scholarly journals Multicenter prospective evaluation of the express view reading mode for small-bowel capsule endoscopy studies

2018 ◽  
Vol 06 (05) ◽  
pp. E616-E621 ◽  
Author(s):  
Jean-Christophe Saurin ◽  
Philippe Jacob ◽  
Laurent Heyries ◽  
Christian Pesanti ◽  
Franck Cholet ◽  
...  
Keyword(s):  
Small Bowel ◽  
Capsule Endoscopy ◽  
Reading Time ◽  
High Sensitivity ◽  
Prospective Evaluation ◽  
Precise Location ◽  
The Mean ◽  
Film Reading ◽  
Consensus Reading ◽  
Significant Lesion

Abstract Background Reducing the reading time of capsule endoscopy films is of high priority for gastroenterologists. We report a prospective multicenter evaluation of an “express view” reading mode (Intromedic capsule system). Methods Eighty-three patients with obscure gastrointestinal bleeding were prospectively included in 10 centers. All patients underwent small-bowel capsule endoscopy (Intromedic, Seoul, Republic of Korea). Films were read in standard mode, then a second reading was performed in express view mode at a second center. For each lesion, the precise location, nature, and relevance were collected. A consensus reading and review were done by three experts, and considered to be the gold standard. Results The mean reading time of capsule films was 39.7 minutes (11 – 180 minutes) and 19.7 minutes (4 – 40 minutes) by standard and express view mode, respectively (P < 1 × 10 – 4). The consensus review identified a significant lesion in 44/83 patients (53.0 %). Standard reading and express view reading had a 93.3 % and 82.2 % sensitivity, respectively (NS). Consensus review identified 70 significant images from which standard reading and express view reading detected 58 (82.9 %) and 55 (78.6 %), respectively. The informatics algorithm detected 66/70 images (94.3 %) thus missing four small-bowel angiodysplasia. Conclusion The express view algorithm allows an important shortening of Intromedic capsule film reading time with a high sensitivity.

Mo1206 Detection of Duodenal Papilla and Reading Time Using a New System of Small Bowel Capsule Endoscopy: Performance Comparison of SB2 and SB3

2015 ◽  
Vol 148 (4) ◽  
pp. S-638
Author(s):  
Akiko Shiotani ◽  
Keisuke Honda ◽  
Makiko Kawakami ◽  
Motoyasu Osawa ◽  
Manabu Ishii ◽  
...  
Keyword(s):  
Small Bowel ◽  
Capsule Endoscopy ◽  
Reading Time ◽  
Performance Comparison ◽  
Duodenal Papilla ◽  
New System

Automatic detection of different types of small-bowel lesions on capsule endoscopy images using a newly developed deep convolutional neural network

Endoscopy ◽  
2020 ◽  
Vol 52 (09) ◽  
pp. 786-791 ◽  
Author(s):  
Keita Otani ◽  
Ayako Nakada ◽  
Yusuke Kurose ◽  
Ryota Niikura ◽  
Atsuo Yamada ◽  
...  
Keyword(s):  
Neural Network ◽  
Small Bowel ◽  
Capsule Endoscopy ◽  
Characteristic Curve ◽  
Vascular Lesions ◽  
Single Type ◽  
Data Set ◽  
Normal Tissues ◽  
Computer Aided ◽  
The Mean

Abstract Background Previous computer-aided detection systems for diagnosing lesions in images from wireless capsule endoscopy (WCE) have been limited to a single type of small-bowel lesion. We developed a new artificial intelligence (AI) system able to diagnose multiple types of lesions, including erosions and ulcers, vascular lesions, and tumors. Methods We trained the deep neural network system RetinaNet on a data set of 167 patients, which consisted of images of 398 erosions and ulcers, 538 vascular lesions, 4590 tumors, and 34 437 normal tissues. We calculated the mean area under the receiver operating characteristic curve (AUC) for each lesion type using five-fold stratified cross-validation. Results The mean age of the patients was 63.6 years; 92 were men. The mean AUCs of the AI system were 0.996 (95 %CI 0.992 – 0.999) for erosions and ulcers, 0.950 (95 %CI 0.923 – 0.978) for vascular lesions, and 0.950 (95 %CI 0.913 – 0.988) for tumors. Conclusion We developed and validated a new computer-aided diagnosis system for multiclass diagnosis of small-bowel lesions in WCE images.

scholarly journals PEACE: Perception and Expectations toward Artificial Intelligence in Capsule Endoscopy

2021 ◽  
Vol 10 (23) ◽  
pp. 5708
Author(s):  
Romain Leenhardt ◽  
Ignacio Fernandez-Urien Sainz ◽  
Emanuele Rondonotti ◽  
Ervin Toth ◽  
Cedric Van de Bruaene ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Capsule Endoscopy ◽  
Online Survey ◽  
Reading Time ◽  
General Information ◽  
Care Group ◽  
Complete Replacement ◽  
National Leaders ◽  
The Mean ◽  
Standardize Reporting

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.

scholarly journals P232 In suspected small bowel Crohn’s disease: Clinical impact of using capsule endoscopy to make decisions

2020 ◽  
Vol 14 (Supplement_1) ◽  
pp. S258-S259
Author(s):  
R A Gonzalez ◽  
E J Gómez ◽  
L Pereyra ◽  
J M Mella ◽  
G N Panigadi ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Regression Analysis ◽  
Crohn’S Disease ◽  
Small Bowel ◽  
Crohn's Disease ◽  
Logistic Regression Analysis ◽  
Capsule Endoscopy ◽  
Clinical Impact ◽  
Therapeutic Decisions ◽  
The Mean

Abstract Background Capsule endoscopy (CE) can detect small bowel (SB) lesions compatible of Crohn’s disease (CD) in patients with suggestive symptoms but with inconclusive results for the diagnostic workup. However, the clinical impact of CE in helping physicians to make decisions about patients with suspected CD is not currently well established. The aim of the study was to investigate the clinical impact of CE to confirm diagnosis of CD and also to evaluate whether the results of CE modify therapeutic decisions. Methods We conducted a single-centre retrospective cohort study. All consecutive adult’s patients submitted to CE for clinical suspected of CD, on period November 2012 to November 2018, were included. Data on demography, previous research, medications for IBD, CE procedures and follow-up were analysed. Multivariate logistic regression analysis was carried out to identify predictors of CD. Results A total of 329 CE protocols in adult’s patients were performed over the study period. Ninety were in IBD patients and were included in the analysis 63 CEs submitted for suspected of CD: Clinical suspected CD 54(86%) and colitis unclassified 9 (14%). The mean age was 41 years (range 17–77 years) and 54% were males. The CE reached the caecum in 58 cases (92%) and retention was observed in 5 (8%) with only one patient (1.6%) requiring surgical removal. Overall, 28 of 63 patients (44%) had CE findings consistent with the diagnosis of CD. The lesions identified by CE included ulcers 24 (86%), erythema and villous oedema 17(61%), aphthas and mucosal erosions 5 (18%), stenosis 2 (7%) and were distributed mainly in the distal part of the SB (third tertile) in 23 (82%), but in 14 (50%) cases the proximal SB (first and second tertiles) was also affected. The mean Lewis Score (LS) was 903 (112–4356). Significant inflammatory activity (LS ≥ 135) was detected in 17 (27%) and was moderate or severe (LS &gt; 790) in 7 (11%). CE visualise normal SB mucosa in 34 (54%) of patient’s, which rules out CD. Therapeutic started in 23 (36%) of patients, initiating a new IBD medication in most cases in the 3 months after the CE. On logistic regression analysis, male (p = 0.02) and findings in ileocolonoscopy (p = 0.004) were independents predictors of CD. Conclusion In our cohort, CE in suspected CD confirm diagnosis in 44% of cases. Male gender and findings in ileocolonoscopy appear to be independents predictors of CD. CE is a useful tool in suspected CD, since it adds relevant information for diagnosis and had a great impact on therapeutic decisions.

W1631: Prospective Evaluation of the Reproducibility of Capsule Endoscopy Findings At the Time of Deep Spiral Small Bowel Enteroscopy

2010 ◽  
Vol 71 (5) ◽  
pp. AB377-AB378
Author(s):  
Jonathan M. Buscaglia ◽  
Robert J. Richards ◽  
Joel R. Judah ◽  
Mark N. Wilkinson ◽  
Yvette Lam ◽  
...  
Keyword(s):  
Small Bowel ◽  
Capsule Endoscopy ◽  
Prospective Evaluation

scholarly journals Is It Possible to Predict the Presence of Intestinal Angioectasias?

2014 ◽  
Vol 2014 ◽  
pp. 1-6 ◽  
Author(s):  
Tiago Cúrdia Gonçalves ◽  
Joana Magalhães ◽  
Pedro Boal Carvalho ◽  
Maria João Moreira ◽  
Bruno Rosa ◽  
...  
Keyword(s):  
Gastrointestinal Tract ◽  
Small Bowel ◽  
Gastrointestinal Bleeding ◽  
Predictive Factors ◽  
Capsule Endoscopy ◽  
Diagnostic Tool ◽  
Diagnostic Yield ◽  
Vascular Lesions ◽  
Important Diagnostic Tool ◽  
The Mean

Background and Aim. Angioectasias are the most common vascular anomalies found in the gastrointestinal tract. In small bowel (SB), they can cause obscure gastrointestinal bleeding (OGIB) and in this setting, small bowel capsule endoscopy (SBCE) is an important diagnostic tool. This study aimed to identify predictive factors for the presence of SB angioectasias, detected by SBCE. Methods. We retrospectively analyzed the results of 284 consecutive SBCE procedures between April 2006 and December 2012, whose indication was OGIB, of which 47 cases with SB angioectasias and 53 controls without vascular lesions were selected to enter the study. Demographic and clinical data were collected. Results. The mean age of subjects with angioectasias (70.9±14.7) was significantly higher than in controls (53.1±18.6; P<0.001). The presence of SB angioectasias was significantly higher when the indication for the exam was overt OGIB versus occult OGIB (13/19 versus 34/81, P=0.044). Hypertension and hypercholesterolemia were significantly associated with the presence of SB angioectasias (38/62 versus 9/38, P<0.001 and 28/47 versus 19/53, P=0.027, resp.). Other studied factors were not associated with small bowel angioectasias. Conclusions. In patients with OGIB, overt bleeding, older age, hypercholesterolemia, and hypertension are predictive of the presence of SB angioectasias detected by SBCE, which may be used to increase the diagnostic yield of the SBCE procedure and to reduce the proportion of nondiagnostic examinations.

scholarly journals Safety and Efficacy of Small Bowel Examination by Capsule Endoscopy for Patients before Liver Transplantation

2017 ◽  
Vol 2017 ◽  
pp. 1-6 ◽  
Author(s):  
Kawano Seiji ◽  
Takaki Akinobu ◽  
Iwamuro Masaya ◽  
Yasunaka Tetsuya ◽  
Kono Yoshiyasu ◽  
...  
Keyword(s):  
Liver Transplantation ◽  
Small Bowel ◽  
Transit Time ◽  
Capsule Endoscopy ◽  
High Rate ◽  
Clinical Trial Registry ◽  
Safety And Efficacy ◽  
Red Color ◽  
History Of ◽  
The Mean

Background and Aims. Gastrointestinal surveillance is a requirement prior to liver transplantation (LT), but small intestine examination is not generally undertaken. The aim of the present study was to evaluate the safety and efficacy of capsule endoscopy (CE) for patients with end-stage liver disease.Methods. 31 patients who needed LT were enrolled, and 139 patients who underwent CE over the same period of time acted as controls.Results. Frequency of successful achievement of evaluation of the full length of the small bowel, the mean gastric transit time, and the mean small bowel transit time were not significantly different between the two groups. Abnormalities in the small bowel were found in 26 patients. Comparative analysis revealed that history of EV rupture, history of EV treatment, red color sign of EV, and presence of PHG or HCC were significantly associated with patients with >2 two such findings (high score group).Conclusions. Small bowel examination by CE in patients before liver transplantation could be performed safely and is justified by the high rate of abnormal lesions detected particularly in patients with history of EV therapy or bleeding, red color sign, and presence of PHG or HCC. This study was registered in the UMIN Clinical Trial Registry (UMIN000008672).

A Neural Network-based Algorithm for Assessing the Cleanliness of Small Bowel during Capsule Endoscopy

Endoscopy ◽  
2020 ◽  
Author(s):  
Romain Leenhardt ◽  
Marc Souchaud ◽  
Guy Houist ◽  
Jean-Philippe Le Mouel ◽  
Jean-Christophe Saurin ◽  
...  
Keyword(s):  
Neural Network ◽  
Small Bowel ◽  
Capsule Endoscopy ◽  
Third Generation ◽  
Automatic Assessment ◽  
Point Scale ◽  
Automated Assessment ◽  
Calculation Time ◽  
Highly Sensitive ◽  
The Mean

Background and Aims. Cleanliness scores in small bowel (SB) capsule endoscopy (CE) have poor reproducibility. The aim of this study was to evaluate a neural network (NN)-based algorithm for automated assessment of the SB cleanliness during CE. Methods: First, 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. Results: Using a threshold of 79% adequate still frames per video to achieve the best performance, the algorithm yielded a sensitivity of 90.3%, a specificity of 83.3%, and an accuracy of 89.7%. The reproducibility was perfect. The mean calculation time per video was 3 ± 1 minutes. Conclusion: This NN-based algorithm allowing automatic assessment of SB cleanliness during CE was highly sensitive and paves the way for automated, standardized SBCE reports.

The effect of macrogol administration on the quality of macroscopic images and transit time in canine capsule endoscopy

2014 ◽  
Vol 17 (4) ◽  
pp. 673-679 ◽  
Author(s):  
A. Rychlik ◽  
M. Nowicki ◽  
M. Kander ◽  
M. Szweda
Keyword(s):  
Small Bowel ◽  
Transit Time ◽  
Capsule Endoscopy ◽  
Large Bowel ◽  
Small Bowel Mucosa ◽  
The Mean ◽  
Colonoscopy Preparation ◽  
Mean Time ◽  
Bowel Mucosa

Abstract The present experiment evaluated the quality of macroscopic images and the mean time of capsule passage through different sections of the gastrointestinal tract in dogs subjected to different preparation protocols before capsule endoscopy. In the first examination, the colonoscopy preparation protocol was applied, and in the second examination, the animals were administered macrogol. The study revealed that macrogol administration before capsule endoscopy significantly improved the quality of macroscopic images. The colonoscopy preparation protocol may not support accurate visualization of the large bowel mucosa and, in selected patients, also the small bowel mucosa. Macrogol administration had no effect on capsule transit time through the alimentary canal. Capsules used in endoscopic evaluations of the small bowel in humans may have limited applications in macroscopic examinations of large bowel mucosa in dogs.

Sign in / Sign up

Export Citation Format

Share Document