Role of Artificial Intelligence in Video Capsule Endoscopy.
Ontology highlight
ABSTRACT:
SUBMITTER: Tziortziotis I
PROVIDER: S-EPMC8303156 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:ObjectivesArtificial intelligence (AI) may be practical for image classification of small bowel capsule endoscopy (CE). However, creating a functional AI model is challenging. We attempted to create a dataset and an object detection CE AI model to explore modeling problems to assist in reading small bowel CE.MethodsWe extracted 18,481 images from 523 small bowel CE procedures performed at Kyushu University Hospital from September 2014 to June 2021. We annotated 12,320 images with 23,033 disease lesions, combined them with 6161 normal images as the dataset, and examined the characteristics. Based on the dataset, we created an object detection AI model using YOLO v5 and we tested validation.ResultsWe annotated the dataset with 12 types of annotations, and multiple annotation types were observed in the same image. We test validated our AI model with 1396 images, and sensitivity for all 12 types of annotations was about 91%, with 1375 true positives, 659 false positives, and 120 false negatives detected. The highest sensitivity for individual annotations was 97%, and the highest area under the receiver operating characteristic curve was 0.98, but the quality of detection varied depending on the specific annotation.ConclusionsObject detection AI model in small bowel CE using YOLO v5 may provide effective and easy-to-understand reading assistance. In this SEE-AI project, we open our dataset, the weights of the AI model, and a demonstration to experience our AI. We look forward to further improving the AI model in the future.
| S-EPMC10288072 | biostudies-literature
Project description:Background and aimsArtificial intelligence (AI)-based applications have transformed several industries and are widely used in various consumer products and services. In medicine, AI is primarily being used for image classification and natural language processing and has great potential to affect image-based specialties such as radiology, pathology, and gastroenterology (GE). This document reviews the reported applications of AI in GE, focusing on endoscopic image analysis.MethodsThe MEDLINE database was searched through May 2020 for relevant articles by using key words such as machine learning, deep learning, artificial intelligence, computer-aided diagnosis, convolutional neural networks, GI endoscopy, and endoscopic image analysis. References and citations of the retrieved articles were also evaluated to identify pertinent studies. The manuscript was drafted by 2 authors and reviewed in person by members of the American Society for Gastrointestinal Endoscopy Technology Committee and subsequently by the American Society for Gastrointestinal Endoscopy Governing Board.ResultsDeep learning techniques such as convolutional neural networks have been used in several areas of GI endoscopy, including colorectal polyp detection and classification, analysis of endoscopic images for diagnosis of Helicobacter pylori infection, detection and depth assessment of early gastric cancer, dysplasia in Barrett's esophagus, and detection of various abnormalities in wireless capsule endoscopy images.ConclusionsThe implementation of AI technologies across multiple GI endoscopic applications has the potential to transform clinical practice favorably and improve the efficiency and accuracy of current diagnostic methods.
| S-EPMC7732722 | biostudies-literature
Project description:Artificial intelligence (AI), which has demonstrated outstanding achievements in image recognition, can be useful for the tedious capsule endoscopy (CE) reading. We aimed to develop a practical AI-based method that can identify various types of lesions and tried to evaluate the effectiveness of the method under clinical settings. A total of 203,244 CE images were collected from multiple centers selected considering the regional distribution. The AI based on the Inception-Resnet-V2 model was trained with images that were classified into two categories according to their clinical significance. The performance of AI was evaluated with a comparative test involving two groups of reviewers with different experiences. The AI summarized 67,008 (31.89%) images with a probability of more than 0.8 for containing lesions in 210,100 frames of 20 selected CE videos. Using the AI-assisted reading model, reviewers in both the groups exhibited increased lesion detection rates compared to those achieved using the conventional reading model (experts; 34.3%-73.0%; p = 0.029, trainees; 24.7%-53.1%; p = 0.029). The improved result for trainees was comparable to that for the experts (p = 0.057). Further, the AI-assisted reading model significantly shortened the reading time for trainees (1621.0-746.8 min; p = 0.029). Thus, we have developed an AI-assisted reading model that can detect various lesions and can successfully summarize CE images according to clinical significance. The assistance rendered by AI can increase the lesion detection rates of reviewers. Especially, trainees could improve their efficiency of reading as a result of reduced reading time using the AI-assisted model.
| S-EPMC7595411 | biostudies-literature
Project description:BackgroundIntestinal transplantation is a procedure which inflicts immunological and infectious complications that affect the transplanted graft, posing both diagnostic and therapeutic challenges. Video capsule endoscopy (VCE) offers easy access to the entire small intestine and presents itself as an interesting option. However, at present, no studies evaluating the usefulness of video capsule endoscopies in this setting have been published. Our aim was to evaluate the usefulness of VCE in detecting complications that arise after intestinal transplantation.MethodsWe included 7 adult patients with either isolated intestine (n = 1) or multivisceral grafts (n = 6). These patients underwent 12 VCE between 2004 and 2015 at the Sahlgrenska University Hospital. The median age was 42 (21-67) years (4 women/3 men). VCE was used in clinical situations where the conventional diagnostic methods failed to provide answers to the clinical question.ResultsIndications for the procedure were: suspicion of rejection (n = 4 examinations), gastrointestinal dysmotility (n = 4 examinations), high stomal output (n = 2 examinations), suspicion of lymphoproliferative disease in the transplanted graft (n = 1 examination), and clinical surveillance (n = 1 examination). The median time after transplantation for performing an examination was 740 (26-3059) days. VCE was useful in 83% of the examinations and the results influenced the planned management. The overall agreement between VCE findings and biopsies was moderate (κ = 0.54, P = 0.05) but increased when comparing the presence of inflammation/rejection (κ = 0.79, P < 0.001).ConclusionsVCE is a promising diagnostic method after intestinal transplantation. However, larger studies are needed to evaluate its potential risks and gains.
| S-EPMC5142358 | biostudies-literature
Project description:BackgroundAngiodysplasia (AGD) is rarely diagnosed in dogs with gastrointestinal bleeding (GIB) and is reported in case reports in dogs.ObjectiveDescribe signalment, clinical and diagnostic features of dogs with gastrointestinal (GI) AGD diagnosed by video capsule endoscopy (VCE).AnimalsDogs with overt or suspected GIB which underwent VCE.MethodsDogs for which a VCE was submitted for overt or suspected GIB from 2016 to 2021 were selected retrospectively. Medical records and full-length VCE recordings where AGDs were initially detected, were reviewed by 2 trained internists. AGD was considered definitive if 2 readers detected it. Signalment, clinical signs, blood work, medications, concurrent diseases, findings of previous conventional endoscopy, and surgical exploration (if applicable) of dogs with AGD were recorded.ResultsDefinitive AGD was diagnosed in 15 of 291 (5%) dogs (12 males, 3 females). Twelve (80%) had overt GIB, 11 (73%) had hematochezia, and 6 (40%) had microcytic and hypochromic anemia. AGD was missed by conventional endoscopy in 9/9 dogs and exploratory surgery in 3/3 dogs. Thirteen capsules were administered by mouth (1 incomplete study), and 2 via endoscopy directly into the duodenum. AGD was visualized in the stomach of 3 dogs, in the small intestine of 4, and in the colon of 13 dogs.Conclusion and clinical importanceAlthough rare, AGD should be considered in dogs with suspected GIB after a negative conventional endoscopy or surgical exporation. Video capsuel endoscopy appears to be a sensitive test to identify AGD within the GI tract.
| S-EPMC10061205 | biostudies-literature
Project description:BackgroundGuidelines suggest computed tomography colonography (CTC) following incomplete optical colonoscopy (OC). Colon capsule endoscopies (CCE) have been suggested as an alternative, although completion rates have been unsatisfactory. Introduction of artificial intelligence (AI)-based localization algorithms of the camera capsules may enable identification of incomplete CCE investigations overlapping with incomplete OCs.ObjectiveThe study aims to investigate relative sensitivity of CCE compared with CTC following incomplete OC, investigate the completion rate when combining results from the incomplete OC and CCE, and develop a forward-tracking algorithm ensuring a safe completeness of combined investigations.MethodsIn this prospective paired study, patients with indication for CTC following incomplete OC were included for CCE and CTC. Location of CCE abortion and OC abortion were registered to identify complete combined investigations. AI-based algorithm for localization of capsules were developed reconstructing the passage of the colon.ResultsIn 237 individuals with CTC indication; 105 were included, of which 97 underwent both a CCE and CTC. CCE was complete in 66 (68%). Including CCEs which reached most oral point of incomplete OC, 73 (75%) had complete colonic investigations; 78 (80%) had conclusive investigations. Relative sensitivity of CCE compared with CTC was 2.67 (95% confidence interval (CI) 1.76;4.04) for polyps >5 mm and 1.91 (95% CI 1.18;3.09) for polyps >9 mm. An AI-based algorithm was developed.ConclusionSensitivity of CCE following incomplete OC was superior to CTC. Introducing and improving algorithm-based localization of capsule abortion may increase identification of overall complete investigation rates following incomplete OC.ClinicalTrials.gov identifier: NCT02826993.
| S-EPMC7435000 | biostudies-literature
Project description:Artificial intelligence (AI) is widely used to analyze gastrointestinal (GI) endoscopy image data. AI has led to several clinically approved algorithms for polyp detection, but application of AI beyond this specific task is limited by the high cost of manual annotations. Here, we show that a weakly supervised AI can be trained on data from a clinical routine database to learn visual patterns of GI diseases without any manual labeling or annotation. We trained a deep neural network on a dataset of N = 29,506 gastroscopy and N = 18,942 colonoscopy examinations from a large endoscopy unit serving patients in Germany, the Netherlands and Belgium, using only routine diagnosis data for the 42 most common diseases. Despite a high data heterogeneity, the AI system reached a high performance for diagnosis of multiple diseases, including inflammatory, degenerative, infectious and neoplastic diseases. Specifically, a cross-validated area under the receiver operating curve (AUROC) of above 0.70 was reached for 13 diseases, and an AUROC of above 0.80 was reached for two diseases in the primary data set. In an external validation set including six disease categories, the AI system was able to significantly predict the presence of diverticulosis, candidiasis, colon and rectal cancer with AUROCs above 0.76. Reverse engineering the predictions demonstrated that plausible patterns were learned on the level of images and within images and potential confounders were identified. In summary, our study demonstrates the potential of weakly supervised AI to generate high-performing classifiers and identify clinically relevant visual patterns based on non-annotated routine image data in GI endoscopy and potentially other clinical imaging modalities.
| S-EPMC8941159 | biostudies-literature
Project description:BACKGROUND AND STUDY AIMS?:Lynch syndrome (LS) patients have an increased risk of small bowel cancer. The question is whether surveillance will lead to early detection of (pre)malignant lesions. We recently reported on prevalence of small bowel neoplasia (SBN) in LS patients as assessed by video capsule endoscopy (VCE). The aim of this prospective study was to determine the incidence of SBN. PATIENTS AND METHODS?:Asymptomatic LS patients who underwent a VCE were invited to undergo a second VCE procedure 2 years later. If abnormalities or polypoid lesions larger than 1?cm were detected, subsequent endoscopic procedures were performed. RESULTS?:A total of 155 (78?%) of the initial 200 patients underwent a second VCE procedure after a mean of 2.2 (range 1?-?6) years. In 17 of the 155 (11?%) patients possibly significant lesions were detected, which required further investigation by means of gastroduodenoscopy (n?=?8) or balloon-assisted endoscopy (n?=?9). These procedures revealed no SBN. CONCLUSION?:No SBN was found after 2 years. Surveillance of the small bowel by VCE does not seem to be warranted in asymptomatic LS patients.
| S-EPMC5500106 | biostudies-literature
Project description:BackgroundDespite differences in the information obtained by capsule endoscopy (CE) and magnetic resonance enterography (MRE), one of these modalities is usually needed when evaluating disease activity. There are no data on patients' preference that would help guide the choice between these two modalities in these instances.AimTo compare patients' tolerance and preference to MRE versus CE.Patients and methodsPatients with known small bowel Crohn's disease (CD) in clinical remission (Crohn's disease activity index [CDAI] <150) or with mild symptoms (CDAI <220) were prospectively recruited. All patients underwent MRE followed by CE. Patients were asked to fill out a questionnaire addressing specific points regarding inconvenience during the preparation for the procedures, the procedures, and postprocedures. Side effects and procedure preference were addressed. Questionnaires were included for analysis only when more than 95% of the items were addressed.ResultsFifty-six patients fulfilled inclusion criteria. Pre-exam discomfort, during-exam discomfort, nausea, vomiting, bloating, and abdominal pain were all significantly more prominent in MRE as compared to CE (P<0.0001, P<0.0001, P<0.0001, P=0.009, P=0.0002, P<0.0001, respectively). MRE was perceived as a more difficult procedure (P<0.0001). Furthermore, MRE was associated with a specific adverse event - claustrophobia. Seventy-eight percent of patients (44 patients) preferred to repeat CE as compared to 22% (P<0.0001) who preferred MRE.ConclusionCE was better tolerated by CD patients compared to MRE and was preferred by 78% of patients. The superior tolerability of CE should be considered along with the diagnostic features, and more data sought when choosing between these two modalities for CD patients for long-term follow-up.
| S-EPMC4908937 | biostudies-literature
Project description:Background and study aims Determining the etiology and location of gastrointestinal motility disorders can be challenging. A range of investigations targeting specific areas of gastrointestinal transit are available, but many provide clinical data for a given gastrointestinal region alone or for non-specific whole gut transit, and are otherwise of limited use. Video capsule endoscopy allows endoscopic visualisation of the entire gastrointestinal tract, and may also provide more specific data for regional transit time abnormalities. Patients and methods Data from video capsules ingested by 71 ambulatory healthy subjects were recorded and analyzed to determine gastric and small bowel transit times in the fasting state. Results Median, and interquartile range (IQR), gastric transit time was 22 (10-48) minutes, and median (IQR) small bowel transit time was 198.5 (157-240.5) minutes. Conclusion These data, for the first time to our knowledge, provide references for gastrointestinal transit times among healthy ambulatory subjects using video capsule endoscopy. This potentially strengthens clinical use of video capsule endoscopy in the investigation of patients with suspected gastrointestinal motility disorders.
| S-EPMC7035031 | biostudies-literature