Objectives. The complimentary value of computed tomographic enterography (CTE) and double-balloon enteroscopy (DBE) combined with capsule endoscopy (CE) was evaluated in the diagnosis of obscure gastrointestinal bleeding (OGIB). Methods. Patients who received CE examinations at Ruijin Hospital between July 2007 and July 2014 with the indication of OGIB were identified, and those who also underwent DBE and/or CTE were included. Their clinical information was retrieved, and results from each test were compared with findings from the other two examinations. Results. The overall diagnostic yield of CE was comparable with DBE (73.9% versus 60.9%) but was significantly higher than the yield of CTE (87% versus 25%, p < 0.001). The diagnostic yield of angiodysplasia at CE was significantly higher than CTE (73% versus 8%, p < 0.001) and DBE (39.1% versus 17.4%, p = 0.013), while no significant difference was found between the three approaches for small bowel tumors. DBE and CTE identified small bowel diseases undetected or undetermined by CE. Conversely, CE improved diagnosis in the cases with negative CTE and DBE, and findings at initial CE directed further diagnosis made by DBE. Conclusions. Combination of the three diagnostic platforms provides complementary value in the diagnosis of OGIB.
Objectives. Achieving a comprehensive view of gastric mucosa has been a challenge for magnetic-guided capsule endoscopy (MGCE) for years. This study works on optimizing the performance of MGCE by changing the conventional positions to the five body positions. Methods. Sixty patients were enrolled in the study and underwent MGCE. All patients were asked to adopt five body positions (left lateral, supine, right lateral, knee-chest, and sitting). In each position, the ability to visualize the six gastric landmarks (cardia, fundus, body, angulus, antrum, and pylorus) was assessed. Rates of complete visualization were calculated for different position combinations. Results. Supine position was the best for cardia and body visualization (91.7% and 86.7%, resp., p < 0.001). Left lateral position was the best for fundus visualization (91.7%, p < 0.001). Knee-chest position was the best for angulus observation (80.0%, p < 0.001). Right lateral and sitting positions were the best for antrum observation (88.3% and 90.0%, resp., p < 0.001). Right lateral position was the best for pylorus observation (81.7%, p < 0.001). The supine + right lateral + knee-chest combination achieved better angulus visualization than conventional 3-position combination (93.3% versus 63.3%, p < 0.001). Five-position combination significantly improved the comprehensive gastric landmark visualization (93.3%, p < 0.001). Conclusion. Compared with 3-position combination, 5-position combination should be adopted for gastric mucosal visualization by MGCE.
BACKGROUND Small intestinal vascular malformations (angiodysplasias) are common causes of small intestinal bleeding. While capsule endoscopy has become the primary diagnostic method for angiodysplasia, manual reading of the entire gastrointestinal tract is time-consuming and requires a heavy workload, which affects the accuracy of diagnosis. AIM To evaluate whether artificial intelligence can assist the diagnosis and increase the detection rate of angiodysplasias in the small intestine, achieve automatic disease detection, and shorten the capsule endoscopy (CE) reading time. METHODS A convolutional neural network semantic segmentation model with a feature fusion method, which automatically recognizes the category of vascular dysplasia under CE and draws the lesion contour, thus improving the efficiency and accuracy of identifying small intestinal vascular malformation lesions, was proposed. Resnet-50 was used as the skeleton network to design the fusion mechanism, fuse the shallow and depth features, and classify the images at the pixel level to achieve the segmentation and recognition of vascular dysplasia. The training set and test set were constructed and compared with PSPNet, Deeplab3+, and UperNet. RESULTS The test set constructed in the study achieved satisfactory results, where pixel accuracy was 99%, mean intersection over union was 0.69, negative predictive value was 98.74%, and positive predictive value was 94.27%. The model parameter was 46.38 M, the float calculation was 467.2 G, and the time length to segment and recognize a picture was 0.6 s. CONCLUSION Constructing a segmentation network based on deep learning to segment and recognize angiodysplasias lesions is an effective and feasible method for diagnosing angiodysplasias lesions.
With the development and generalization of endoscopic technology and screening, clinical application of magnetically controlled capsule gastroscopy (MCCG) has been increasing. In recent years, various types of MCCG are used globally. Therefore, establishing relevant guidelines on MCCG is of great significance. The current guidelines containing 23 statements were established based on clinical evidence and expert opinions, mainly focus on aspects including definition and diagnostic accuracy, application population, technical optimization, inspection process, and quality control of MCCG. The level of evidence and strength of recommendations were evaluated. The guidelines are expected to guide the standardized application and scientific innovation of MCCG for the reference of clinicians.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.