Effectiveness and safety of capsule endoscopy in the diagnosis of small bowel diseases

Development and validation of a deep learning system for detection of small bowel pathologies in capsule endoscopy: a pilot study in a Singapore institution

INTRODUCTION

Deep learning models can assess the quality of images and discriminate among abnormalities in small bowel capsule endoscopy (CE), reducing fatigue and the time needed for diagnosis. They serve as a decision support system, partially automating the diagnosis process by providing probability predictions for abnormalities.

METHODS

We demonstrated the use of deep learning models in CE image analysis, specifically by piloting a bowel preparation model (BPM) and an abnormality detection model (ADM) to determine frame-level view quality and the presence of abnormal findings, respectively. We used convolutional neural network-based models pretrained on large-scale open-domain data to extract spatial features of CE images that were then used in a dense feed-forward neural network classifier. We then combined the open-source Kvasir-Capsule dataset (n = 43) and locally collected CE data (n = 29).

RESULTS

Model performance was compared using averaged five-fold and two-fold cross-validation for BPMs and ADMs, respectively. The best BPM model based on a pre-trained ResNet50 architecture had an area under the receiver operating characteristic and precision-recall curves of 0.969±0.008 and 0.843±0.041, respectively. The best ADM model, also based on ResNet50, had top-1 and top-2 accuracies of 84.03±0.051 and 94.78±0.028, respectively. The models could process approximately 200-250 images per second and showed good discrimination on time-critical abnormalities such as bleeding.

CONCLUSION

Our pilot models showed the potential to improve time to diagnosis in CE workflows. To our knowledge, our approach is unique to the Singapore context. The value of our work can be further evaluated in a pragmatic manner that is sensitive to existing clinician workflow and resource constraints.

Safety and efficacy of small-bowel capsule endoscopy examination in patients with Billroth II gastrojejunostomy

BACKGROUND

Small-bowel capsule endoscopy (SBCE) has become an increasingly utilized imaging modality for patients suspected of having small intestinal diseases. However, data regarding the role of SBCE in patients with Billroth II gastrojejunostomy are limited. The objective is to evaluate the safety and efficacy of SBCE in Billroth II gastrojejunostomy patients.

METHODS

We retrospectively studied patients with Billroth II gastrojejunostomy who underwent MiroCam capsule endoscopy between August 2013 and October 2019. Baseline patient characteristics; gastroscopic and SBCE findings; capsule transit time; and the occurrence of adverse events were collected and compared between groups with and without anastomotic lesions.

RESULTS

In total, 30 patients were analyzed in the study. The median age was 59 years, and 26 patients (86.7%) were men. The majority of SBCE positive findings including ulcers (10.0%), angioectasias (6.7%) and polyps (6.7%). In patients with (n = 10) and without (n = 20) anastomotic lesions, the anastomotic lesion was significantly associated with a delayed gastric transit time (GTT) (P = 0.026), but the two groups showed no significant difference in completion (P > 0.05). All patients underwent successful SBCE examinations without adverse events, except device transit into the afferent loop, where it remained for nearly 2 h, occurred in one case with anastomotic ulcers.

CONCLUSIONS

This retrospective study demonstrates that SBCE is a safe and effective diagnostic tool in patients with Billroth II gastrojejunostomy with a favorable gastroscopic evaluation within 7 days prior. The frequently real-time monitoring is suggested due to the risk of retention in the afferent loop, and a delayed food intake is required when a prolonged stay in the afferent loop occurred.

Capsule endoscopy in diagnosis of small bowel diseases: a health technology assessment

OBJECTIVES

Capsule endoscopy (CE) has been widely used in the diagnosis of small bowel disease (SBD) in the world. To bring CE into the national health insurance directory, and intensify its popularization in primary hospital, the government needs high-quality HTA evidence for decision makers. We were appointed by the National Health and Family Planning Commission of China to evaluate the effectiveness, safety, economy, and applicability of CE in the diagnosis of SBD, to provide the best currently available evidence for decision making.

METHODS

We searched the Cochrane Library (Issue 8, 2013), PubMed, EMbase, INAHTA, VIP, CBM, CNKI and WanFang Data. All confirmed or suspected SBD patients with diagnosis by CE versus other alternative therapies were considered. Health technology assessments (HTAs), systematic reviews (SRs), meta-analyses, randomized controlled trials (RCTs), guidelines and economic studies were included. Two investigators selected studies, assessed the quality and extracted data independently, and a descriptive analysis was used.

RESULTS

We included 4 HTAs, 11 SRs/meta-analyses, 2 RCTs, 5 guidelines, and 10 economic studies for assessment. The results showed that the disease detection rate of CE was higher than that of many other traditional technologies and that the main adverse event for CE was retention (0.7% to 3.0%). These results were consistent with those of the guidelines. Comprehensive results of economic studies showed the superiority of CE compared with other technologies. As the first choice, CE can decrease potential costs, especially when used in outpatients.

CONCLUSIONS

(i) CE has advantages in diagnostic yield, safety, and cost in the diagnosis of SBD, but some limitations exist. It still needs more high-quality evidence on CE diagnosis accuracy. (ii) When the government approves the introduction of CE in a hospital, many factors must be considered, such as the local disease burden, clinical demand, ability to pay, and staff. At the same time, it is necessary to standardize training for operating physicians, to reduce economic losses caused by poor technical ability of the medical staff.

Learning curve of capsule endoscopy

BACKGROUND/AIMS

Capsule endoscopy (CE) has become an important tool for the diagnosis of small bowel disease. Although CE does not require the skill of endoscope insertion, the images should be interpreted by a person with experience in assessing images of the gastrointestinal mucosa. This investigation aimed to document the number of cases needed by trainees to gain the necessary experience for CE competency.

METHODS

Fifteen cases were distributed to 12 trainees with no previous experience of CE during their gastroenterology training as clinical fellows. Twelve trainees and an expert were asked to read CE images from one patient each week for 15 weeks. The diagnosis was reported using five categories (no abnormalities detected, small bowel erosion or ulcer, small bowel tumor, Crohn disease, and active small bowel bleeding with no identifiable source). We then examined, using the κ coefficient, how the degree of mean agreements between the trainees and the expert changed as the training progressed each week.

RESULTS

The agreement rate of CE diagnosis increased as the frequencies of interpretation increased. Most of the mean κ coefficients were >0.60 and >0.80 after week 9 and 11, respectively.

CONCLUSIONS

Experience with approximately 10 cases of CE is appropriate for trainees to attain CE competency.

A case of lobulated and pedunculated duodenal hyperplastic polyp treated with snare polypectomy

We report herein the case of a lobulated and pedunculated hyperplastic polyp in the third portion of the duodenum causing anemia and occult blood in stools, which was detected by capsule endoscopy (CE) and treated with snare polypectomy. A 71-year-old man was referred to our hospital because of anemia and occult blood in stools. Three months earlier, he had been admitted to another hospital because of hemorrhage from gastric antral vascular ectasia (GAVE). Despite being treated for GAVE, hemoglobin decreased gradually. Esophagogastroduodenoscopy (EGD) and colonoscopy revealed no source of bleeding. However, CE revealed a polyp at the distal duodenum. Barium meal and EGD revealed a lobulated and pedunculated polyp in the third portion of the duodenum. The polyp was treated with snare polypectomy. Histopathological examination of the polyp revealed hyperplasia. After treatment of the polyp, the anemia improved gradually. To our knowledge, there are only 6 reported cases of a duodenal hyperplastic polyp, including our case. The polyp was pedunculated in only 2 cases and lobulated only in our case. Moreover, our case was diagnosed by CE. When a patient presents with anemia or obscure gastrointestinal bleeding undiagnosed by EGD and colonoscopy, CE is useful for detecting the bleeding lesion.

A retrospective analysis comparing small bowel follow-through with wireless capsule endoscopy in the evaluation of obscure gastrointestinal bleeding

A comparative retrospective study was conducted to evaluate diagnostic findings between small bowel follow-through (SBFT) and wireless capsule endoscopy in the presence of obscure gastrointestinal bleeding. A convenience sample of 31 patients with previous negative upper and lower endoscopy was included in the study. Wireless capsule endoscopy established a significant source of obscure gastrointestinal bleeding 53% of the time. The diagnostic capacity of radiographic SBFT was measured at 17% as compared with that of the wireless capsule endoscopy. The clinical findings along with the digital images obtained from the wireless capsule endoscopy was found to be the optimum diagnostic tool in the evaluation of obscure gastrointestinal bleeding in the small bowel.

Five years' experience with capsule endoscopy in a single center

Capsule endoscopy (CE) is a novel technology that facilitates highly effective and noninvasive imaging of the small bowel. Although its efficacy in the evaluation of obscure gastrointestinal bleeding (OGIB) has been proven in several trials, data on uses of CE in different small bowel diseases are rapidly accumulating in the literature, and it has been found to be superior to alternative diagnostic tools in a range of such diseases. Based on literature evidence, CE is recommended as a first-line investigation for OGIB after negative bidirectional endoscopy. CE has gained an important role in the diagnosis and follow-up of Crohn's disease and celiac disease and in the surveillance of small bowel tumors and polyps in selected patients. Capsule retention is the major complication, with a frequency of 1%-2%. The purpose of this review was to discuss the procedure, indications, contraindications and adverse effects associated with CE. We also review and share our five-year experience with CE in various small bowel diseases. The recently developed balloon-assisted enteroscopies have both diagnostic and therapeutic capability. At the present time, CE and balloon-assisted enteroscopies are complementary techniques in the diagnosis and management of small bowel diseases.

Diagnostic value of digital subtraction angiography in small intestinal bleeding

Due to lack of specific clinical symptoms of small intestinal bleeding and the limitation of its conventional examination methods, diagnosis of small intestinal bleeding is in a great dilemma. The purpose of this paper is to review the value of digital subtraction angiography (DSA) in the diagnosis of small intestinal bleeding and hope to instruct clinical diagnosis and therapy sufficiently.