10 years of capsule endoscopy: an update

A Comparative Analysis of Optimization Algorithms for Gastrointestinal Abnormalities Recognition and Classification Based on Ensemble XcepNet23 and ResNet18 Features

Esophagitis, cancerous growths, bleeding, and ulcers are typical symptoms of gastrointestinal disorders, which account for a significant portion of human mortality. For both patients and doctors, traditional diagnostic methods can be exhausting. The major aim of this research is to propose a hybrid method that can accurately diagnose the gastrointestinal tract abnormalities and promote early treatment that will be helpful in reducing the death cases. The major phases of the proposed method are: Dataset Augmentation, Preprocessing, Features Engineering (Features Extraction, Fusion, Optimization), and Classification. Image enhancement is performed using hybrid contrast stretching algorithms. Deep Learning features are extracted through transfer learning from the ResNet18 model and the proposed XcepNet23 model. The obtained deep features are ensembled with the texture features. The ensemble feature vector is optimized using the Binary Dragonfly algorithm (BDA), Moth-Flame Optimization (MFO) algorithm, and Particle Swarm Optimization (PSO) algorithm. In this research, two datasets (Hybrid dataset and Kvasir-V1 dataset) consisting of five and eight classes, respectively, are utilized. Compared to the most recent methods, the accuracy achieved by the proposed method on both datasets was superior. The Q_SVM's accuracies on the Hybrid dataset, which was 100%, and the Kvasir-V1 dataset, which was 99.24%, were both promising.

Efficacy of a comprehensive binary classification model using a deep convolutional neural network for wireless capsule endoscopy

The manual reading of capsule endoscopy (CE) videos in small bowel disease diagnosis is time-intensive. Algorithms introduced to automate this process are premature for real clinical applications, and multi-diagnosis using these methods has not been sufficiently validated. Therefore, we developed a practical binary classification model, which selectively identifies clinically meaningful images including inflamed mucosa, atypical vascularity or bleeding, and tested it with unseen cases. Four hundred thousand CE images were randomly selected from 84 cases in which 240,000 images were used to train the algorithm to categorize images binarily. The remaining images were utilized for validation and internal testing. The algorithm was externally tested with 256,591 unseen images. The diagnostic accuracy of the trained model applied to the validation set was 98.067%. In contrast, the accuracy of the model when applied to a dataset provided by an independent hospital that did not participate during training was 85.470%. The area under the curve (AUC) was 0.922. Our model showed excellent internal test results, and the misreadings were slightly increased when the model was tested in unseen external cases while the classified 'insignificant' images contain ambiguous substances. Once this limitation is solved, the proposed CNN-based binary classification will be a promising candidate for developing clinically-ready computer-aided reading methods.

Artificial Intelligence Research and Development for Application in Video Capsule Endoscopy

Artificial intelligence (AI) research for medical applications has expanded quickly. Advancements in computer processing now allow for the development of complex neural network architectures (eg, convolutional neural networks) that are capable of extracting and learning complex features from massive data sets, including large image databases. Gastroenterology and endoscopy are well suited for AI research. Video capsule endoscopy is an ideal platform for AI model research given the large amount of data produced by each capsule examination and the annotated databases that are already available. Studies have demonstrated high performance for applications of capsule-based AI models developed for various pathologic conditions.

Therapeutic Impact of Deep Balloon-assisted Small Bowel Enteroscopy on Red Blood Cell Transfusion

Objective Evaluate impact of balloon-assisted deep small bowel enteroscopy on red blood cell transfusion requirement in patients with obscure gastrointestinal (GI) bleeding.

Methods Retrospective study of patients, who underwent balloon-assisted deep enteroscopy with double-balloon enteroscopy (DBE) at two tertiary care academic centers (University of Wisconsin and Aurora St. Luke’s Medical Center) over a 55-month consecutive period. Sixty-nine patients with reliable blood transfusion records were identified during this time period. DBE was preceded by small bowel capsule endoscopy (CE) within 1 year in 38 cases. Transfusion requirements 6 months prior and postintervention were measured to see if DBE had any impact on the need for blood transfusions.

Results Sixty-nine patients (25 females and 44 males) were included. Mean age ± standard deviation (SD) was 63 ± 17 years. Wilcoxon signed rank test statistics were used to find the difference in the rate of blood transfusion. There was a statistically significant decrease in rate of packed red blood cell (pRBC) transfusion post DBE and endoscopic therapy with coagulation (p < 0.001). Argon plasma coagulation was used to ablate all arteriovenous malformations (AVMs) except in one (subepithelial lesion). Those that required > 5 units pRBC transfusions pre-DBE had the most benefit.

Conclusions Our study demonstrates that transfusion requirements are significantly reduced in those undergoing therapy with DBE and coagulation for obscure GI bleed.

Deep learning for wireless capsule endoscopy: a systematic review and meta-analysis

BACKGROUND AND AIMS

Deep learning is an innovative algorithm based on neural networks. Wireless capsule endoscopy (WCE) is considered the criterion standard for detecting small-bowel diseases. Manual examination of WCE is time-consuming and can benefit from automatic detection using artificial intelligence (AI). We aimed to perform a systematic review of the current literature pertaining to deep learning implementation in WCE.

METHODS

We conducted a search in PubMed for all original publications on the subject of deep learning applications in WCE published between January 1, 2016 and December 15, 2019. Evaluation of the risk of bias was performed using tailored Quality Assessment of Diagnostic Accuracy Studies-2. Pooled sensitivity and specificity were calculated. Summary receiver operating characteristic curves were plotted.

RESULTS

Of the 45 studies retrieved, 19 studies were included. All studies were retrospective. Deep learning applications for WCE included detection of ulcers, polyps, celiac disease, bleeding, and hookworm. Detection accuracy was above 90% for most studies and diseases. Pooled sensitivity and specificity for ulcer detection were .95 (95% confidence interval [CI], .89-.98) and .94 (95% CI, .90-.96), respectively. Pooled sensitivity and specificity for bleeding or bleeding source were .98 (95% CI, .96-.99) and .99 (95% CI, .97-.99), respectively.

CONCLUSIONS

Deep learning has achieved excellent performance for the detection of a range of diseases in WCE. Notwithstanding, current research is based on retrospective studies with a high risk of bias. Thus, future prospective, multicenter studies are necessary for this technology to be implemented in the clinical use of WCE.

Clinical Practice Guideline for Enteroscopy

Management of small bowel diseases has evolved since the advent of capsule endoscopy (CE) and balloon-assisted enteroscopy (BAE). One of the most common indications for enteroscopy is obscure gastrointestinal bleeding (OGIB), followed by small bowel stenosis, tumors, and inflammatory bowel disease. Although enteroscopes have been regarded as useful tools, correct guidelines are required to ensure that we manipulate these enteroscopes safely and efficiently in clinical practice. Herein, the Japanese Gastroenterological Endoscopy Society has developed 'Clinical Practice Guidelines for Enteroscopy' in collaboration with the Japanese Society of Gastroenterology, the Japanese Gastroenterological Association, and the Japanese Association for Capsule Endoscopy. These guidelines are based on the evidence available until now, but small bowel endoscopy is a relatively new technology, so the guidelines include recommendations based on a consensus reached among experts when the evidence has not been considered sufficient. These guidelines were not designed to be disease-based, but focus on how we should use small bowel CE and BAE in everyday clinical practice.

Deep learning for polyp recognition in wireless capsule endoscopy images

PURPOSE

Wireless capsule endoscopy (WCE) enables physicians to examine the digestive tract without any surgical operations, at the cost of a large volume of images to be analyzed. In the computer-aided diagnosis of WCE images, the main challenge arises from the difficulty of robust characterization of images. This study aims to provide discriminative description of WCE images and assist physicians to recognize polyp images automatically.

METHODS

We propose a novel deep feature learning method, named stacked sparse autoencoder with image manifold constraint (SSAEIM), to recognize polyps in the WCE images. Our SSAEIM differs from the traditional sparse autoencoder (SAE) by introducing an image manifold constraint, which is constructed by a nearest neighbor graph and represents intrinsic structures of images. The image manifold constraint enforces that images within the same category share similar learned features and images in different categories should be kept far away. Thus, the learned features preserve large intervariances and small intravariances among images.

RESULTS

The average overall recognition accuracy (ORA) of our method for WCE images is 98.00%. The accuracies for polyps, bubbles, turbid images, and clear images are 98.00%, 99.50%, 99.00%, and 95.50%, respectively. Moreover, the comparison results show that our SSAEIM outperforms existing polyp recognition methods with relative higher ORA.

CONCLUSION

The comprehensive results have demonstrated that the proposed SSAEIM can provide descriptive characterization for WCE images and recognize polyps in a WCE video accurately. This method could be further utilized in the clinical trials to help physicians from the tedious image reading work.

Saliency based ulcer detection for wireless capsule endoscopy diagnosis

Ulcer is one of the most common symptoms of many serious diseases in the human digestive tract. Especially for the ulcers in the small bowel where other procedures cannot adequately visualize, wireless capsule endoscopy (WCE) is increasingly being used in the diagnosis and clinical management. Because WCE generates large amount of images from the whole process of inspection, computer-aided detection of ulcer is considered an indispensable relief to clinicians. In this paper, a two-staged fully automated computer-aided detection system is proposed to detect ulcer from WCE images. In the first stage, we propose an effective saliency detection method based on multi-level superpixel representation to outline the ulcer candidates. To find the perceptually and semantically meaningful salient regions, we first segment the image into multi-level superpixel segmentations. Each level corresponds to different initial region sizes of the superpixels. Then we evaluate the corresponding saliency according to the color and texture features in superpixel region of each level. In the end, we fuse the saliency maps from all levels together to obtain the final saliency map. In the second stage, we apply the obtained saliency map to better encode the image features for the ulcer image recognition tasks. Because the ulcer mainly corresponds to the saliency region, we propose a saliency max-pooling method integrated with the Locality-constrained Linear Coding (LLC) method to characterize the images. Experiment results achieve promising 92.65% accuracy and 94.12% sensitivity, validating the effectiveness of the proposed method. Moreover, the comparison results show that our detection system outperforms the state-of-the-art methods on the ulcer classification task.

Bleeding Frame and Region Detection in the Wireless Capsule Endoscopy Video

Wireless capsule endoscopy (WCE) enables noninvasive and painless direct visual inspection of a patient's whole digestive tract, but at the price of long time reviewing large amount of images by clinicians. Thus, an automatic computer-aided technique to reduce the burden of physicians is highly demanded. In this paper, we propose a novel color feature extraction method to discriminate the bleeding frames from the normal ones, with further localization of the bleeding regions. Our proposal is based on a twofold system. First, we make full use of the color information of WCE images and utilize K-means clustering method on the pixel represented images to obtain the cluster centers, with which we characterize WCE images as words-based color histograms. Then, we judge the status of a WCE frame by applying the support vector machine (SVM) and K-nearest neighbor methods. Comprehensive experimental results reveal that the best classification performance is obtained with YCbCr color space, cluster number 80 and the SVM. The achieved classification performance reaches 95.75% in accuracy, 0.9771 for AUC, validating that the proposed scheme provides an exciting performance for bleeding classification. Second, we propose a two-stage saliency map extraction method to highlight bleeding regions, where the first-stage saliency map is created by means of different color channels mixer and the second-stage saliency map is obtained from the visual contrast. Followed by an appropriate fusion strategy and threshold, we localize the bleeding areas. Quantitative as well as qualitative results show that our methods could differentiate the bleeding areas from neighborhoods correctly.

Computer-aided bleeding detection in WCE video

Wireless capsule endoscopy (WCE) can directly take digital images in the gastrointestinal tract of a patient. It has opened a new chapter in small intestine examination. However, a major problem associated with this technology is that too many images need to be manually examined by clinicians. Currently, there is no standard for capsule endoscopy image interpretation and classification. Most state-of-the-art CAD methods often suffer from poor performance, high computational cost, or multiple empirical thresholds. In this paper, a new method for rapid bleeding detection in the WCE video is proposed. We group pixels through superpixel segmentation to reduce the computational complexity while maintaining high diagnostic accuracy. Feature of each superpixel is extracted using the red ratio in RGB space and fed into support vector machine for classification. Also, the influence of edge pixels has been removed in this paper. Comparative experiments show that our algorithm is superior to the existing methods in terms of sensitivity, specificity, and accuracy.

First clinical trial of a newly developed capsule endoscope with panoramic side view for small bowel: a pilot study

BACKGROUND AND STUDY AIMS

Capsule endoscopy is the first-line diagnostic technique for the small bowel. However, the inability to visualize the duodenal papilla is an inherent limitation of this method. In the present study, we evaluated feasibility of a newly developed CapsoCam SV1 capsule.

PATIENTS AND METHODS

This is a prospective dual center study of a newly developed video capsule CapsoCam SV1 from Capsovision, CA, providing panoramic 360° imaging. A high frequency of 20 frames occurs per second for the first 2 h and thereafter 12 frames/s, with a battery life of 15 h. We evaluated feasibility and completeness of small bowel examination together with secondary endpoints of duodenal papilla detection in 33 patients. Patients swallowed the capsules following colonoscopy or were prepared with 2 L of polyethylene glycol solution prior to the examination. All patients swallowed 20 mg of metoclopramide and 160 mg of simethicone 30 min before ingestion of the capsule.

RESULTS

Thirty-one of the 33 patients' data could be evaluated. Small bowel examination was complete in all procedures. Mean time to pass the small bowel was 258 ± 136 min. Average small bowel cleanliness was 3.3 ± 0.5. In 71% of the patients, we identified the duodenal papilla. No adverse reaction in relation to the capsule examination was observed.

CONCLUSIONS

CapsoCam SV1 is a safe and efficient tool in small bowel examination. The duodenal papilla as the only landmark in small bowel is detected in more than 70% of the patients.

STORYBOARD OF WCE VIDEO EXTRACTION BASED ON FRAME DIFFERENCE

Wireless capsule endoscopy (WCE) is an imaging technology that enables close examination of the interior of the entire small intestine. A major problem associated with this new technology is that a large volume of video data need to be examined manually by clinicians. It is therefore useful to design a mechanism that allows the clinicians to gain certain evaluation of a video without watching the whole video. In this paper, a shot detection-based method is presented for automatically establishing the WCE video static storyboard, and then moving storyboard is extracted based on the selected representative frames under the supervision of clinicians. Experimental results show that most of the representative frames containing relevant features can be extracted from the original WCE video. The proposed method can significantly and safely reduce the number of frames that need to be examined by clinicians and thus speed up the diagnosis procedures.

Relationship between gastric transit time and complete examination rate of the capsule endoscopy examinations

AIM: To investigate the right timing for intervention when capsule endoscope transits for a relatively long time in the stomach.

METHODS: The following items were analyzed in 109 patients who underwent capsule endoscopy (CE) examinations: the relationship between gastric transit time (GTT) and complete examination rate (CER); the correlation between GTT and small bowel transit time (SBTT); the difference in GTT between groups of complete and incomplete examinations; and the risk of incomplete examination in patients with strictures of the small intestine.

RESULTS: No difference was found in CER among groups with GTT ≤ 30 min, 30-60 min, 60-90 min, or > 90 min (P = 0.971). Injection of metoclopramide in patients with longer GTT resulted in shorter SBTT compared to their counterparts with shorter GTT (t = -2.027, P = 0.046). No difference was found in GTT between groups of complete and incomplete examinations [45.6 min ± 35.8 min (n = 85) vs 42.0 min ± 36.4 min (n = 24), P = 0.665]. The risk of incomplete examination in patients with strictures of the small intestine was 6.588-fold higher than those without strictures (OR = 6.588, 95% CI = 1.866-23.258, P = 0.004).

CONCLUSION: Too early delivery of capsule endoscope in the duodenum might not improve CER. This procedure should be considered only if the retention of CE in the stomach exceeds 90 min, and it is better to be completed within 30 min.