Development of a deep learning-based software for calculating cleansing score in small bowel capsule endoscopy.
Ontology highlight
ABSTRACT:
SUBMITTER: Nam JH
PROVIDER: S-EPMC7904767 | biostudies-literature | 2021 Feb
REPOSITORIES: biostudies-literature
Publications
Development of a deep learning-based software for calculating cleansing score in small bowel capsule endoscopy.
Nam Ji Hyung JH Hwang Youngbae Y Oh Dong Jun DJ Park Junseok J Kim Ki Bae KB Jung Min Kyu MK Lim Yun Jeong YJ
Scientific reports 20210224 1
A standardized small bowel (SB) cleansing scale is currently not available. The aim of this study was to develop an automated calculation software for SB cleansing score using deep learning. Consecutively performed capsule endoscopy cases were enrolled from three hospitals. A 5-step scoring system based on mucosal visibility was trained for deep learning in the training set. Performance of the trained software was evaluated in the validation set. Average cleansing score (1.0 to 5.0) by deep lear ...[more]
Similar Datasets
Project description:Capsule endoscopy (CE) enables evaluation of the entire mucosal surface of the small bowel (SB), which is one of the most important steps for evaluating obscure gastrointestinal bleeding. Although the diagnostic yield of SB CE depends on many clinical factors, there are no reports on quality indicators. Thus, the Korean Gut Image Study Group (KGISG) publishes an article titled, "Quality Indicators for Small Bowel Capsule Endoscopy" under approval from the Korean Society of Gastrointestinal Endoscopy (KSGE). Herein, we initially identified process quality indicators, while the structural and outcome indicators are reserved until sufficient clinical data are accumulated. We believe that outcomes of SB CE can be improved by trying to meet our proposed quality indicators.
| S-EPMC5398361 | biostudies-literature
Project description:Small bowel capsule endoscopy is considered a first-line diagnostic tool for the investigation of small bowel diseases. Gastroenterological and endoscopic societies have proposed and established measures known as quality indicators, quality measures or performance measures for the majority of endoscopic procedures, in order to ensure competence, healthcare quality and define areas requiring improvement. However, there is a paucity of publications describing small bowel capsule endoscopy quality indicators. Hereby, we attempt to identify and describe a number of pre-procedure, intra-procedure and post-procedure quality indicators, regarding process measures in small bowel capsule endoscopy, after a comprehensive review of the literature.
| S-EPMC6064801 | biostudies-literature
Project description:ObjectiveIntestinal motility may be different in obese and nonobese patients, but this has not been determined. Here, we sought to evaluate the effect of obesity on small bowel capsule endoscopy (SBCE). Patients and Methods. We retrospectively analyzed the cases of the 340 patients who underwent SBCE for small intestinal disease (excluding cases of unobservable total small bowel, small bowel stenosis, and bowel resection) at our hospital during the period January 2014 to December 2020 to extract patient background factors and the bowel transit times of SBCE according to the presence/absence of obesity (defined as a body mass index (BMI) ≥ 25 kg/m2).ResultsThe obese group was 54 patients (nonobese, n = 286). The small bowel transit time (SBTT) was significantly shorter in the obese patients compared to the nonobese patients (p = 0.0026), and when we divided the patients by their short/long SBTTs using 216.5 min as the cutoff, we observed significant between-group differences in the patients' age (≥60 years) and in the patients' hospitalization status at the time of the SBCE examination. A multivariate analysis revealed that hospitalized status at the examination is a factor contributing significantly to a long SBTT (OR 0.25, 95% CI: 0.15-0.42, p < 0.0001). An analysis using the outpatient/inpatient conditions showed that obesity was an independent factor in the inpatient status at the SBCE examination with a significant short SBTT (OR 2.91, 95% CI: 1.06-7.97, p = 0.0380). Constipation at the examination was also a factor contributing to a long SBTT (OR 0.26, 95% CI: 0.07-0.99, p = 0.0493).ConclusionThe SBTT of the SBCE was significantly shorter in the obese patients. This tendency was especially evident in the hospitalized state.
| S-EPMC9112179 | biostudies-literature
Project description:IntroductionSmall bowel (SB) capsule endoscopy (SBCE) is a sensitive modality for screening the entire SB of patients with Crohn's disease (CD); however, the prognostic impact of the results is unclear. We evaluated the ability of the SBCE score to predict therapeutic intervention for patients with CD and SB lesions without clinical symptoms as well as negative C-reactive protein (CRP) levels.MethodsFifty-six patients who underwent a patency evaluation and had a CD activity index (CDAI) score <150 mg/dL and CRP level <0.5 mg/dL were included. Twenty-one and 35 patients had CD classified as Montreal classifications L1 and L3, respectively. The initial SBCE scores were subsequently grouped according to the presence or absence of intervention based on cutoff values. We examined whether the scores could predict the need for therapeutic intervention at 1 year, 2 years, and 5 years. The CD activity in capsule endoscopy (CDACE) score was used as the SBCE score.ResultsThe median observation period was 1,326 days. Twenty-one patients received therapeutic intervention. There were significant differences between patients with and without treatment intervention according to the CDACE cutoff value of 420 at 1 year, 2 years, and 5 years. Significant differences between patients with Montreal classification L1 with and without intervention were observed at 1 year and 2 years. The CDACE score was moderately and strongly correlated with the Lewis score and capsule endoscopy CDAI score, respectively (Spearman rank correlation coefficient: ρ = 0.6462 and ρ = 0.9199, respectively; p < 0.0001).ConclusionA CDACE score ≥420 is predictive of intervention after 1 year for patients with CD, a CDAI score <150, and a CRP level <0.5 mg/dL. A larger study with a prospective design is necessary to validate our findings.
| S-EPMC11249762 | biostudies-literature
Project description:Background and study aims Small bowel ulcerations are efficiently detected with deep learning techniques, whereas the ability to diagnose Crohn's disease (CD) in the colon with it is unknown. This study examined the ability of a deep learning framework to detect CD lesions with pan-enteric capsule endoscopy (CE) and classify lesions of different severity. Patients and methods CEs from patients with suspected or known CD were included in the analysis. Two experienced gastroenterologists classified anonymized images into normal mucosa, non-ulcerated inflammation, aphthous ulceration, ulcer, or fissure/extensive ulceration. An automated framework incorporating multiple ResNet-50 architectures was trained. To improve its robustness and ability to characterize lesions, image processing methods focused on texture enhancement were employed. Results A total of 7744 images from 38 patients with CD were collected (small bowel 4972, colon 2772) of which 2748 contained at least one ulceration (small bowel 1857, colon 891). With a patient-dependent split of images for training, validation, and testing, ulcerations were diagnosed with a sensitivity, specificity, and diagnostic accuracy of 95.7 % (CI 93.4-97.4), 99.8 % (CI 99.2-100), and 98.4 % (CI 97.6-99.0), respectively. The diagnostic accuracy was 98.5 % (CI 97.5-99.2) for the small bowel and 98.1 % (CI 96.3-99.2) for the colon. Ulcerations of different severities were classified with substantial agreement (κ = 0.72). Conclusions Our proposed framework is in excellent agreement with the clinical standard, and diagnostic accuracies are equally high for the small bowel and colon. Deep learning approaches have a great potential to help clinicians detect, localize, and determine the severity of CD with pan-enteric CE.
| S-EPMC8367448 | biostudies-literature
Project description:Delayed gastric emptying is a significant factor in incomplete small bowel capsule examinations. Gastric transit could be hastened by external magnetic control of the capsule. We studied the feasibility of this approach to improve capsule endoscopy completion rates.Prospective, single-center, randomized controlled trial involving 122 patients attending for small bowel capsule endoscopy using MiroCam Navi. Patients were randomized to either the control group (mobilisation for 30 minutes after capsule ingestion, followed by intramuscular metoclopramide 10 mg if the capsule failed to enter the small bowel) or the intervention group (1000 mL of water prior to capsule ingestion, followed by positional change and magnetic steering). Outcome measures were capsule endoscopy completion rate, gastric clarity and distention, relationship of body habitus to capsule endoscopy completion rate (CECR), and patient comfort scores.122 patients were recruited (61 each to the control and intervention groups: mean age 49 years [range 21 - 85], 61 females). There was no significant difference in CECR between the two groups (P = 0.39). Time to first pyloric image was significantly shorter in the intervention group (P = 0.03) but there was no difference in gastric transit times (P = 0.12), suggesting that magnetic control hastens capsular transit to the gastric antrum but does not influence duodenal passage. Gastric clarity and distention were significantly better in the intervention group (P < 0.0001 and P < 0.0001 respectively).Magnetic steering of a small bowel capsule is unable to overcome pyloric contractions to enhance gastric emptying and improve capsule endoscope completion rate. Excellent mucosal visualisation within the gastric cavity suggests this technique could be harnessed for capsule examination of the stomach.
| S-EPMC4751924 | biostudies-other
Project description:AimsWireless capsule endoscopy (WCE) and magnetic resonance enterography (MRE) are increasingly utilized to evaluate the small bowel (SB) in Crohn's disease (CD). The primary aims were to compare the ability of WCE and MRE to detect SB inflammation in children with newly diagnosed CD, and in the terminal ileum (TI) to compare them to ileo-colonoscopy. Secondary aims were to compare diagnostic accuracy of WCE and MRE and changes in Paris classification after each study.MethodsPatients (10 to 17 years of age) requiring ileo-colonoscopy for suspected CD were invited to participate. Only patients with endoscopic/histologic evidence of CD underwent MRE and WCE. SB inflammation and extent were documented and comparative analyses performed.ResultsOf 38 initially recruited subjects, 20 completed the study. WCE and MRE were similarly sensitive in identifying active TI inflammation (16 [80%] versus 12 [60%]) and any SB inflammation (17 [85%] versus 16 [80%]). However, WCE detected more extensive SB disease than MRE with active inflammation throughout the SB in 15 [75%] versus 1 [5%] patient (P < 0.001). Moreover, WCE was more likely to detect proximal SB disease (jejunum and ileum) compared to MRE (85% versus 50%, P = 0.04). Overall, the Paris classification changed in 65% and 85% of patients following MRE and WCE, respectively.ConclusionsWCE is as sensitive as MRE for identifying active TI inflammation, but appears more sensitive in identifying more proximal SB inflammation. In the absence of concern regarding stricturing or extra-luminal disease WCE can be considered for the evaluation of suspected SB CD.
| S-EPMC7678730 | biostudies-literature
Project description:Three-dimensional (3D) reconstruction of capsule endoscopic images has been attempted for a long time to obtain more information on small bowel structures. Due to the limited hardware resources of capsule size and battery capacity, software approaches have been studied but have mainly exhibited inherent limitations. Recently, stereo camera-based capsule endoscopy, which can perform hardware-enabled 3D reconstruction, has been developed. We aimed to evaluate the feasibility of newly developed 3D capsule endoscopy in clinical practice. This study was a prospective, single-arm, feasibility study conducted at two university-affiliated hospitals in South Korea. Small bowel evaluation was performed using a newly developed 3D capsule endoscope for patients with obscure gastrointestinal bleeding, suspected or established Crohn's disease, small bowel tumors, and abdominal pain of unknown origin. We assessed the technical limitations, performance, and safety of the new capsule endoscope. Thirty-one patients (20 men and 11 women; mean age: 44.5 years) were enrolled. There was no technical defect preventing adequate visualization of the small bowel. The overall completion rate was 77.4%, the detection rate was 64.5%, and there was no capsule retention. All capsule endoscopic procedures were completed uneventfully. In conclusion, newly developed 3D capsule endoscopy was safe and feasible, showing similar performance as conventional capsule endoscopy. Newly added features of 3D reconstruction and size measurement are expected to be useful in the characterization of subepithelial tumours.
| S-EPMC7138835 | biostudies-literature
Project description:Background and study aims Capsule endoscopy (CE) has transformed examination of the small bowel (SB), once considered a dark continent. The present study aimed to describe the indications, diagnostic yield, practical issues and complications of CE in one of the largest tertiary center in India. Patients and methods This retrospective analysis from a prospectively maintained database, conducted from January 2013 to June 2021 included 1155 CEs performed during this period. Patient medical records were reviewed for indications, results, and complications of CE. Results A total of 1154 patients (809 males and 345 females), mean age 53 years (range 6-87 years), one capsule got stuck in the esophagus, were included in the study. Active SB bleeding had no effect on SB transit time (324.7±161 minutes, n = 137 patients with active bleed vs 310.6±166.9 minutes, n = 1017 patients without active bleed; P = 0.35). The indication and diagnostic yield (DY) of CE were potential overt SB bleed (68.6% & 43.9%), potential occult SB bleed (8.2% and 40%), chronic diarrhea (7.9% and 28.4%), abdominal pain (6.5% and 21.3%), anemia (5.9% and 57.9%), and suspected/known case of Crohn's disease (2.3% & 56.5%) respectively. The DY for patients with age ≥60 years was similar to those with age < 60 years (61.9% vs. 51.8% respectively; P = 0.4). 21 patients (1.8%) had capsule retention of which six (0.5%) had to be referred for surgery. Conclusions CE is a safe and effective investigation with ever increasing range of indications. Potential SB bleed remains the most common indication for CE with high detection rate.
| S-EPMC10442921 | biostudies-literature
Project description:BackgroundCapsule endoscopy (CE) is frequently hindered by intra-luminal debris. Our aim was to determine whether a combination bowel preparation would improve small-bowel visualization, diagnostic yield, and the completion rate of CE.MethodsSingle-blind, prospective randomized-controlled study of outpatients scheduled for CE. Bowel-preparation subjects ingested 2 L of polyethylene glycol solution the night prior to CE, 5 mL simethicone and 5 mg metoclopramide 20 minutes prior to CE and laid in the right lateral position 30 minutes after swallowing CE. Controls had no solid food after 7 p.m. the night prior to CE and no liquids 4 hours prior to CE. Participants completed a satisfaction survey. Capsule readers completed a small-bowel-visualization assessment.ResultsFifty patients were prospectively enrolled (56% female) with a median age of 54.4 years and 44 completed the study (23 patients in the control group and 21 in the preparation group). There was no significant difference between groups on quartile-based small-bowel visualization (all P > 0.05). There was no significant difference between groups in diagnostic yield (P = 0.69), mean gastric (P = 0.10) or small-bowel transit time (P = 0.89). The small-bowel completion rate was significantly higher in the preparation group (100% vs 78%; P = 0.02). Bowel-preparation subjects reported significantly more discomfort than controls (62% vs 17%; P = 0.01).ConclusionsCombined bowel preparation did not improve small-bowel visualization but did significantly increase patient discomfort. The CE completion rate improved in the preparation group but the diagnostic yield was unaffected. Based on our findings, a bowel preparation prior to CE does not appear to improve CE performance and results in decreased patient satisfaction (ClinicalTrials.gov, No. NCT01243736).
| S-EPMC7217271 | biostudies-literature