Can we improve the detection rate and interobserver agreement in capsule endoscopy?

Video capsule endoscopy findings in dogs with chronic enteropathy and in healthy dogs

BACKGROUND

Video capsule endoscopy is a noninvasive technique for evaluation of the gastrointestinal tract.

OBJECTIVE

To investigate the safety of using the video capsule ALICAM in dogs with chronic enteropathy (CE) >10 kg, and to compare macroscopic gastrointestinal morphology between CE dogs and healthy controls (HC).

ANIMALS

Fifteen CE dogs and 15 similarly breed, age and body weight matched HC.

METHODS

All dogs underwent a clinical work up including blood analyses, fecal samples, abdominal ultrasonographic examination, and blood pressure measurement. The dogs were withheld from food for 16 hours before and 8 hours after they PO received an ALICAM. All recordings were quality assessed, and blindly evaluated by 2 trained observers.

RESULTS

The median age of CE dogs and HC was 3.3 (interquartile range [IQR] 2.5-5.9) years and 4.7 (IQR 3.3-5.6) years, respectively. The median body weight in the CE dogs and HC was 25.9 (IQR 20.6-30.9) kg, and 29 (IQR 16.2-30.5) kg, respectively. Complete recordings of the gastrointestinal tract were obtained from all dogs without complications. No significant differences were found between groups regarding number of abnormalities such as irregular mucosa, erythema, nonbleeding erosions, bleeding erosions, and dilated lacteals, as well as severity and extent of the abnormalities.

CONCLUSIONS AND CLINICAL IMPORTANCE

The use of ALICAM for evaluation of the gastrointestinal tract in CE dogs and HC seems safe and feasible regarding gastrointestinal transit and macroscopic morphology assessment in dogs >10 kg. Abnormalities were found in similar proportions in CE dogs and HC.

More than 20 procedures are necessary to learn small bowel capsule endoscopy: Learning curve pilot study of 535 trainee cases

Background and study aims The number of procedures needed to acquire a sufficient level of skills to perform an unassisted evaluation of small bowel capsule endoscopy (SBCE) is unknown. We aimed to establish learning curves, diagnostic accuracy, and the number of procedures needed for reviewing small bowel capsule endoscopies unassisted. Methods An expert panel developed a 1-day course including lessons (examination, anatomy, and pathology) and hands-on training. After completing the course, participants received 50 cases in a randomized sequence. An interactive questionnaire about landmarks, findings, and diagnosis followed each case. After submitting the questionnaire, participants received feedback. Data are presented using CUSUM (cumulative sum control chart) learning curves and sensitivity/specificity analyses compared with expert opinions. Results We included 22 gastroenterologists from 11 different Danish hospitals. A total of 535 cases were reviewed (mean: 28; range: 11-50). CUSUM plots demonstrated learning progression for diagnosis and findings during the course, but none of the participants reached a learning plateau with sufficient competencies. The sensitivity for all findings was 65% (95% confidence interval [CI] 0.51-0.82) for the first 20 procedures and 67% (95% CI 0.58-0.73) from case 21 until completion or dropout. The specificity was 63% (95% CI 0.52-0.74) for the first 20 procedures and 57% (95% CI 0.37-0.77) for the rest. Conclusions Our data indicate that learning SBCE may be more difficult than previously recognized due to low discriminative abilities after 20 cases except for the identification of CD. This indicates that 20 SBCE cases may not be sufficient to achieve competency for reviewing SBCE without supervision.

Inter/Intra-Observer Agreement in Video-Capsule Endoscopy: Are We Getting It All Wrong? A Systematic Review and Meta-Analysis

Video-capsule endoscopy (VCE) reading is a time- and energy-consuming task. Agreement on findings between readers (either different or the same) is a crucial point for increasing performance and providing valid reports. The aim of this systematic review with meta-analysis is to provide an evaluation of inter/intra-observer agreement in VCE reading. A systematic literature search in PubMed, Embase and Web of Science was performed throughout September 2022. The degree of observer agreement, expressed with different test statistics, was extracted. As different statistics are not directly comparable, our analyses were stratified by type of test statistics, dividing them in groups of "None/Poor/Minimal", "Moderate/Weak/Fair", "Good/Excellent/Strong" and "Perfect/Almost perfect" to report the proportions of each. In total, 60 studies were included in the analysis, with a total of 579 comparisons. The quality of included studies, assessed with the MINORS score, was sufficient in 52/60 studies. The most common test statistics were the Kappa statistics for categorical outcomes (424 comparisons) and the intra-class correlation coefficient (ICC) for continuous outcomes (73 comparisons). In the overall comparison of inter-observer agreement, only 23% were evaluated as "good" or "perfect"; for intra-observer agreement, this was the case in 36%. Sources of heterogeneity (high, I2 81.8-98.1%) were investigated with meta-regressions, showing a possible role of country, capsule type and year of publication in Kappa inter-observer agreement. VCE reading suffers from substantial heterogeneity and sub-optimal agreement in both inter- and intra-observer evaluation. Artificial-intelligence-based tools and the adoption of a unified terminology may progressively enhance levels of agreement in VCE reading.

Development and Validation of an Artificial Intelligence Model for Small Bowel Capsule Endoscopy Video Review

IMPORTANCE

Reading small bowel capsule endoscopy (SBCE) videos is a tedious task for clinicians, and a new method should be applied to solve the situation.

OBJECTIVES

To develop and evaluate the performance of a convolutional neural network algorithm for SBCE video review in real-life clinical care.

DESIGN, SETTING, AND PARTICIPANTS

In this multicenter, retrospective diagnostic study, a deep learning neural network (SmartScan) was trained and validated for the SBCE video review. A total of 2927 SBCE examinations from 29 medical centers were used to train SmartScan to detect 17 types of CE structured terminology (CEST) findings from January 1, 2019, to June 30, 2020. SmartScan was later validated with conventional reading (CR) and SmartScan-assisted reading (SSAR) in 2898 SBCE examinations collected from 22 medical centers. Data analysis was performed from January 25 to December 31, 2021.

EXPOSURE

An artificial intelligence-based tool for interpreting clinical images of SBCE.

MAIN OUTCOMES AND MEASURES

The detection rate and efficiency of CEST findings detected by SSAR and CR were compared.

RESULTS

A total of 5825 SBCE examinations were retrospectively collected; 2898 examinations (1765 male participants [60.9%]; mean [SD] age, 49.8 [15.5] years) were included in the validation phase. From a total of 6084 CEST-classified SB findings, SSAR detected 5834 findings (95.9%; 95% CI, 95.4%-96.4%), significantly higher than CR, which detected 4630 findings (76.1%; 95% CI, 75.0%-77.2%). SmartScan-assisted reading achieved a higher per-patient detection rate (79.3% [2298 of 2898]) for CEST findings compared with CR (70.7% [2048 of 2298]; 95% CI, 69.0%-72.3%). With SSAR, the mean (SD) number of images (per SBCE video) requiring review was reduced to 779.2 (337.2) compared with 27 910.8 (12 882.9) with CR, for a mean (SD) reduction rate of 96.1% (4.3%). The mean (SD) reading time with SSAR was shortened to 5.4 (1.5) minutes compared with CR (51.4 [11.6] minutes), for a mean (SD) reduction rate of 89.3% (3.1%).

CONCLUSIONS AND RELEVANCE

This study suggests that a convolutional neural network-based algorithm is associated with an increased detection rate of SBCE findings and reduced SBCE video reading time.

A Library of Logic Models to Explain How Interventions to Reduce Diagnostic Errors Work

OBJECTIVES

We aimed to create a library of logic models for interventions to reduce diagnostic error. This library can be used by those developing, implementing, or evaluating an intervention to improve patient care, to understand what needs to happen, and in what order, if the intervention is to be effective.

METHODS

To create the library, we modified an existing method for generating logic models. The following five ordered activities to include in each model were defined: preintervention; implementation of the intervention; postimplementation, but before the immediate outcome can occur; the immediate outcome (usually behavior change); and postimmediate outcome, but before a reduction in diagnostic errors can occur. We also included reasons for lack of progress through the model. Relevant information was extracted about existing evaluations of interventions to reduce diagnostic error, identified by updating a previous systematic review.

RESULTS

Data were synthesized to create logic models for four types of intervention, addressing five causes of diagnostic error in seven stages in the diagnostic pathway. In total, 46 interventions from 43 studies were included and 24 different logic models were generated.

CONCLUSIONS

We used a novel approach to create a freely available library of logic models. The models highlight the importance of attending to what needs to occur before and after intervention delivery if the intervention is to be effective. Our work provides a useful starting point for intervention developers, helps evaluators identify intermediate outcomes, and provides a method to enable others to generate libraries for interventions targeting other errors.

Efficacy of a comprehensive binary classification model using a deep convolutional neural network for wireless capsule endoscopy

The manual reading of capsule endoscopy (CE) videos in small bowel disease diagnosis is time-intensive. Algorithms introduced to automate this process are premature for real clinical applications, and multi-diagnosis using these methods has not been sufficiently validated. Therefore, we developed a practical binary classification model, which selectively identifies clinically meaningful images including inflamed mucosa, atypical vascularity or bleeding, and tested it with unseen cases. Four hundred thousand CE images were randomly selected from 84 cases in which 240,000 images were used to train the algorithm to categorize images binarily. The remaining images were utilized for validation and internal testing. The algorithm was externally tested with 256,591 unseen images. The diagnostic accuracy of the trained model applied to the validation set was 98.067%. In contrast, the accuracy of the model when applied to a dataset provided by an independent hospital that did not participate during training was 85.470%. The area under the curve (AUC) was 0.922. Our model showed excellent internal test results, and the misreadings were slightly increased when the model was tested in unseen external cases while the classified 'insignificant' images contain ambiguous substances. Once this limitation is solved, the proposed CNN-based binary classification will be a promising candidate for developing clinically-ready computer-aided reading methods.

The impact of reader fatigue on the accuracy of capsule endoscopy interpretation

BACKGROUND AND AIMS

Capsule endoscopy (CE) interpretation requires the review of many thousands of images, with lesions often limited to just a few frames. In this study we aim to determine whether lesion detection declines according to the number of capsule videos read.

METHODS

32 participants, 16 of which were novices (NR) and 16 experienced (ER) capsule readers took part in this prospective evaluation study. Participants read six capsule cases with a variety of lesions, in a randomly assigned order during a single sitting. Psychomotor Vigilance Tests and Fatigue Scores were recorded prior to commencing and then after every two capsules read. Changes in lesion detection and measures of fatigue were assessed across the duration of the study.

RESULTS

Mean agreement with the predefined lesions was 48.3% (SD:16.1), and 21.3% (SD:15.1) for the experienced and novice readers respectively. Lesion detection declined amongst experienced reader after the first study (p = 0.01), but remained stable after subsequent capsules read, while NR accuracy was unaffected by capsule numbers read. Objective measures of fatigue did not correlate with reading accuracy.

CONCLUSION

This study demonstrates that reader accuracy declines after reading just one capsule study. Subjective and objective measures of fatigue were not sufficient to predict the onset of the effects of fatigue.

Kvasir-Capsule, a video capsule endoscopy dataset

Artificial intelligence (AI) is predicted to have profound effects on the future of video capsule endoscopy (VCE) technology. The potential lies in improving anomaly detection while reducing manual labour. Existing work demonstrates the promising benefits of AI-based computer-assisted diagnosis systems for VCE. They also show great potential for improvements to achieve even better results. Also, medical data is often sparse and unavailable to the research community, and qualified medical personnel rarely have time for the tedious labelling work. We present Kvasir-Capsule, a large VCE dataset collected from examinations at a Norwegian Hospital. Kvasir-Capsule consists of 117 videos which can be used to extract a total of 4,741,504 image frames. We have labelled and medically verified 47,238 frames with a bounding box around findings from 14 different classes. In addition to these labelled images, there are 4,694,266 unlabelled frames included in the dataset. The Kvasir-Capsule dataset can play a valuable role in developing better algorithms in order to reach true potential of VCE technology.

Feasibility, complications, and quality of visualization using video capsule endoscopy in 40 dogs with overt or questionable gastrointestinal bleeding

Background

Prospective studies describing video capsule endoscopy (VCE), its feasibility, and complications in dogs are limited.

Objective

To assess VCE, quality of visualization, complications, and risk factors for incomplete studies in dogs with overt or questionable gastrointestinal bleeding (GIB).

Animals

Forty dogs with overt or questionable GIB.

Methods

Prospective, multicenter, interventional study. From August 2017 to March 2020, dogs were examined by VCE (ALICAM) because of overt or questionable GIB. Reported outcomes included diagnostic results of VCE study, quality of visualization, and complications. Risk factors for incomplete studies were evaluated using logistic regression.

Results

In total, 40 dogs (13 overt, 27 questionable GIB) were included. The capsules were administered PO in 29 and endoscopically in 11 dogs (6 duodenum, 5 stomach). One capsule was not retrieved. In 24 of 39 recordings, bleeding lesions were identified (10 overt GIB, 14 questionable GIB). Overall, the quality of visualization was poor to limited in the stomach and colon, and adequate to good in the small intestine. The most common complication was an incomplete study in 15/39 studies, particularly after oral administration (13/28). Risk factors for incomplete study after oral administration included administration of simethicone or opioids, chronic enteropathy, and capsule gastric transit time >6 hours.

Conclusions and Clinical Importance

Video capsule endoscopy can be used to diagnose a variety of lesions causing bleeding in the gastrointestinal tract of dogs with questionable GIB. Incomplete studies are the most common complications in dogs after oral administration of capsules.

Double-headed small-bowel capsule endoscopy: Real-world experience from a multi-centre British study

INTRODUCTION

Capsule endoscopy (CE) is well established the investigation of small-bowel (SB) pathology. We compared the use of double-headed (DH) capsules, to conventional single-headed (SH), in a real-world patient cohort in the first multicentre British study.

METHODS

Over 9 months, patients referred for routine SBCE at 4 tertiary referral centres in the UK underwent DH CE instead of conventional SH using MiroCam^Ⓡ MC2000 as per local protocols. One head (L/R) was chosen at random and reported by an expert reviewer. The DH recordings, anonymised and randomised, reported by another expert or re-read after a 4-week interval. For each CE, numbers and types of findings and overall conclusion/diagnosis were compared between SH and DH examinations.

RESULTS

211 CEs were performed. 7 failed to reach the SB; 204 analysed. Indications were: SB bleeding (n = 94); ?SB inflammation or reassessment of known inflammatory bowel disease (IBD) (n = 84); ?SB neoplasia including suspicious radiological imaging (n = 15); and, others e.g. ?celiac disease (n = 11). For SB bleeding: 27/94 (28.7%) examinations reported differences between SH and DH readings. In 17 (18.1%) the findings were clinically significant. SH CE missed angiectasias (5 pts), SB inflammation (7 pts), oesophagitis (2 pts) and SB masses (2 pts). In 1 patient, the extent of angiectasias seen was greater on the DH reading. For IBD: findings differed in 30/84 (35.7%) of CEs; 11 (13.1%) were clinically significant. In 5, signs of active inflammation were missed by the SH reading. In 6, assessment of extent/severity differed. For?SB neoplasia findings differed in 2/15 (13.3%) of examinations. Both were clinically significant. For others: 1/11 (9.1%) examinations differed; however, not deemed clinically significant. Overall, use of DH CE impacted the diagnosis in 30/204 (14.7%).

CONCLUSIONS

The use of DH CE provides more information with the potential to change clinical diagnosis and therefore management. Therefore, the routine adoption of DH CE in SB assessment should be considered.

Panenteric capsule endoscopy identifies proximal small bowel disease guiding upstaging and treatment intensification in Crohn's disease: A European multicentre observational cohort study

Background

Endoscopically defined mucosal healing in Crohn's disease is associated with improved outcomes. Panenteric capsule endoscopy enables a single non‐invasive assessment of small and large bowel mucosal inflammation.

Aims and Methods

This multicentre observational study of patients with suspected and established Crohn's disease examined the feasibility, safety and impact on patient outcomes of panenteric capsule endoscopy in routine clinical practice. The potential role in assessment of disease severity and extent by a comparison with existing clinical and biochemical markers is examined.

Results

Panenteric capsule endoscopy was performed on 93 patients (71 with established and 22 with suspected Crohn's disease). A complete examination occurred in 85% (79/93). Two cases (2.8%) of capsule retention occurred in patients with established Crohn's disease. Panenteric capsule resulted in management change in 38.7% (36/93) patients, including 64.6% (32/48) of those with an established diagnosis whose disease was active, and all three patients with newly diagnosed Crohn's disease. Montreal classification was upstaged in 33.8% of patients with established Crohn's disease and mucosal healing was demonstrated in 15.5%. Proximal small bowel disease upstaged disease in 12.7% and predicted escalation of therapy (odds ratio 40.3, 95% confidence interval 3.6–450.2). Raised C‐reactive protein and faecal calprotectin were poorly sensitive in detecting active disease (0.48 and 0.59 respectively).

Conclusions

Panenteric capsule endoscopy was feasible in routine practice and the ability to detect proximal small bowel disease may allow better estimation of prognosis and guide treatment intensification. Panenteric capsule endoscopy may be a suitable non‐invasive endoscopic investigation in determining disease activity and supporting management decisions.

Summarise the established knowledge on this subject

Biochemical and clinical markers poorly predict active disease and need for treatment escalation;

Panenteric capsule endoscope is feasible, safe and has the potential to non‐invasively assess patients with Crohn's Disease.

What are the significant and/or new findings of this study?

Panenteric capsule endoscope can upstage disease in one‐third of patients with a threefold increase in the identification of proximal small bowel disease;

Identification of proximal small bowel disease predicted treatment intensification.

Artificial intelligence in small bowel capsule endoscopy - current status, challenges and future promise

Neural network-based solutions are under development to alleviate physicians from the tedious task of small-bowel capsule endoscopy reviewing. Computer-assisted detection is a critical step, aiming to reduce reading times while maintaining accuracy. Weakly supervised solutions have shown promising results; however, video-level evaluations are scarce, and no prospective studies have been conducted yet. Automated characterization (in terms of diagnosis and pertinence) by supervised machine learning solutions is the next step. It relies on large, thoroughly labeled databases, for which preliminary "ground truth" definitions by experts are of tremendous importance. Other developments are under ways, to assist physicians in localizing anatomical landmarks and findings in the small bowel, in measuring lesions, and in rating bowel cleanliness. It is still questioned whether artificial intelligence will enter the market with proprietary, built-in or plug-in software, or with a universal cloud-based service, and how it will be accepted by physicians and patients.

Deep learning for wireless capsule endoscopy: a systematic review and meta-analysis

BACKGROUND AND AIMS

Deep learning is an innovative algorithm based on neural networks. Wireless capsule endoscopy (WCE) is considered the criterion standard for detecting small-bowel diseases. Manual examination of WCE is time-consuming and can benefit from automatic detection using artificial intelligence (AI). We aimed to perform a systematic review of the current literature pertaining to deep learning implementation in WCE.

METHODS

We conducted a search in PubMed for all original publications on the subject of deep learning applications in WCE published between January 1, 2016 and December 15, 2019. Evaluation of the risk of bias was performed using tailored Quality Assessment of Diagnostic Accuracy Studies-2. Pooled sensitivity and specificity were calculated. Summary receiver operating characteristic curves were plotted.

RESULTS

Of the 45 studies retrieved, 19 studies were included. All studies were retrospective. Deep learning applications for WCE included detection of ulcers, polyps, celiac disease, bleeding, and hookworm. Detection accuracy was above 90% for most studies and diseases. Pooled sensitivity and specificity for ulcer detection were .95 (95% confidence interval [CI], .89-.98) and .94 (95% CI, .90-.96), respectively. Pooled sensitivity and specificity for bleeding or bleeding source were .98 (95% CI, .96-.99) and .99 (95% CI, .97-.99), respectively.

CONCLUSIONS

Deep learning has achieved excellent performance for the detection of a range of diseases in WCE. Notwithstanding, current research is based on retrospective studies with a high risk of bias. Thus, future prospective, multicenter studies are necessary for this technology to be implemented in the clinical use of WCE.

Indications and diagnostic yield of small-bowel capsule endoscopy in a real-world setting

Background

Indications and diagnostic yield of small-bowel video capsule endoscopy (SB-VCE) are communicated in recent clinical academic guidelines. However, guidelines are based mainly on relatively few, small, selection-biased studies at experienced centers, and thus we lack information on indications and diagnostic yield of SB-VCE in the real-world community setting. The aim of the study was to evaluate indications and diagnostic yield of SB-VCE in the real-world community setting.

Methods

Our local VCE clinical database was used to identify patients undergoing SB-VCE procedures over a 7-year period (2011–2018). Patients were broadly referred and underwent SB-VCE using PillCam™ SB 2 and SB 3 capsule systems. Procedures were reviewed by local endoscopists, who had undergone similar formal SB-VCE review training. Medical reports of the procedures were composed as such. We retrospectively reviewed all reports and gathered data regarding indications and findings. Diagnostic yield was considered positive if SB-VCE visualized any type of clinically significant pathological finding.

Results

536 SB-VCE procedures in 516 patients were included in final assessment. Patient mean (± SD) age was 50 ± 20 years with approximately even female/male ratio (275:241). The overall proportion of positive findings was 42% (225/536). The two main indications were obscure gastrointestinal bleeding (occult/anemia or overt/active, OGIB) of 46% (246/536) and definite/suspected Crohn’s disease (CD) of 39% (210/536). Positive SB-VCE findings were obtained in 44% (108/246) of procedures with indication of OGIB and in 50% (104/210) of procedures with indication of CD.

Conclusions

The indications for SB-VCE are largely consistent with guidelines but with an apparently relatively low diagnostic yield in our real-world community setting.

Nomenclature and semantic descriptions of ulcerative and inflammatory lesions seen in Crohn's disease in small bowel capsule endoscopy: An international Delphi consensus statement

BACKGROUND

In the medical literature, the nomenclature and descriptions (ND) of small bowel (SB) ulcerative and inflammatory (U-I) lesions in capsule endoscopy (CE) are scarce and inconsistent. Inter-observer variability in interpreting these findings remains a major limitation in the assessment of the severity of mucosal lesions, which can impact negatively on clinical care, training and research on SB-CE.

OBJECTIVE

Focusing on SB-CE in Crohn's disease (CD), our aim is to establish a consensus on the ND of U-I lesions.

METHODS

An international panel of experienced SB-CE readers was formed during the 2016 United European Gastroenterology Week meeting. A core group of five CE and inflammatory bowel disease (IBD) experts established an Internet-based, three-round Delphi consensus but did not participate in the voting process. The core group built illustrated questionnaires, including SB-CE still frames of U-I lesions from patients with documented CD. Twenty-seven other experts were asked to rate and comment on the different proposals for the ND of the most frequent SB U-I lesions. For each round, we used a 6-point rating scale (varying from 'strongly disagree' to 'strongly agree'). The consensus was reached when at least 80 % of the voting members scored the statement within the 'agree' or 'strongly agree' categories.

RESULTS

A 100% participation rate was obtained for all the rounds. Consensual ND were reached for the following seven U-I lesions: aphthoid erosion, deep ulceration, superficial ulceration, stenosis, edema, hyperemia and denudation.

CONCLUSION

Considering the most frequent SB U-I lesions seen in CE in CD, a consensual ND was reached by the international group of experts. These descriptions and names are useful not only for daily practice and medical education, but also for medical research.

Training in video capsule endoscopy: Current status and unmet needs

Since its introduction to clinical practice nearly 20 years ago, wireless capsule endoscopy has revolutionized the landscape in the diagnosis and management of small bowel diseases. Over the past 10 years, capsule endoscopy has evolved beyond the small intestine and a range of capsules are now available to examine the esophagus, stomach and colon. Because of its ease of use, tolerability, paucity of complications and ability to visualize the entire gastrointestinal tract, capsule endoscopy has entered the mainstream of clinical practice. This review of the literature summarizes the current state of capsule training and highlights the limited data available to assess reader competence and standards expected of an independent practitioner. There are neither standardized teaching strategies nor national or international metrics for accreditation of physicians and non-physicians interested in mastering this examination. Summating the few publications, there appears to be consensus that diagnostic expertise improves with experience, and that trainees should be fully supervised for at least 20 full case studies. Formative and summative assessment is advisable and the number of taught cases should not be the sole determinant of competence. The review also highlights differences in recommendations from major national gastroenterology societies. Finally, the authors discuss areas of unmet needs in teaching and learning for capsule endoscopy.

Methodology to develop machine learning algorithms to improve performance in gastrointestinal endoscopy

Assisted diagnosis using artificial intelligence has been a holy grail in medical research for many years, and recent developments in computer hardware have enabled the narrower area of machine learning to equip clinicians with potentially useful tools for computer assisted diagnosis (CAD) systems. However, training and assessing a computer's ability to diagnose like a human are complex tasks, and successful outcomes depend on various factors. We have focused our work on gastrointestinal (GI) endoscopy because it is a cornerstone for diagnosis and treatment of diseases of the GI tract. About 2.8 million luminal GI (esophageal, stomach, colorectal) cancers are detected globally every year, and although substantial technical improvements in endoscopes have been made over the last 10-15 years, a major limitation of endoscopic examinations remains operator variation. This translates into a substantial inter-observer variation in the detection and assessment of mucosal lesions, causing among other things an average polyp miss-rate of 20% in the colon and thus the subsequent development of a number of post-colonoscopy colorectal cancers. CAD systems might eliminate this variation and lead to more accurate diagnoses. In this editorial, we point out some of the current challenges in the development of efficient computer-based digital assistants. We give examples of proposed tools using various techniques, identify current challenges, and give suggestions for the development and assessment of future CAD systems.

Optimising the performance and interpretation of small bowel capsule endoscopy

Small bowel capsule endoscopy has become a commonly used tool in the investigation of gastrointestinal symptoms and is now widely available in clinical practice. In contrast to conventional endoscopy, there is a lack of clear consensus on when competency is achieved or the way in which capsule endoscopy should be performed in order to maintain quality and clinical accuracy. Here we explore the evidence on the key factors that influence the quality of small bowel capsule endoscopy services.

Small-Bowel Capsule Endoscopy in Clinical Practice: Has Anything Changed Over 13 Years?

BACKGROUND

In Lombardia, one of the 20 Italian administrative Regions, small-bowel capsule endoscopy (SBCE) was introduced in 2001. In January 2011, the Regional Health Authorities established a reimbursement for outpatient SBCE.

AIM

To prospectively record data on SBCE between 2011-2013 and compare them to similar data retrospectively collected from the same geographical area (covering the period 2001-2008) and published in 2008.

METHODS

Consecutive SBCEs performed between January 2011 and December 2013 in Lombardia were prospectively collected.

RESULTS

In 3 years, 3142 SBCEs were collected; the diagnostic yield (DY) and the overall complication rate were 48.4 and 0.9%, respectively. The main indication was suspected small-bowel bleeding (76.6% of patients); complete small-bowel inspection was achieved in 2796 (89.0%) patients. SBCE was performed as an outpatient procedure in 1945 patients (61.9%). A significant increase in the rate of patients undergoing SBCE for suspected small-bowel bleeding was observed from 2001-2008 to 2011-2013 (67.3 vs. 76.1%; p < 0.001). There was an increase in the number of complete small-bowel examinations (81.2 vs. 89.0%; p < 0.001) and of outpatient SBCEs (6.7 vs. 61.9%; p < 0.001). Conversely, both the retention rate (2.1 vs. 0.8%; p < 0.001) and the rate of patients undergoing SBCE for Crohn's disease (11.5 vs. 5.5%; p < 0.001) decreased significantly. The overall DY remained stable (50.6 vs. 48.4%; p = 0.089).

CONCLUSION

Our study shows that, over 13 years, the SBCE safety profile and completion rate significantly improved over time; a change in the spectrum of clinical indications was also observed.

Current Status of Interpretation of Small Bowel Capsule Endoscopy

Capsule endoscopy (CE) has revolutionized direct small bowel imaging and is widely used in clinical practice. Remote visualization of bowel images enables painless, well-tolerated endoscopic examinations. Small bowel CE has a high diagnostic yield and the ability to examine the entire small bowel. The diagnostic yield of CE relies on lesion detection and interpretation. In this review, issues related to lesion detection and interpretation of CE have been addressed, and the current status of automated reading software development has been reviewed. Clinical significance of an external real-time image viewer has also been described.

Meta-analysis shows similar re-bleeding rates among Western and Eastern populations after index video capsule endoscopy

BACKGROUND & AIMS

Video capsule endoscopy (VCE) is the first-line diagnostic procedure for investigating obscure gastrointestinal bleeding (OGIB). Different re-bleeding rates following index VCE have been reported among Western and Eastern studies.

METHODS

We conducted a comprehensive literature search to identify studies examining re-bleeding rates after VCE for OGIB. Meta-analysis assessed the pooled proportion of re-bleeding events after VCE for OGIB according to study's origin (Western vs. Eastern) and according to the length of follow-up (≥24 months vs. <24 months). We also calculated the re-bleeding odds ratios (OR; 95% CI) after positive vs. negative index VCE, overt vs. occult initial presentation of bleeding and after interventional treatment for positive index cases, according to the study's origin.

RESULTS

We included 46 (30 Western and 16 Eastern) studies with 5796 patients. Significant heterogeneity was detected among meta-analyzed studies. Overall, the pooled re-bleeding rate was similar between Western (29%; 95% CI: 23-34) and Eastern (21%; 95% CI: 15-27) populations, irrespective of the length of follow-up. The odds of re-bleeding was significantly higher after positive as compared to negative index VCE in Eastern studies (OR: 1.77; 95% CI: 1.07-2.94). Application of specific treatment after positive index VCE was associated with lower re-bleeding odds in both Western (OR: 0.37; 95% CI: 0.16-0.87) and Eastern (OR: 0.39; 95% CI: 0.21-0.72) populations.

CONCLUSIONS

Patients undergoing VCE for OGIB have similar re-bleeding rates in the East and the West, regardless of the length of follow-up. However, increased re-bleeding odds after positive index VCE is observed in Eastern studies.

Systematic review and meta-analysis of the performance of nurses in small bowel capsule endoscopy reading

INTRODUCTION

Increasing demands on healthcare systems mean that nurses are taking on more roles as physician extenders. Capsule endoscopy (CE) is a laborious procedure where specialist nurses could reduce physician workload and rationalise resource utilisation. The aim of this review and meta-analysis is to consolidate data on nurses' performance in small bowel CE (SBCE).

MATERIALS AND METHODS

A comprehensive literature search was conducted for randomised controlled trials and comparative studies on nurses in SBCE reading compared to physicians. We examined the performance of nurses compared to SBCE-trained physicians.

RESULTS

Sixteen relevant studies were identified, with 820 SBCE examinations involving 20 nurses. 11/16 studies reported the numbers of SBCE findings detected. Overall, the pooled proportion of all findings reported by physicians and nurses was 86%. Studies involving nurses with endoscopic experience showed a summative detection rate of 89%. 7/16 studies reported the number of videos where there was agreement between the nurse and physicians for overall findings/diagnosis. The overall proportion of videos with agreement was 68%. In studies where nurses had endoscopy experience, the proportion of videos with agreement was 71%.

CONCLUSION

Our meta-analysis supports a more active role for nurses in SBCE reading. We suggest nurses can function as independent CE readers in general, given adequate training and formal credentialing.

A 13-year time trend analysis of 3724 small bowel video capsule endoscopies and a forecast model during the financial crisis in Greece

INTRODUCTION

Since its introduction, small bowel video capsule endoscopy (VCE) use has evolved considerably.

AIM

Evaluation of the temporal changes of small bowel VCE utilization in three tertiary centers in Greece in Era 1 (2002-2009) and Era 2 (2010-2014) and the development a forecast model for future VCE use during 2015-2017.

MATERIALS AND METHODS

Data from all small bowel VCE examinations were retrieved and analyzed in terms of the annual number of the performed examinations, their indications and the significance of their findings.

RESULTS

Overall, we evaluated 3724 VCE examinations. The number of studies peaked in 2009 (n=595) and then decreased to reach 225 in 2014. Overall, more (53.8 vs. 51.4%) patients with iron-deficiency anemia and obscure gastrointestinal bleeding (IDA/OGIB) and fewer (10.7 vs. 14%) patients with chronic diarrhea were evaluated in Era 2 compared with Era 1 (P=0.046). In Era 2, there were more nondiagnostic examinations (39.5 vs. 29.3%, P<0.001), whereas the rate of cases with relevant findings decreased from 47.8 to 40.9%. According to the time trend analysis, we developed a forecast model with two scenarios: the pessimistic and the optimistic. Validation of the model with 2015 data showed that reality was close to the pessimistic scenario: the number of exams further decreased to 190, studies carried out for IDA/OGIB increased to 67%, and there were more negative than positive exams (40.7 vs. 39.2%).

CONCLUSION

The number of VCE studies carried out after the emergence of the financial crisis decreased significantly and VCE indications were optimized. Our forecast model predicts lower numbers of VCE studies, with IDA/OGIB being the dominant indication. However, the predicted increase of negative exams requires further evaluation.

Capsule endoscopy of the small bowel

Capsule endoscopy (CE) is a first line small bowel investigative modality which provides more sensitive mucosal imaging than comparators. It is a non-invasive, non-irradiating tool well tolerated by patients. The risk of retention of the capsule can be minimised by ensuring luminal patency using the Agile patency device. Research continues into how to minimise missed pathology and variability in the identification of pathology or interpretation of images. The consensus is that bowel preparation using laxatives improves visibility and diagnostic yield. Research includes the development of image recognition software, both to eliminate sequentially identical images to improve viewing speed and to select or enhance images likely to represent pathology. However, careful reading by experienced capsule endoscopists remains the benchmark. This should be performed at a speed comfortable to the viewer, probably at a maximum of 15 frames per second. Some prior experience of endoscopy appears to be helpful for novice capsule endoscopists and formal training on a hands-on training course seems to improve pathology recognition, for novices and for those with CE experience.

Impact of the endoscopist's experience on the negative predictive value of capsule endoscopy

INTRODUCTION

The impact of the accumulated experience of the capsule endoscopy (CE) reader on the accuracy of this test is discussed.

AIM

To determine whether the negative predictive value of CE findings changes along the learning curve.

METHODS

We reviewed the first 900 CE read by 3 gastroenterologists experienced in endoscopy over 8 years. These 900 CE were divided into 3 groups (300 CE each): group 1 consisted of the sum of the first 100 CE read by each of the 3 endoscopists; group 2, the sum of the second 100 and groups 3, the sum of the third 100. Patients with normal CE were monitored for at least 28 months to estimate the negative predictive value.

RESULTS

A total of 54 (18%) CE in group 1, 58 (19.3%) in group 2 and 47 (15.6%) in group 3 were normal, although only 34 patients in group 1, 38 in group 2 and 36 in group 3 with normal CE completed follow up and were eventually studied. The negative predictive value was 88.2% in group 1, 89.5% in group 2 and 97% in group 3 (P>.05).

CONCLUSION

The negative predictive value tended to increase, but remained high and did not change significantly after the first 100 when readers are experienced in conventional endoscopy and have preliminary specific training.

Software for enhanced video capsule endoscopy: challenges for essential progress

Video capsule endoscopy (VCE) has revolutionized the diagnostic work-up in the field of small bowel diseases. Furthermore, VCE has the potential to become the leading screening technique for the entire gastrointestinal tract. Computational methods that can be implemented in software can enhance the diagnostic yield of VCE both in terms of efficiency and diagnostic accuracy. Since the appearance of the first capsule endoscope in clinical practice in 2001, information technology (IT) research groups have proposed a variety of such methods, including algorithms for detecting haemorrhage and lesions, reducing the reviewing time, localizing the capsule or lesion, assessing intestinal motility, enhancing the video quality and managing the data. Even though research is prolific (as measured by publication activity), the progress made during the past 5 years can only be considered as marginal with respect to clinically significant outcomes. One thing is clear-parallel pathways of medical and IT scientists exist, each publishing in their own area, but where do these research pathways meet? Could the proposed IT plans have any clinical effect and do clinicians really understand the limitations of VCE software? In this Review, we present an in-depth critical analysis that aims to inspire and align the agendas of the two scientific groups.

Optimizing lesion detection in small-bowel capsule endoscopy: from present problems to future solutions

This review presents issues pertaining to lesion detection in small-bowel capsule endoscopy (SBCE). The use of prokinetics, chromoendoscopy, diagnostic yield indicators, localization issues and the use of 3D reconstruction are presented. The authors also review the current status (and future expectations) in automatic lesion detection software development. Automatic lesion detection and reporting, and development of an accurate lesion localization system are the main software challenges of our time. The 'smart', selective and judicious use (before as well as during SBCE) of prokinetics in combination with other modalities (such as real time and/or purge) improves the completion rate of SBCE. The tracking of the capsule within the body is important for the localization of abnormal findings and planning of further therapeutic interventions. Currently, localization is based on transit time. Recently proposed software and hardware solutions are proposed herein. Moreover, the feasibility of software-based 3D representation (attempt for 3D reconstruction) is examined.

Utility of 3-dimensional image reconstruction in the diagnosis of small-bowel masses in capsule endoscopy (with video)

BACKGROUND

In small-bowel capsule endoscopy (SBCE), differentiating masses (ie, lesions of higher probability for neoplasia) requiring more aggressive intervention from bulges (essentially, false-positive findings) is a challenging task; recently, software that enables 3-dimensional (3D) reconstruction has become available.

OBJECTIVE

To evaluate whether "coupling" 3D reconstructed video clips with the standard 2-dimensional (s2D) counterparts helps in distinguishing masses from bulges.

DESIGN

Three expert and 3 novice SBCE readers, blind to others and in a random order, reviewed the s2D video clips and subsequently the s2D clips coupled with their 3D reconstruction (2D+3D).

SETTING

Multicenter study in 3 community hospitals in Italy and a university hospital in Scotland.

PATIENTS

Thirty-two deidentified 5-minute video clips, containing mucosal bulging (19) or masses (13).

INTERVENTION

3D reconstruction of s2D SBCE video clips.

MAIN OUTCOME MEASURE

Differentiation of masses from bulges with s2D and 2D+3D video clips, estimated by the area under the receiver operating characteristic curve (AUC); interobserver agreement.

RESULTS

AUC for experts and novices for s2D video clips was .74 and .5, respectively (P = .0053). AUC for experts and novices with 2D+3D was .70 (compared with s2D: P = .245) and .57 (compared s2D: P = .049), respectively. AUC for experts and novices with 2D+3D was similar (P = .1846). The interobserver agreement was good for both experts and novices with the s2D (k = .71 and .54, respectively) and the 2D+3D video clips (k = .58 in both groups).

LIMITATIONS

Few, short video clips; fixed angle of 3D reconstruction.

CONCLUSIONS

The adjunction of a 3D reconstruction to the s2D video reading platform does not improve the performance of expert SBCE readers, although it significantly increases the performance of novices in distinguishing masses from bulging.