Small-bowel capsule endoscopy in patients with Meckel's diverticulum: clinical features, diagnostic workup, and findings. A European multicenter I-CARE study.

BACKGROUND AND AIMS: Meckel's diverticulum (MD) may remain silent or be associated with adverse events such as GI bleeding. The main aim of this study was to evaluate indicative small-bowel capsule endoscopy (SBCE) findings, and the secondary aim was to describe clinical presentation in patients with MD. METHODS: This retrospective European multicenter study included patients with MD undergoing SBCE from 2001 until July 2021. RESULTS: Sixty-nine patients with a confirmed MD were included. Median age was 32 years with a male-to-female ratio of approximately 3:1. GI bleeding or iron-deficiency anemia was present in nearly all patients. Mean hemoglobin was 7.63 ± 1.8 g/dL with a transfusion requirement of 52.2%. Typical capsule endoscopy (CE) findings were double lumen (n = 49 [71%]), visible entrance into the MD (n = 49 [71%]), mucosal webs (n = 30 [43.5%]), and bulges (n = 19 [27.5%]). Two or more of these findings were seen in 48 patients (69.6%). Ulcers were detected in 52.2% of patients (n = 36). In 63.8% of patients (n = 44), a combination of double lumen and visible entrance into the MD was evident, additionally revealing ulcers in 39.1% (n = 27). Mean percent SB (small bowel) transit time for the first indicative image of MD was 57% of the total SB transit time. CONCLUSIONS: Diagnosis of MD is rare and sometimes challenging, and a preoperative criterion standard does not exist. In SBCE, the most frequent findings were double-lumen sign and visible diverticular entrance, sometimes together with ulcers.

Feasibility and diagnostic yield of small-bowel capsule endoscopy in patients with surgically altered gastric anatomy: the SAGA study.

BACKGROUND AND AIMS: Little is known about small-bowel (SB) capsule endoscopy (CE) in patients with a history of gastric surgery. This study aims to evaluate the feasibility and diagnostic yield (DY) of orally ingested SB-CE in patients with surgically altered gastric anatomy. METHODS: Twenty-four European centers retrospectively identified patients who had SB-CE after total or subtotal gastrectomy. The primary outcome was the DY of SB-CE (intermediate P1 to highly P2 relevant findings). Secondary outcomes were gastric and SB transit times, completion, cleanliness, and adverse event rates. RESULTS: Studied were 248 procedures from 243 patients (mean age, 62 years) with a history of partial gastrectomy (Billroth I, 13.1%; Billroth II, 34.6%), total gastrectomy (7.4%), Whipple procedure (12.8%), sleeve gastrectomy (7.2%), or gastric bypass surgery (24.7%). Obscure GI bleeding was the most frequent indication (85.1%). SB completion rate was 84.3%. One capsule retention in the SB was noted (adverse event rate, .4%). Median SB transit time was 286 minutes (interquartile range [235; 387]). Cleanliness was rated as adequate in 92.1% of procedures. After exclusion of abnormalities found at the upper anastomotic site, the DY was 43.6%, with inflammatory/ulcerated lesions observed more frequently (23.4%) than vascular lesions (21.0%). CONCLUSIONS: SB-CE seems to be feasible and safe in selected patients with a history of major gastric surgery and comes with a high DY. The spectrum of abnormal SB findings in these patients may be different from what is known from the literature in nonoperated patients.

A neural network-based algorithm for assessing the cleanliness of small bowel during capsule endoscopy.

BACKGROUND: Cleanliness scores in small-bowel capsule endoscopy (SBCE) have poor reproducibility. The aim of this study was to evaluate a neural network-based algorithm for automated assessment of small-bowel cleanliness during capsule endoscopy. METHODS: 600 normal third-generation SBCE still frames were categorized as "adequate" or "inadequate" in terms of cleanliness by three expert readers, according to a 10-point scale, and served as a training database. Then, 156 third-generation SBCE recordings were categorized in a consensual manner as "adequate" or "inadequate" in terms of cleanliness; this testing database was split into two independent 78-video subsets for the tuning and evaluation of the algorithm, respectively. RESULTS: Using a threshold of 79 % "adequate" still frames per video to achieve the best performance, the algorithm yielded a sensitivity of 90.3 %, specificity of 83.3 %, and accuracy of 89.7 %. The reproducibility was perfect. The mean calculation time per video was 3 (standard deviation 1) minutes. CONCLUSION: This neural network-based algorithm allowing automatic assessment of small-bowel cleanliness during capsule endoscopy was highly sensitive and paves the way for automated, standardized SBCE reports.

A neural network algorithm for detection of GI angiectasia during small-bowel capsule endoscopy.

BACKGROUND AND AIMS: GI angiectasia (GIA) is the most common small-bowel (SB) vascular lesion, with an inherent risk of bleeding. SB capsule endoscopy (SB-CE) is the currently accepted diagnostic procedure. The aim of this study was to develop a computer-assisted diagnosis tool for the detection of GIA. METHODS: Deidentified SB-CE still frames featuring annotated typical GIA and normal control still frames were selected from a database. A semantic segmentation images approach associated with a convolutional neural network (CNN) was used for deep-feature extractions and classification. Two datasets of still frames were created and used for machine learning and for algorithm testing. RESULTS: The GIA detection algorithm yielded a sensitivity of 100%, a specificity of 96%, a positive predictive value of 96%, and a negative predictive value of 100%. Reproducibility was optimal. The reading process for an entire SB-CE video would take 39 minutes. CONCLUSIONS: The developed CNN-based algorithm had high diagnostic performances, allowing detection of GIA in SB-CE still frames. This study paves the way for future automated CNN-based SB-CE reading softwares.

Artificial Intelligence-assisted Analysis of Pan-enteric Capsule Endoscopy in Patients with Suspected Crohn's Disease: A Study on Diagnostic Performance.

BACKGROUND AND AIM: Pan-enteric capsule endoscopy [PCE] is a highly sensitive but time-consuming tool for detecting pathology. Artificial intelligence [AI] algorithms might offer a possibility to assist in the review and reduce the analysis time of PCE. This study examines the agreement between PCE assessments aided by AI technology and standard evaluations, in patients suspected of Crohn's disease [CD]. METHOD: PCEs from a prospective, blinded, multicentre study, including patients suspected of CD, were processed by the deep learning solution AXARO® [Augmented Endoscopy, Paris, France]. Based on the image output, two observers classified the patient's PCE as normal or suggestive of CD, ulcerative colitis, or cancer. The primary outcome was per-patient sensitivities and specificities for detecting CD and inflammatory bowel disease [IBD]. Complete reading of PCE served as the reference standard. RESULTS: A total of 131 patients' PCEs were analysed, with a median recording time of 303 min. The AXARO® framework reduced output to a median of 470 images [2.1%] per patient, and the pooled median review time was 3.2 min per patient. For detecting CD, the observers had a sensitivity of 96% and 92% and a specificity of 93% and 90%, respectively. For the detection of IBD, both observers had a sensitivity of 97% and had a specificity of 91% and 90%, respectively. The negative predictive value was 95% for CD and 97% for IBD. CONCLUSIONS: Using the AXARO® framework reduced the initial review time substantially while maintaining high diagnostic accuracy-suggesting its use as a rapid tool to rule out IBD in PCEs of patients suspected of Crohn's disease.

Features of colorectal adenomas among young patients with Lynch syndrome according to path_MMR: Results from the PRED-IdF registry.

BACKGROUND: Lynch syndrome (LS) is the most frequent inherited colorectal cancer syndrome. AIM: To assess the burden of adenoma in LS patients under 50 years-old followed in the PRED-IdF network. METHODS: From January 2010 to January 2019, all patients under 50 years of age with a confirmed LS germline mutation were included. The main objective was the description of adenomas characteristics according to path_MMR. RESULTS: We analyzed data from 708 patients (mean age 34.8 ± 8.6), of which 41.8 % were male. Among these patients, 37.6% had path_MLH1, 45.4% path_MSH2, 13.9% path_MSH6, 2.9% path_PMS2, and 1.2% path_EpCAM. The analysis included 1721 (70.9%) follow-up colonoscopies. A total of 682 adenomas were detected, including 140 (20.5%) advanced adenomas. The adenoma detection rates during the first and follow-up colonoscopies were 19.2% and 20.5%, respectively. Most adenomas were <10 mm (57.9%), located in the proximal colon (334, 48.9%), and presented as non-polypoid lesions (493, 72.3%). The median growth time for adenomas was 23 months (range 9-114) irrespective of the path_MMR mutation (p = 0.62). CONCLUSION: LS patients under 50 years of age have a high burden of adenomas, particularly small non-polypoid adenomas located in the proximal colon. These results highlight the need for intensive screening, with a particular focus on the proximal colon.

ERCP 2.0: Biliary 3D-reconstruction in patients with malignant hilar stricture.

BACKGROUND: Endoscopic retrograde cholangiopancreatography (ERCP) for malignant hilar strictures is challenging. The correlation between Magnetic resonance cholangiopancreatography (MRCP) and per ERCP 2D fluoroscopic images is not obvious. The aim of this study was to evaluate the feasibility and potential usefulness of MRCP-based handmade biliary 3D reconstruction in this setting. METHODS: Methods Patients who underwent MRCP followed by ERCP for biliary drainage of a malignant hilar stricture at our institution between 2018 and 2020 were reviewed. A handmade 3D segmentation using 3D slicer© (Kitware, France) was fashioned and reviewed with an expert radiologist. The primary outcome was the feasibility of biliary segmentation. RESULTS: A total of 16 patients were included. The mean age was 70.1 (+/- 8.6) years-old and 68.8% had hilar cholangiocarcinoma. Handmade segmentation was successful in all cases. The agreement between the MRCP interpretation and the 3D reconstruction was 37.5%, as per the Bismuth classification. 3D reconstruction available prior to ERCP could have helped guide for better stent placement in 11 cases (68.8%). CONCLUSIONS: MRCP-based biliary 3D segmentation-reconstruction, in patients with malignant hilar stricture is feasible and seems to provide a better anatomical understanding compared to MRCP and could help improve endoscopic management.

Where does capsule endoscopy fit in the diagnostic algorithm of small bowel intussusception?

INTRODUCTION: The investigation of small bowel (SB) intussusception is variable, reflecting the lack of existing standards. The aim of this study was to understand the role of small bowel capsule endoscopy (SBCE) to investigate this pathology. METHODOLOGY: This was a retrospective multi-centre study. Patients with intussusception on SBCE and those where SBCE was carried out due to findings of intussusception on radiological investigations were included. Relevant information was collected. RESULTS: Ninety-five patients (median age 39+/-SD19.1 years, IQR 30) were included. Radiological investigations were carried out in 71 patients (74.7%) prior to SBCE with intussusception being present in 60 patients on radiological investigations (84.5%). Thirty patients (42.2%) had intussusception on radiological investigations followed by a normal SBCE. Ten patients (14.1%) had findings of intussusception on radiological investigations, a normal SBCE and repeat radiological investigations that were also normal. Abnormal findings were noted on SBCE that could explain intussusception on imaging in (16 patients) 22.5% of patients. Five patients (5.3%) underwent radiological investigations and SBCE to investigate coeliac disease and intussusception. None had associated malignancy. Four patients (4.2%) underwent SBCE to investigate familial polyposis syndromes and went on to SB enteroscopy and surgery accordingly. Most patients (n = 14; 14.8%) with intussusception on initial SBCE (without prior radiological imaging) had suspected SB bleeding (n = 10, 10.5%). Four patients (4.2%) had additional findings of a mass on CT scan and went on to have surgery. CONCLUSION: SBCE should be used to complement radiology when investigating intussusception. It is a safe non-invasive test that will minimise unnecessary surgery. Additional radiological investigations following a negative SBCE in cases of intussusception noted on initial radiological investigations are unlikely to yield positive findings. Radiological investigations following intussusception noted on SBCE in case of patients presenting with obscure gastrointestinal bleeding, may yield additional findings.

Evaluation by a Machine Learning System of Two Preparations for Small Bowel Capsule Endoscopy: The BUBS (Burst Unpleasant Bubbles with Simethicone) Study.

Background: Bubbles often mask the mucosa during capsule endoscopy (CE). Clinical scores assessing the cleanliness and the amount of bubbles in the small bowel (SB) are poorly reproducible unlike machine learning (ML) solutions. We aimed to measure the amount of bubbles with ML algorithms in SB CE recordings, and compare two polyethylene glycol (PEG)-based preparations, with and without simethicone, in patients with obscure gastro-intestinal bleeding (OGIB). Patients & Methods: All consecutive outpatients with OGIB from a tertiary care center received a PEG-based preparation, without or with simethicone, in two different periods. The primary outcome was a difference in the proportions (%) of frames with abundant bubbles (>10%) along the full-length video sequences between the two periods. SB CE recordings were analyzed by a validated computed algorithm based on a grey-level of co-occurrence matrix (GLCM), to assess the abundance of bubbles in each frame. Results: In total, 105 third generation SB CE recordings were analyzed (48 without simethicone and 57 with simethicone-added preparations). A significant association was shown between the use of a simethicone-added preparation and a lower abundance of bubbles along the SB (p = 0.04). A significantly lower proportion of "abundant in bubbles" frames was observed in the fourth quartile (30.5% vs. 20.6%, p = 0.02). There was no significant impact of the use of simethicone in terms of diagnostic yield, SB transit time and completion rate. Conclusion: An accurate and reproducible computed algorithm demonstrated significant decrease in the abundance of bubbles along SB CE recordings, with a marked effect in the last quartile, in patients for whom simethicone had been added in PEG-based preparations, compared to those without simethicone.

Key research questions for implementation of artificial intelligence in capsule endoscopy.

Background: Artificial intelligence (AI) is rapidly infiltrating multiple areas in medicine, with gastrointestinal endoscopy paving the way in both research and clinical applications. Multiple challenges associated with the incorporation of AI in endoscopy are being addressed in recent consensus documents. Objectives: In the current paper, we aimed to map future challenges and areas of research for the incorporation of AI in capsule endoscopy (CE) practice. Design: Modified three-round Delphi consensus online survey. Methods: The study design was based on a modified three-round Delphi consensus online survey distributed to a group of CE and AI experts. Round one aimed to map out key research statements and challenges for the implementation of AI in CE. All queries addressing the same questions were merged into a single issue. The second round aimed to rank all generated questions during round one and to identify the top-ranked statements with the highest total score. Finally, the third round aimed to redistribute and rescore the top-ranked statements. Results: Twenty-one (16 gastroenterologists and 5 data scientists) experts participated in the survey. In the first round, 48 statements divided into seven themes were generated. After scoring all statements and rescoring the top 12, the question of AI use for identification and grading of small bowel pathologies was scored the highest (mean score 9.15), correlation of AI and human expert reading-second (9.05), and real-life feasibility-third (9.0). Conclusion: In summary, our current study points out a roadmap for future challenges and research areas on our way to fully incorporating AI in CE reading.

Nomenclature and Definition of Atrophic Lesions in Small Bowel Capsule Endoscopy: A Delphi Consensus Statement of the International CApsule endoscopy REsearch (I-CARE) Group.

(1) Background: Villous atrophy is an indication for small bowel capsule endoscopy (SBCE). However, SBCE findings are not described uniformly and atrophic features are sometimes not recognized; (2) Methods: The Delphi technique was employed to reach agreement among a panel of SBCE experts. The nomenclature and definitions of SBCE lesions suggesting the presence of atrophy were decided in a core group of 10 experts. Four images of each lesion were chosen from a large SBCE database and agreement on the correspondence between the picture and the definition was evaluated using the Delphi method in a broadened group of 36 experts. All images corresponded to histologically proven mucosal atrophy; (3) Results: Four types of atrophic lesions were identified: mosaicism, scalloping, folds reduction, and granular mucosa. The core group succeeded in reaching agreement on the nomenclature and the descriptions of these items. Consensus in matching the agreed definitions for the proposed set of images was met for mosaicism (88.9% in the first round), scalloping (97.2% in the first round), and folds reduction (94.4% in the first round), but granular mucosa failed to achieve consensus (75.0% in the third round); (4) Conclusions: Consensus among SBCE experts on atrophic lesions was met for the first time. Mosaicism, scalloping, and folds reduction are the most reliable signs, while the description of granular mucosa remains uncertain.

Prospective evaluation of third-generation small bowel capsule endoscopy videos by independent readers demonstrates poor reproducibility of cleanliness classifications.

OBJECTIVE: The detection of lesions during small bowel (SB) capsule endoscopy (CE) depends on the cleanliness of the intestine. Quality reporting and comparison of different preparation methods require reliable scores. Three scores known as quantitative index (QI), qualitative evaluation (QE), and overall adequacy assessment (OAA), have been proposed to assess SB cleanliness, and are sometimes used in clinical practice and in clinical trials. However, none of these scores has received any external validation. The aim of our study was to re-assess the reproducibility of these three specific scores. METHODS: One-hundred-and-fifty-five complete third-generation SB-CE video recordings were extracted from a multicenter randomized controlled trial (PREPINTEST) which evaluated three modalities of SB preparation for CE. Three experts independently read the 155 SB-CE video recordings twice, in a random order, over 48 -h periods at 6-week intervals, using the QI, QE and OAA scores. Cohen's linearly weighted kappa coefficients were calculated to assess intra-observer and inter-observer agreements. RESULTS: Intra-observer reproducibility was fair to moderate, with kappa coefficients between 0.37 and 0.46 for QI, 0.41 and 0.51 for QE, 0.41 and 0.50 for OAA. Inter-observer reproducibility was fair to substantial according to kappa coefficients between experts varying from 0.40 to 0.64, 0.29 to 0.65, and 0.52 to 0.71, for QI, QE and OAA, respectively. CONCLUSIONS: QI, QE and OAA scores, currently used for evaluation of the quality of the preparation of SB-CE, are not sufficiently reproducible. Other scores or methods are therefore needed for SB-CE cleanliness assessment.

PEACE: Perception and Expectations toward Artificial Intelligence in Capsule Endoscopy.

Artificial intelligence (AI) has shown promising results in digestive endoscopy, especially in capsule endoscopy (CE). However, some physicians still have some difficulties and fear the advent of this technology. We aimed to evaluate the perceptions and current sentiments toward the use of AI in CE. An online survey questionnaire was sent to an audience of gastroenterologists. In addition, several European national leaders of the International CApsule endoscopy REsearch (I CARE) Group were asked to disseminate an online survey among their national communities of CE readers (CER). The survey included 32 questions regarding general information, perceptions of AI, and its use in daily life, medicine, endoscopy, and CE. Among 380 European gastroenterologists who answered this survey, 333 (88%) were CERs. The mean average time length of experience in CE reading was 9.9 years (0.5-22). A majority of CERs agreed that AI would positively impact CE, shorten CE reading time, and help standardize reporting in CE and characterize lesions seen in CE. Nevertheless, in the foreseeable future, a majority of CERs disagreed with the complete replacement all CE reading by AI. Most CERs believed in the high potential of AI for becoming a valuable tool for automated diagnosis and for shortening the reading time. Currently, the perception is that AI will not replace CE reading.

A multisystem-compatible deep learning-based algorithm for detection and characterization of angiectasias in small-bowel capsule endoscopy. A proof-of-concept study.

BACKGROUND AND AIMS: Current artificial intelligence (AI)-based solutions for capsule endoscopy (CE) interpretation are proprietary. We aimed to evaluate an AI solution trained on a specific CE system (Pillcam®, Medtronic) for the detection of angiectasias on images captured by a different proprietary system (MiroCam®, Intromedic). MATERIAL AND METHODS: An advanced AI solution (Axaro®, Augmented Endoscopy), previously trained on Pillcam® small bowell images, was evaluated on independent datasets with more than 1200 Pillcam® and MiroCam® still frames (equally distributed, with or without angiectasias). Images were reviewed by experts before and after AI interpretation. RESULTS: Sensitivity for the diagnosis of angiectasia was 97.4% with Pillcam® images and 96.1% with Mirocam® images, with specificity of 98.8% and 97.8%, respectively. Performances regarding the delineation of regions of interest and the characterization of angiectasias were similar in both groups (all above 95%). Processing time was significantly shorter with Mirocam® (20.7 ms) than with Pillcam® images (24.6 ms, p<0.0001), possibly related to technical differences between systems. CONCLUSION: This proof-of-concept study on still images paves the way for the development of resource-sparing, "universal" CE databases and AI solutions for CE interpretation.

Poor Quality of Small Bowel Capsule Endoscopy Images Has a Significant Negative Effect in the Diagnosis of Small Bowel Malignancy.

BACKGROUND AND AIMS: Capsule endoscopy (CE) is a visual modality; hence, diagnosis relies on image quality. We studied the contribution of image parameters to visualization quality and their effect on diagnostic certainty of small bowel (SB) lesions. METHODS: Five clear CE images of common SB pathology - two vascular lesions, two inflammatory, one polyp - were processed for three image parameters to simulate poor SB conditions: opacity (color-matched to luminal content; 10-90%, 10% increments); blurriness (radius 1-10 pixels; one pixel increments); and contrast (-50-50%; 10% increments). Nine expert readers evaluated whether images were adequate for diagnosis. Points where perception of image quality changed significantly were determined for each parameter. Three further sets of SBCE images (vascular, inflammatory, and neoplastic lesions; nine images/set) were processed for four points/parameters. Twenty experienced/expert CE readers reviewed these images. RESULTS: The negative effects of opacity in diagnostic certainty were mostly evident in images of neoplasia; images of vascular and inflammatory lesions were less affected. Similar results were observed with increasing blur radius, simulating movement, and poor focus. The proportions of readers finding vascular and inflammatory images adequate for diagnosis did not drop significantly at wider blur radii, while images of neoplasia were quickly deemed inadequate. Low contrast had a greater negative effect than high, most consistently in neoplastic lesions. CONCLUSION: Poor visualization quality in all parameters affected mostly neoplastic lesions. Software to increase contrast and sharpen images can improve visualization quality; smart frame rate adaptation could improve the number of high-quality frames obtained. Thoroughness in SB cleansing is most important when there is a suspicion of neoplasia.

CAD-CAP: a 25,000-image database serving the development of artificial intelligence for capsule endoscopy.

Background and study aims Capsule endoscopy (CE) is the preferred method for small bowel (SB) exploration. With a mean number of 50,000 SB frames per video, SBCE reading is time-consuming and tedious (30 to 60 minutes per video). We describe a large, multicenter database named CAD-CAP (Computer-Assisted Diagnosis for CAPsule Endoscopy, CAD-CAP). This database aims to serve the development of CAD tools for CE reading. Materials and methods Twelve French endoscopy centers were involved. All available third-generation SB-CE videos (Pillcam, Medtronic) were retrospectively selected from these centers and deidentified. Any pathological frame was extracted and included in the database. Manual segmentation of findings within these frames was performed by two pre-med students trained and supervised by an expert reader. All frames were then classified by type and clinical relevance by a panel of three expert readers. An automated extraction process was also developed to create a dataset of normal, proofread, control images from normal, complete, SB-CE videos. Results Four-thousand-one-hundred-and-seventy-four SB-CE were included. Of them, 1,480 videos (35 %) containing at least one pathological finding were selected. Findings from 5,184 frames (with their short video sequences) were extracted and delimited: 718 frames with fresh blood, 3,097 frames with vascular lesions, and 1,369 frames with inflammatory and ulcerative lesions. Twenty-thousand normal frames were extracted from 206 SB-CE normal videos. CAD-CAP has already been used for development of automated tools for angiectasia detection and also for two international challenges on medical computerized analysis.