Artificial Intelligence in Colon Capsule Endoscopy—A Systematic Review

Artificial intelligence in gastroenterology: Ethical and diagnostic challenges in clinical practice

This article discusses the manuscript recently published in the World Journal of Gastroenterology, which explores the application of deep learning models in decision-making processes via wireless capsule endoscopy. Integrating artificial intelligence (AI) into gastrointestinal disease diagnosis represents a transformative step toward precision medicine, enhancing real-time accuracy in detecting multi-category lesions at earlier stages, including small bowel lesions and precancerous polyps, ultimately improving patient outcomes. However, the use of AI in clinical settings raises ethical considerations that extend beyond technological potential. Issues of patient privacy, data security, and potential diagnostic biases require careful attention. AI models must prioritize diverse and representative datasets to mitigate inequities and ensure diagnostic accuracy across populations. Furthermore, balancing AI with clinical expertise is crucial, positioning AI as a supportive tool rather than a replacement for physician judgment. Addressing these ethical challenges will support the responsible deployment of AI, through equitable contribution to patient-centered care.

Towards full integration of explainable artificial intelligence in colon capsule endoscopy's pathway

Despite recent surge of interest in deploying colon capsule endoscopy (CCE) for early diagnosis of colorectal diseases, there remains a large gap between the current state of CCE in clinical practice, and the state of its counterpart optical colonoscopy (OC). This is due to several factors, such as low quality bowel cleansing, logistical challenges around both delivery and collection of the capsule, and most importantly, the tedious manual assessment of images after retrieval. Our study, built on the "Danish CareForColon2015 trial (cfc2015)" is aimed at closing this gap, by focusing on the full integration of AI in CCE's pathway, where image processing steps linked to the detection, localization and characterisation of important findings are carried out autonomously using various AI algorithms. We developed a family of algorithms based on explainable deep neural networks (DNN) that detect polyps within a sequence of images, feed only those images containing polyps into two parallel independent networks to characterize, and estimate the size of important findings. Our recognition DNN to detect colorectal polyps was trained and validated ([Formula: see text]) and tested ([Formula: see text]) on an unaugmented database of 1751 images containing colorectal polyps and 1672 images of normal mucosa reached an impressive sensitivity of [Formula: see text], a specificity of [Formula: see text], and a negative predictive value (NPV) of [Formula: see text]. The characterisation DNN trained on an unaugmented database of 317 images featuring neoplastic polyps and 162 images of non-neoplastic polyps reached a sensitivity of [Formula: see text] and a specificity of [Formula: see text] in classifying polyps. The size estimation DNN trained on an unaugmented database of 280 images reached an accuracy of [Formula: see text] in correctly segmenting the polyps. By automatically incorporating important information including size, location and pathology of the findings into CCE's pathway, we moved a step closer towards the full integration of explainable AI (XAI) in CCE's routine clinical practice. This translates into a fewer number of unnecessary investigations and resection of diminutive, insignificant colorectal polyps.

Unifying terminology, reporting, and bowel preparation standards in colon capsule endoscopy: Nyborg Consensus

Background and study aims

Colon capsule endoscopy (CCE) is becoming increasingly popular in Europe. However, development of quality assurance and standardized terminology has not kept pace with clinical integration of this technology. As a result, there are significant variations in reporting standards, highlighting the need for a standardized terminology and framework. We used the RAND process to achieve a consensus of experts to determine the terminology in CCE, bowel cleansing assessment, and quality assurance reporting and future research priorities.

Methods

A panel comprising 14 European CCE experts evaluated 45 statements during the international REFLECT symposium (Nyborg, Denmark) through three survey rounds and face-to-face and virtual discussions in the initial two rounds. Participants anonymously rated statement appropriateness.

Results

Twenty-eight consensus statements were developed. Eight statements focus on consistent terminology for confirming CCE-detected polypoid and inflammatory colonic lesions with colonoscopy. To ensure standardization and quality assurance, 13 mandatory fields were recommended for inclusion in a CCE report. Three endorsed reporting methodologies were suggested, emphasizing prompt notification for suspected malignant findings, recommending a generic disclaimer regarding stomach and small bowel visualization intentions, and establishing reporting timelines at an interdepartmental level based on urgency. Four bowel preparation scale-related statements led to the recommendation to adoptithe Colon Capsule CLEansing Assessment and Reporting (CC-CLEAR) scale as the preferred scale.

Conclusions

This study established a framework for terminology, reporting, and assessment of bowel cleansing for CCE. Future research should focus on optimizing bowel preparation regimens and exploring artificial intelligence applications in CCE.

Colon capsule endoscopy: Can it contribute to green endoscopy?

Climate change due to sustained carbon dioxide (CO2) emissions poses a serious threat to human existence, such as extreme weather events that must be addressed in all sectors of society. Gastrointestinal endoscopy is a healthcare sector that produces high levels of CO2 emissions. Colonoscopy (CS) is the gold standard for colorectal cancer (CRC) screening that reduces the number of CRC-related deaths. However, vast amounts of cleaning solutions used to disinfect the colonoscope are disposed of, and multiple nonrenewable wastes are generated in performing CS, which significantly impact the environment. Currently, colon capsule endoscopy (CCE) retains good accuracy and has excellent potential to reduce CO2 emission through a simple procedure. However, to date, colon capsules are single-use and lack a clear collection pathway. In addition, there is a lack of specific data regarding the environmental impact of CCE. Further research is needed to prove that CCE is a more environmentally friendly tool than CS.

Polyp Matching in Colon Capsule Endoscopy: Pioneering CCE-Colonoscopy Integration Towards an AI-Driven Future

Background: Colon capsule endoscopy (CCE) is becoming more widely available across Europe, but its uptake is slow due to the need for follow-up colonoscopy for therapeutic procedures and biopsies, which impacts its cost-effectiveness. One of the major factors driving the conversion to colonoscopy is the detection of excess polyps in CCE that cannot be matched during subsequent colonoscopy. The capsule's rocking motion, which can lead to duplicate reporting of the same polyp when viewed from different angles, is likely a key contributor. Objectives: This review aims to explore the types of polyp matching reported in the literature, assess matching techniques and matching accuracy, and evaluate the development of machine learning models to improve polyp matching in CCE and subsequent colonoscopy. Methods: A systematic literature search was conducted in EMBASE, MEDLINE, and PubMed. Due to the scarcity of research in this area, the search encompassed clinical trials, observational studies, reviews, case series, and editorial letters. Three directly related studies were included, and ten indirectly related studies were included for review. Results: Polyp matching in colon capsule endoscopy still needs to be developed, with only one study focused on creating criteria to match polyps within the same CCE video. Another study established that experienced CCE readers have greater accuracy, reducing interobserver variability. A machine learning algorithm was developed in one study to match polyps between initial CCE and subsequent colonoscopy. Only around 50% of polyps were successfully matched, requiring further optimisation. As Artificial Intelligence (AI) algorithms advance in CCE polyp detection, the risk of duplicate reporting may increase when clinicians are presented with polyp images or timestamps, potentially complicating the transition to AI-assisted CCE reading in the future. Conclusions: Polyp matching in CCE is a developing field with considerable challenges, especially in matching polyps within the same video. Although AI shows potential for decent accuracy, more research is needed to refine these techniques and make CCE a more reliable, non-invasive alternative to complement conventional colonoscopy for lower GI investigations.

Bowel cleansing quality evaluation in colon capsule endoscopy: what is the reference standard?

BACKGROUND

The diagnostic accuracy of colon capsule endoscopy (CCE) depends on a well-cleansed bowel. Evaluating the cleansing quality can be difficult with a substantial interobserver variation.

OBJECTIVES

Our primary aim was to establish a standard of agreement for bowel cleansing in CCE based on evaluations by expert readers. Then, we aimed to investigate the interobserver agreement on bowel cleansing.

DESIGN

We conducted an interobserver agreement study on bowel cleansing quality.

METHODS

Readers with different experience levels in CCE and colonoscopy evaluated bowel cleansing quality on the Leighton-Rex scale and Colon Capsule CLEansing Assessment and Report (CC-CLEAR), respectively. All evaluations were reported on an image level. A total of 24 readers rated 500 images on each scale.

RESULTS

An expert opinion-based agreement standard could be set for poor and excellent cleansing but not for the spectrum in between, as the experts agreed on only a limited number of images representing fair and good cleansing. The overall interobserver agreement on the Leighton-Rex full scale was good (intraclass correlation coefficient (ICC) 0.84, 95% CI (0.82-0.85)) and remained good when stratified by experience level. On the full CC-CLEAR scale, the overall agreement was moderate (ICC 0.62, 95% CI (0.59-0.65)) and remained so when stratified by experience level.

CONCLUSION

The interobserver agreement was good for the Leighton-Rex scale and moderate for CC-CLEAR, irrespective of the reader's experience level. It was not possible to establish an expert-opinion standard of agreement for cleansing quality in CCE images. Dedicated training in using the scales may improve agreement and enable future algorithm calibration for artificial intelligence supported cleansing evaluation.

TRIAL REGISTRATION

All included images were derived from the CAREforCOLON 2015 trial (Registered with The Regional Health Research Ethics Committee (Registration number: S-20190100), the Danish data protection agency (Ref. 19/29858), and ClinicalTrials.gov (registration number: NCT04049357)).

The Diagnostic Accuracy of Colon Capsule Endoscopy in Inflammatory Bowel Disease-A Systematic Review and Meta-Analysis

Colon capsule endoscopy (CCE) has regained popularity for lower gastrointestinal investigations since the COVID-19 pandemic. While there have been systematic reviews and meta-analyses on colonic polyp detection using CCE, there is a lack of comprehensive evidence concerning colonic inflammation. Therefore, this systematic review and meta-analysis aimed to assess the diagnostic accuracy of CCE for colonic inflammation, predominantly ulcerative colitis (UC) and Crohn's disease (CD). Methods: We systematically searched electronic databases (EMBASE, MEDLINE, PubMed Central, and Cochrane Library) for studies comparing the diagnostic accuracy between CCE and optical endoscopy as the standard reference. A bivariate random effect model was used for the meta-analysis. Results: From 3797 publications, 23 studies involving 1353 patients were included. Nine studies focused on UC, and ten focused on CD. For UC, CCE showed a pooled sensitivity of 92% (95% CI, 88-95%), a specificity of 71% (95% CI, 35-92%), and an AUC of 0.93 (95% CI, 0.89-0.97). For CD, the pooled sensitivity was 92% (95% CI, 89-95%), and the specificity was 88% (95% CI, 84-92%), with an AUC of 0.87 (95% CI, 0.76-0.98). Overall, for inflammatory bowel disease, the pooled sensitivity, specificity, and AUC were 90% (95% CI, 85-93%), 76% (95% CI, 56-90%), and 0.92 (95% CI, 0.94-0.97), respectively. Conclusions: Despite the challenges around standardised disease scoring and the lack of histological confirmation, CCE performs well in diagnosing inflammatory bowel disease. It demonstrates high sensitivity in both UC and Crohn's terminal ileitis and colitis and high specificity in Crohn's disease. Further studies are needed to evaluate the diagnostic accuracy of other colonic inflammatory conditions.

Smart Endoscopy Is Greener Endoscopy: Leveraging Artificial Intelligence and Blockchain Technologies to Drive Sustainability in Digestive Health Care

The surge in the implementation of artificial intelligence (AI) in recent years has permeated many aspects of our life, and health care is no exception. Whereas this technology can offer clear benefits, some of the problems associated with its use have also been recognised and brought into question, for example, its environmental impact. In a similar fashion, health care also has a significant environmental impact, and it requires a considerable source of greenhouse gases. Whereas efforts are being made to reduce the footprint of AI tools, here, we were specifically interested in how employing AI tools in gastroenterology departments, and in particular in conjunction with capsule endoscopy, can reduce the carbon footprint associated with digestive health care while offering improvements, particularly in terms of diagnostic accuracy. We address the different ways that leveraging AI applications can reduce the carbon footprint associated with all types of capsule endoscopy examinations. Moreover, we contemplate how the incorporation of other technologies, such as blockchain technology, into digestive health care can help ensure the sustainability of this clinical speciality and by extension, health care in general.

Familial intestinal polyposis and device assisted enteroscopy: where do we stand?

INTRODUCTION

Hereditary polyposis syndromes are a group of inherited disorders associated with a high risk of developing colorectal cancer. The best known ones are familial adenomatous polyposis (FAP), Peutz-Jeghers (PJS), juvenile polyposis and Cowden syndromes, as well as conditions predisposing to cancer, such as Lynch syndrome. Some of them are characterized by an increased risk of small bowel polyps occurrence.

AREAS COVERED

Literature search in PubMed was performed in November 2022 and a narrative review was carried out. Since performing small bowel polypectomy is important in such patients, device assisted enteroscopy (DAE) is the key for this procedure. A screening strategy for small bowel polyps is recommended only for PJS. Guidelines endorse either magnetic resonance imaging (MRI) or videocapsule endoscopy (VCE) every 1-3 years, according to the phenotype of the disease. Enteroscopy should be considered for therapeutic purpose in patients with a positive VCE or MRI. DAE has a central role in the resection of polyps larger than mm or causing symptoms of subocclusion or intussusception. Both single (SBE) and double balloon enteroscopy (DBE) are indicated and able to resect polyps up to 6-10 cm. American guidelines have restricted the indications to small bowel enteroscopy only to FAP patients with grade IV Spiegelman.

EXPERT OPINION

Only some groups of patients (PJS, FAP with demonstrated small bowel polyp burden) may benefit from DAE.

The Promise of Artificial Intelligence in Digestive Healthcare and the Bioethics Challenges It Presents

With modern society well entrenched in the digital area, the use of Artificial Intelligence (AI) to extract useful information from big data has become more commonplace in our daily lives than we perhaps realize. Medical specialties that rely heavily on imaging techniques have become a strong focus for the incorporation of AI tools to aid disease diagnosis and monitoring, yet AI-based tools that can be employed in the clinic are only now beginning to become a reality. However, the potential introduction of these applications raises a number of ethical issues that must be addressed before they can be implemented, among the most important of which are issues related to privacy, data protection, data bias, explainability and responsibility. In this short review, we aim to highlight some of the most important bioethical issues that will have to be addressed if AI solutions are to be successfully incorporated into healthcare protocols, and ideally, before they are put in place. In particular, we contemplate the use of these aids in the field of gastroenterology, focusing particularly on capsule endoscopy and highlighting efforts aimed at resolving the issues associated with their use when available.

Clinicians’ Guide to Artificial Intelligence in Colon Capsule Endoscopy—Technology Made Simple

Artificial intelligence (AI) applications have become widely popular across the healthcare ecosystem. Colon capsule endoscopy (CCE) was adopted in the NHS England pilot project following the recent COVID pandemic’s impact. It demonstrated its capability to relieve the national backlog in endoscopy. As a result, AI-assisted colon capsule video analysis has become gastroenterology’s most active research area. However, with rapid AI advances, mastering these complex machine learning concepts remains challenging for healthcare professionals. This forms a barrier for clinicians to take on this new technology and embrace the new era of big data. This paper aims to bridge the knowledge gap between the current CCE system and the future, fully integrated AI system. The primary focus is on simplifying the technical terms and concepts in machine learning. This will hopefully address the general “fear of the unknown in AI” by helping healthcare professionals understand the basic principle of machine learning in capsule endoscopy and apply this knowledge in their future interactions and adaptation to AI technology. It also summarises the evidence of AI in CCE and its impact on diagnostic pathways. Finally, it discusses the unintended consequences of using AI, ethical challenges, potential flaws, and bias within clinical settings.

Low Colon Capsule Endoscopy (CCE) False Negative Rate for Polyps Excluding Reader Error

BACKGROUND

CCE is a diagnostic tool lacking clinical data on false negative rates. We aimed to assess this rate and the reader/technical error breakdown.

METHODS

False negative CCEs were identified after comparing to a colonoscopy database. Missed pathology characteristics and study indications/quality were collated. Cases were re-read by experts and newly identified lesions/pathologies were verified by an expert panel and categorised as reader/technical errors.

RESULTS

Of 532 CCEs, 203 had an adequately reported comparative colonoscopy, 45 (22.2%) had missed polyps, and 26/45 (57.8%) reached the colonic section with missed pathology. Of the cases, 22 (84.6%) had adequate bowel preparation. Indications included 13 (50%) polyp surveillance, 12 (46%) GI symptoms, 1 (4%) polyp screening. CCE missed 18 (69.2%) diminutive polyps and 8 (30.8%) polyps ≥ 6 mm, 18/26 (69.2%) of these were adenomas. Excluding incomplete CCE correlates, colonoscopy total and significant polyp yield were 97/184 (52.7%) and 50/97 (51.5%), respectively. CCE total polyp and significant polyp false negative rate was 26.8% (26/97) and 16% (8/50), respectively. Following re-reading, reader and technical error was 20/26 (76.9%) and 6/26 (23.1%). Total and significant missed polyp rates were 20.6% (20/97) and 14% (7/50) for reader error, 6.2% (6/97) and 2% (1/50) for technical error.

CONCLUSIONS

False negative CCE rate is not insubstantial and should be factored into clinical decision making.

Colon Capsule Endoscopy in the Diagnosis of Colon Polyps: Who Needs a Colonoscopy?

Colon screening programs have reduced colon cancer mortality. Population screening should be minimally invasive, safe, acceptably sensitive, cost-effective, and scalable. The range of screening modalities include guaiac or immunochemical fecal occult blood testing and CT colonography and colonoscopy. A number of carefully controlled studies concur that second-generation capsule endoscopy has excellent sensitivity for polyp detection and a high negative predictive value. Colon capsules fulfill the screening expectation of safety, high sensitivity for polyp detection, and patient acceptance, and appear to straddle the divide between occult blood testing and colonoscopy. While meeting these criteria, there remains the challenges of scaling, capsule practitioner training, resource allocation, and implementing change of practice. Like CT colonography, capsule screening presents the clinician with a decision on the threshold for colonoscopy referral. Overall, colon capsules are an invaluable tool in polyp detection and colon screening and offer a filter that determines “who needs a colonoscopy?”.