Colon capsule for panendoscopy: a narrow window of opportunity

Pan-Enteric Capsule Endoscopy: Current Applications and Future Perspectives

Background

The role of capsule endoscopy in the evaluation of the small bowel is well established, and current guidelines position it as a first-line test in a variety of clinical scenarios. The advent of double-headed capsules further enabled the endoscopic assessment of colonic mucosa and the opportunity for a one-step noninvasive examination of the entire bowel (pan-enteric capsule endoscopy [PCE]).

Summary

We reviewed the technical procedure and preparation of patients for PCE, as well as its current clinical applications and future perspectives. In non-stricturing and non-penetrating Crohn's disease affecting the small bowel and colon, PCE monitors disease activity by assessing mucosal healing, a major treatment outcome, with a higher diagnostic yield than cross-sectional imaging or conventional colonoscopy. Also in ulcerative colitis, double-headed capsules have been used to monitor disease activity noninvasively. Currently, validated scoring systems have been specifically devised for these double-headed capsules and permit a standardized assessment of the inflammatory burden. In suspected mid-lower digestive bleeding, some exploratory studies have demonstrated the feasibility and high diagnostic yield of PCE, which may work as a filter indicating which patients may benefit of further invasive procedures, namely, for planned hemostatic procedures. The possibility of using PCE is also discussed in the context of polyposis syndromes with simultaneous involvement of the small intestine and colon.

Key Messages

PCE is a feasible, effective, and safe diagnostic procedure to evaluate the small bowel and colon. It has been increasingly explored in the setting of inflammatory bowel diseases and, more recently, in suspected mid-lower digestive bleeding. PCE is expected to reduce the demand for invasive procedures and expand the scope of noninvasive intestinal evaluation in the coming future.

Artificial Intelligence and Panendoscopy-Automatic Detection of Clinically Relevant Lesions in Multibrand Device-Assisted Enteroscopy

Device-assisted enteroscopy (DAE) is capable of evaluating the entire gastrointestinal tract, identifying multiple lesions. Nevertheless, DAE's diagnostic yield is suboptimal. Convolutional neural networks (CNN) are multi-layer architecture artificial intelligence models suitable for image analysis, but there is a lack of studies about their application in DAE. Our group aimed to develop a multidevice CNN for panendoscopic detection of clinically relevant lesions during DAE. In total, 338 exams performed in two specialized centers were retrospectively evaluated, with 152 single-balloon enteroscopies (Fujifilm®, Porto, Portugal), 172 double-balloon enteroscopies (Olympus®, Porto, Portugal) and 14 motorized spiral enteroscopies (Olympus®, Porto, Portugal); then, 40,655 images were divided in a training dataset (90% of the images, n = 36,599) and testing dataset (10% of the images, n = 4066) used to evaluate the model. The CNN's output was compared to an expert consensus classification. The model was evaluated by its sensitivity, specificity, positive (PPV) and negative predictive values (NPV), accuracy and area under the precision recall curve (AUC-PR). The CNN had an 88.9% sensitivity, 98.9% specificity, 95.8% PPV, 97.1% NPV, 96.8% accuracy and an AUC-PR of 0.97. Our group developed the first multidevice CNN for panendoscopic detection of clinically relevant lesions during DAE. The development of accurate deep learning models is of utmost importance for increasing the diagnostic yield of DAE-based panendoscopy.

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.