding in the colon wall and the small bowel is diagnosed and treated with endoscopes. However, the locations of this condition are often problematic to treat using traditional flexible and tethered tools. New studies commonly consider untethered devices for solving this problem. However, there still exists a gap in the extant literature, and more research is needed to diagnose and deliver drugs in the lower gastrointestinal tract using soft robotic carriers. This paper discusses the development of an untethered, magnetically-responsive bio-inspired soft carrier. A molding process is utilized to produce prototypes from Diisopropylidene-1,6-diphenyl-1,6-hexanediol-based Polymer with Ethylene Glycol Dimethacrylate (DiAPLEX) MP-3510 - a shape memory polymer with a low transition temperature to enable the fabrication of these carriers. The soft carrier design is validated through simulation results of deformation caused by magnetic elements embedded in the carrier in response to an external field. The thermal responsiveness of the fabricated prototype carriers is assessed ex vivo and in a phantom. The results indicate a feasible design capable of administering drugs to a target inside a phantom of a large intestine. The soft carrier introduces a method for the controlled release of drugs by utilizing the rubbery modulus of the polymer and increasing the recovery force through magnetic actuation.

Tracking and Dynamic Tuning of a Wireless Powered Endoscopic Capsule

This work presents an inductive wireless power transfer system for powering an endoscopy capsule supplying energy to power electronic devices allocated inside a capsule of ≈26.1 mm × 9 mm. A receiver with three coils in quadrature with dimensions of ≈9 mm × 9 mm × 10 mm is located inside the capsule, moving freely inside a transmitter coil with 380 mm diameter through translations and revolutions. The proposed system tracks the variations of the equivalent magnetic coupling coefficient compensating misalignments between the transmitter and receiver coils. The power on the load is estimated and optimized from the transmitter, and the tracking control is performed by actuating on a capacitance in the matching network and on the voltage source frequency. The proposed system can prevent load overheating by limiting the power via adjusting of the magnitude of voltage source VS. Experimental results with uncertainties analysis reveal that, even at low magnetic coupling coefficients k ranging from (1.7 × 10-3, 3.5 × 10-3), the power on the load can be held within the range of 100-130 mW. These results are achieved with any position of the capsule in the space, limited by the diameter of the transmitter coil and height of 200 mm when adjusting the series capacitance of the transmitter in the range (17.4, 19.4) pF and the frequency of the power source in the range (802.1, 809.5) kHz.

Endoscopic capsule robot-based diagnosis, navigation and localization in the gastrointestinal tract

The proliferation of video capsule endoscopy (VCE) would not have been possible without continued technological improvements in imaging and locomotion. Advancements in imaging include both software and hardware improvements but perhaps the greatest software advancement in imaging comes in the form of artificial intelligence (AI). Current research into AI in VCE includes the diagnosis of tumors, gastrointestinal bleeding, Crohn’s disease, and celiac disease. Other advancements have focused on the improvement of both camera technologies and alternative forms of imaging. Comparatively, advancements in locomotion have just started to approach clinical use and include onboard controlled locomotion, which involves miniaturizing a motor to incorporate into the video capsule, and externally controlled locomotion, which involves using an outside power source to maneuver the capsule itself. Advancements in locomotion hold promise to remove one of the major disadvantages of VCE, namely, its inability to obtain targeted diagnoses. Active capsule control could in turn unlock additional diagnostic and therapeutic potential, such as the ability to obtain targeted tissue biopsies or drug delivery. With both advancements in imaging and locomotion has come a corresponding need to be better able to process generated images and localize the capsule’s position within the gastrointestinal tract. Technological advancements in computation performance have led to improvements in image compression and transfer, as well as advancements in sensor detection and alternative methods of capsule localization. Together, these advancements have led to the expansion of VCE across a number of indications, including the evaluation of esophageal and colon pathologies including esophagitis, esophageal varices, Crohn’s disease, and polyps after incomplete colonoscopy. Current research has also suggested a role for VCE in acute gastrointestinal bleeding throughout the gastrointestinal tract, as well as in urgent settings such as the emergency department, and in resource-constrained settings, such as during the COVID-19 pandemic. VCE has solidified its role in the evaluation of small bowel bleeding and earned an important place in the practicing gastroenterologist’s armamentarium. In the next few decades, further improvements in imaging and locomotion promise to open up even more clinical roles for the video capsule as a tool for non-invasive diagnosis of lumenal gastrointestinal pathologies.