Wireless Capsule Endoscopy Video Research Articles

592 Comparison of Endoscopic Placement versus Oral Ingestion of Small Bowel Video Capsule for Evaluation of Inpatients With Small Intestinal Bleeding

INTRODUCTION: Wireless small bowel video capsule endoscopy (VCE) is used to evaluate small intestinal bleeding after upper endoscopy and colonoscopy fail to identify a source of bleeding. The majority of patients swallow the capsule but endoscopic placement in the duodenum is an option. Limited data suggests higher rate of gastric retention of capsule in inpatients due to a variety of reasons, resulting in an incomplete exam. Hypothetically, endoscopic placement should increase likelihood of complete small bowel evaluation but there is little data comparing the two approaches. We aimed to compare completion rates and outcomes of capsule studies via endoscopic placement (CS-EP) versus oral ingestion (CS-OI) in inpatients undergoing VCE. METHODS: Patients who had VCE studies performed inpatient for gastrointestinal bleeding at Rhode Island Hospital between April 2015 and July 2016 were identified retrospectively. Baseline patient demographics, time intervals between reported bleed, date of admission and date of discharge, capsule study, indications for capsule study, completion rates and detection of small bowel bleeding were collected. Statistical tests were done using student's t-test and chi square test. RESULTS: Data was available for 83 patients between April 2015 and July 2016. The most common indications were for obscure bleed (92%) followed by anemia (86%). 29 (35%) patients had small bowel capsule studies that were endoscopically placed. Majority of patients underwent endoscopic placement due to provider preference. CS-EP had a higher proportion of men than CS-OI (66% vs. 44%, P = .06). The mean duration from bleeding episode to capsule study was 8.4 days for both groups. Small bowel bleeding was more likely to be detected by CS-EP than CS-OI (34% vs. 13%, P = 0.02), however completion rates were similar between both studies (69% vs. 76%, P = 0.5). CS-EP had a longer time from study to discharge (days: 7.1 vs. 3.7, P = 0.1) and longer length of stay at the hospital (days: 11.45 vs. 7.47, P = 0.1) compared to CS-OI. CONCLUSION: Based on this single center study, although endoscopic placement of VCE was more likely to detect small bowel bleeding compared to oral ingestion, there was no difference in study completion rates and CS-EP group in fact had a longer length of stay. Investigation into potential causes of longer length of stay and cost of care associated with endoscopic placement are ongoing. Additional data is also being collected for capsule studies performed over several more years.

Deep Convolutional Neural Network for Ulcer Recognition in Wireless Capsule Endoscopy: Experimental Feasibility and Optimization.

Wireless capsule endoscopy (WCE) has developed rapidly over the last several years and now enables physicians to examine the gastrointestinal tract without surgical operation. However, a large number of images must be analyzed to obtain a diagnosis. Deep convolutional neural networks (CNNs) have demonstrated impressive performance in different computer vision tasks. Thus, in this work, we aim to explore the feasibility of deep learning for ulcer recognition and optimize a CNN-based ulcer recognition architecture for WCE images. By analyzing the ulcer recognition task and characteristics of classic deep learning networks, we propose a HAnet architecture that uses ResNet-34 as the base network and fuses hyper features from the shallow layer with deep features in deeper layers to provide final diagnostic decisions. 1,416 independent WCE videos are collected for this study. The overall test accuracy of our HAnet is 92.05%, and its sensitivity and specificity are 91.64% and 92.42%, respectively. According to our comparisons of F1, F2, and ROC-AUC, the proposed method performs better than several off-the-shelf CNN models, including VGG, DenseNet, and Inception-ResNet-v2, and classical machine learning methods with handcrafted features for WCE image classification. Overall, this study demonstrates that recognizing ulcers in WCE images via the deep CNN method is feasible and could help reduce the tedious image reading work of physicians. Moreover, our HAnet architecture tailored for this problem gives a fine choice for the design of network structure.

On the suitability of VMAF for quality assessment of medical videos: Medical ultrasound & wireless capsule endoscopy

With the rapid evolution in modern multimedia networks and systems, services such as telemedicine and tele-surgery are becoming more popular. Quality estimation and monitoring of medical videos is becoming important not only in the field of research, but also in real-time applications and services. The state-of-the-art video quality metric (VQM) called Video Multimethod Assessment Fusion (VMAF) is a promising solution for quality estimation of videos impaired by compression and scaling artifacts. The metric was developed by Netflix for entertainment video content and its good performance does not necessarily extend to medical videos. This paper focuses on evaluating the performance of VMAF in the context of quality assessment (QA) for medical videos. We consider in this paper medical videos compressed via High Efficiency Video Coding (HEVC) and refer in particular to medical ultrasound videos and wireless capsule endoscopy (WCE) videos for the performance estimation of VMAF. The correlation between the subjective scores of these two datasets and VMAF's quality estimates is studied and presented. The results show that VMAF outperforms other state-of-the-art VQMs in the context of WCE videos, but this is not the case for medical ultrasound videos.

Bleeding detection in wireless capsule endoscopy videos - Color versus texture features.

Wireless capsule endoscopy (WCE) is an effective technology that can be used to make a gastrointestinal (GI) tract diagnosis of various lesions and abnormalities. Due to a long time required to pass through the GI tract, the resulting WCE data stream contains a large number of frames which leads to a tedious job for clinical experts to perform a visual check of each and every frame of a complete patient’s video footage. In this paper, an automated technique for bleeding detection based on color and texture features is proposed. The approach combines the color information which is an essential feature for initial detection of frame with bleeding. Additionally, it uses the texture which plays an important role to extract more information from the lesion captured in the frames and allows the system to distinguish finely between borderline cases. The detection algorithm utilizes machine‐learning‐based classification methods, and it can efficiently distinguish between bleeding and nonbleeding frames and perform pixel‐level segmentation of bleeding areas in WCE frames. The performed experimental studies demonstrate the performance of the proposed bleeding detection method in terms of detection accuracy, where we are at least as good as the state‐of‐the‐art approaches. In this research, we have conducted a broad comparison of a number of different state‐of‐the‐art features and classification methods that allows building an efficient and flexible WCE video processing system.

Segmentation of bleeding regions in wireless capsule endoscopy for detection of informative frames

Wireless capsule endoscopy (WCE) is an effective means for diagnosis of gastrointestinal disorders. Detection of informative scenes in WCE video could reduce the length of transmitted videos and help the diagnosis procedure. In this paper, we investigate the problem of simplification of neural networks for automatic bleeding region segmentation inside capsule endoscopy device. Suitable color channels are selected as neural networks inputs, and image classification is conducted using a multi-layer perceptron (MLP) and a convolutional neural network (CNN) separately. Both CNN and MLP structures are simplified to reduce the number of computational operations. Performances of two simplified networks are evaluated on a WCE bleeding image dataset using the DICE score. Simulation results show that applying simplification methods on both MLP and CNN structures reduces the number of computational operations significantly with AUC-ROC greater than 0.97. Although CNN performs better in comparison with the simplified MLP, the simplified MLP segments bleeding regions with a significantly smaller number of computational operations. Concerning the importance of having a simple structure or a more accurate model, each of the designed structures could be selected for inside capsule implementation.

Automatic Segmentation and Detection of Small Bowel Angioectasias in WCE Images.

Angioectasias are lesions that occur in the blood vessels of the bowel and are the cause of more than 8% of all gastrointestinal bleeding episodes. They are usually classified as bleeding related lesions, however current state-of-the-art bleeding detection algorithms present low sensitivity in the detection of these lesions. This paper proposes a methodology for the automatic detection of angioectasias in wireless capsule endoscopy (WCE) videos. This method relies on the automatic selection of a region of interest, selected by using an image segmentation module based on the Maximum a Posteriori (MAP) approach where a new accelerated version of the Expectation-Maximization (EM) algorithm is also proposed. Spatial context information is modeled in the prior probability density function by using Markov Random Fields with the inclusion of a weighted boundary function. Higher order statistics computed in the CIELab color space with the luminance component removed and intensity normalization of high reflectance regions, showed to be effective features regarding angioectasia detection. The proposed method outperforms some current state of the art algorithms, achieving sensitivity and specificity values of more than 96% in a database containing 800 WCE frames labeled by two gastroenterologists.

Application of Convolutional Neural Networks for Automated Ulcer Detection in Wireless Capsule Endoscopy Images.

Detection of abnormalities in wireless capsule endoscopy (WCE) images is a challenging task. Typically, these images suffer from low contrast, complex background, variations in lesion shape and color, which affect the accuracy of their segmentation and subsequent classification. This research proposes an automated system for detection and classification of ulcers in WCE images, based on state-of-the-art deep learning networks. Deep learning techniques, and in particular, convolutional neural networks (CNNs), have recently become popular in the analysis and recognition of medical images. The medical image datasets used in this study were obtained from WCE video frames. In this work, two milestone CNN architectures, namely the AlexNet and the GoogLeNet are extensively evaluated in object classification into ulcer or non-ulcer. Furthermore, we examine and analyze the images identified as containing ulcer objects to evaluate the efficiency of the utilized CNNs. Extensive experiments show that CNNs deliver superior performance, surpassing traditional machine learning methods by large margins, which supports their effectiveness as automated diagnosis tools.

Reduction of bubble-like frames using a RSS filter in wireless capsule endoscopy video

Wireless capsule endoscopy (WCE) is an advanced technique for inner visualization of the digestive tract. However, its large amount of video data collected continuously for several hours by wireless image sensors usually results in tiresome and tedious reading for physicians. To develop this technique in practice, the automatic reduction of large amounts of video data arises as a helpful alternative, which is partly implemented by detecting the non-useful frames, such as those filled with intestinal juices accompanying large bubble-like regions. Based on the bubbles’ morphology properties, a novel automatic approach for detecting the bubble-like frames in capsule video endoscopy that is based on a new ring shape selective (RSS) filter is presented. According to the shape of the bubbles’ bright ring boundary, a group of the shape probability functions and the response intensity functions produced by Hessian matrix eigenvalues are used to construct the RSS filters to enhance the boundary areas of the bubbles. Then, the bubble-like frames can be distinguished by in the bright areas after binary and morphological processing in the filtered images. The experimental results show that the uninformative bubble-like frames can be detected effectively by this approach even under non-uniform illumination conditions.

Multiple bleeding detection in wireless capsule endoscopy

Wireless capsule endoscopy (WCE) is an emerging technology that aims to detect pathology in the patient gastrointestinal tract. Physicians can use WCE to detect various gastrointestinal diseases at early stages. However, the diagnosis is tedious because it requires reviewing hundreds of frames extracted from the captured video. This tedious task has promoted researchers’ efforts to propose automated diagnosis tools of WCE frames in order to detect symptoms of gastrointestinal diseases. In this paper, we propose an automatic multiple bleeding spots detection using WCE video. The proposed approach relies on two main components: (1) a feature extraction intended to capture the visual properties of the multiple bleeding spots, and (2) a supervised and unsupervised learning techniques which aim to accurately recognize multiple bleeding.

A novel method to detect bleeding frame and region in wireless capsule endoscopy video

To detect the region and bleeding frame in the wireless capsule endoscopy video, an automatic computer-aided technique is highly demanded to reduce the burden of physicians. The wireless capsule endoscopy (WCE), is an imaging technology which is recently established and doesn’t require any wired device. This device detects abnormalities in GI tract, i.e. (colon, esophagus, small intestine, and stomach). A WCE video consists of 57,000 images. It is very hard to examine by clinicians. To determine bleeding photos out of fifty-seven thousand WCE images makes the task very hard and expensive. The main goal is to develop an automatic obscure bleeding detection method by using superpixel segmentation and naive Bayes classifier. Naive Bayes and superpixel segmentation are used for this problem.

Cluster based statistical feature extraction method for automatic bleeding detection in wireless capsule endoscopy video

Wireless capsule endoscopy (WCE) is capable of demonstrating the entire gastrointestinal tract at an expense of exhaustive reviewing process for detecting bleeding disorders. The main objective is to develop an automatic method for identifying the bleeding frames and zones from WCE video. Different statistical features are extracted from the overlapping spatial blocks of the preprocessed WCE image in a transformed color plane containing green to red pixel ratio. The unique idea of the proposed method is to first perform unsupervised clustering of different blocks for obtaining two clusters and then extract cluster based features (CBFs). Finally, a global feature consisting of the CBFs and differential CBF is used to detect bleeding frame via supervised classification. In order to handle continuous WCE video, a post-processing scheme is introduced utilizing the feature trends in neighboring frames. The CBF along with some morphological operations is employed to identify bleeding zones. Based on extensive experimentation on several WCE videos, it is found that the proposed method offers significantly better performance in comparison to some existing methods in terms of bleeding detection accuracy, sensitivity, specificity and precision in bleeding zone detection. It is found that the bleeding detection performance obtained by using the proposed CBF based global feature is better than the feature extracted from the non-clustered image. The proposed method can reduce the burden of physicians in investigating WCE video to detect bleeding frame and zone with a high level of accuracy.

Organic Boundary Location Based on Color-Texture of Visual Perception in Wireless Capsule Endoscopy Video.

This paper addresses the problem of automatically locating the boundary between the stomach and the small intestine (the pylorus) in wireless capsule endoscopy (WCE) video. For efficient image segmentation, the color-saliency region detection (CSD) method is developed for obtaining the potentially valid region of the frame (VROF). To improve the accuracy of locating the pylorus, we design the Monitor-Judge model. On the one hand, the color-texture fusion feature of visual perception (CTVP) is constructed by grey level cooccurrence matrix (GLCM) feature from the maximum moments of the phase congruency covariance and hue-saturation histogram feature in HSI color space. On the other hand, support vector machine (SVM) classifier with the CTVP feature is utilized to locate the pylorus. The experimental results on 30 real WCE videos demonstrate that the proposed location method outperforms the related valuable techniques.

CHOBS: Color Histogram of Block Statistics for Automatic Bleeding Detection in Wireless Capsule Endoscopy Video.

Wireless capsule endoscopy (WCE) is the most advanced technology to visualize whole gastrointestinal (GI) tract in a non-invasive way. But the major disadvantage here, it takes long reviewing time, which is very laborious as continuous manual intervention is necessary. In order to reduce the burden of the clinician, in this paper, an automatic bleeding detection method for WCE video is proposed based on the color histogram of block statistics, namely CHOBS. A single pixel in WCE image may be distorted due to the capsule motion in the GI tract. Instead of considering individual pixel values, a block surrounding to that individual pixel is chosen for extracting local statistical features. By combining local block features of three different color planes of RGB color space, an index value is defined. A color histogram, which is extracted from those index values, provides distinguishable color texture feature. A feature reduction technique utilizing color histogram pattern and principal component analysis is proposed, which can drastically reduce the feature dimension. For bleeding zone detection, blocks are classified using extracted local features that do not incorporate any computational burden for feature extraction. From extensive experimentation on several WCE videos and 2300 images, which are collected from a publicly available database, a very satisfactory bleeding frame and zone detection performance is achieved in comparison to that obtained by some of the existing methods. In the case of bleeding frame detection, the accuracy, sensitivity, and specificity obtained from proposed method are 97.85%, 99.47%, and 99.15%, respectively, and in the case of bleeding zone detection, 95.75% of precision is achieved. The proposed method offers not only low feature dimension but also highly satisfactory bleeding detection performance, which even can effectively detect bleeding frame and zone in a continuous WCE video data.

An Automatic Bleeding Frame and Region Detection Scheme for Wireless Capsule Endoscopy Videos Based on Interplane Intensity Variation Profile in Normalized RGB Color Space.

Wireless capsule endoscopy (WCE) is an effective video technology to diagnose gastrointestinal (GI) disease, such as bleeding. In order to avoid conventional tedious and risky manual review process of long duration WCE videos, automatic bleeding detection schemes are getting importance. In this paper, to investigate bleeding, the analysis of WCE images is carried out in normalized RGB color space as human perception of bleeding is associated with different shades of red. In the proposed method, at first, from the WCE image frame, an efficient region of interest (ROI) is extracted based on interplane intensity variation profile in normalized RGB space. Next, from the extracted ROI, the variation in the normalized green plane is presented with the help of histogram. Features are extracted from the proposed normalized green plane histograms. For classification purpose, the K-nearest neighbors classifier is employed. Moreover, bleeding zones in a bleeding image are extracted utilizing some morphological operations. For performance evaluation, 2300 WCE images obtained from 30 publicly available WCE videos are used in a tenfold cross-validation scheme and the proposed method outperforms the reported four existing methods having an accuracy of 97.86%, a sensitivity of 95.20%, and a specificity of 98.32%.

Automatic Computer Aided Bleeding Detection Scheme for Wireless Capsule Endoscopy (WCE) Video Based on Higher and Lower Order Statistical Features in a Composite Color

Wireless capsule endoscopy (WCE) offers noninvasive means to diagnose intestinal anomalies like bleeding. However, one of the problems here is the time consuming complex reviewing process which calls for automatic computer aided bleeding detection techniques to reduce the burden of the physicians. In this paper, pixel based holistic feature extraction scheme is proposed for bleeding frame detection of WCE recordings. Unlike conventional methods, instead of directly using RGB (red, green, blue) color space, a transform color domain is introduced. Higher and lower order statistical analysis on that composite color domain are carried out to extract features from the given WCE image. Feature-based supervised classification using support vector machine is performed to differentiate bleeding and non-bleeding images. Next, in order to improve the bleeding frame detection performance in WCE video, a post-processing scheme is developed utilizing the variation in temporal characteristics of consecutive frames. Finally, a zone detection algorithm is proposed to identify bleeding regions in the detected bleeding images where some morphological operations are also used. Extensive experimentation is carried out on a numerous number of WCE images and videos. It is observed that the proposed algorithm can detect bleeding frame and zones from WCE video recordings with a satisfactory level of performance.

Feature Selection and Classification of Ulcerated Lesions Using Statistical Analysis for WCE Images

Wireless capsule endoscopy (WCE) is a technology developed to inspect the whole gastrointestinal tract (especially the small bowel area that is unreachable using the traditional endoscopy procedure) for various abnormalities in a non-invasive manner. However, visualization of a massive number of images is a very time-consuming and tedious task for physicians (prone to human error). Thus, an automatic scheme for lesion detection in WCE videos is a potential solution to alleviate this problem. In this work, a novel statistical approach was chosen for differentiating ulcer and non-ulcer pixels using various color spaces (or more specifically using relevant color bands). The chosen feature vector was used to compute the performance metrics using SVM with grid search method for maximum efficiency. The experimental results and analysis showed that the proposed algorithm was robust in detecting ulcers. The performance in terms of accuracy, sensitivity, and specificity are 97.89%, 96.22%, and 95.09%, respectively, which is promising.

Quality assessment for wireless capsule endoscopy videos compressed via HEVC: From diagnostic quality to visual perception

Maintaining the quality of medical images and videos is an essential part of the e-services provided by the healthcare sector. The convergence of modern communication systems and the healthcare industry necessitates the provision of better quality of service and experience by the service provider. Recent inclusion and standardization of the high efficiency video coder (HEVC) has made it possible for medical data to be compressed and transmitted over wireless networks with minimal compromise of the quality. Quality evaluation and assessment of these medical videos transmitted over wireless networks is another important research area that requires further exploration and attention. In this paper, we have conducted an in-depth study of video quality assessment for compressed wireless capsule endoscopy (WCE) videos. Our study includes the performance evaluation of several state-of-the-art objective video quality metrics in terms of determining the quality of compressed WCE videos. Subjective video quality experiments were conducted with the assistance of experts and non-experts in order to predict the diagnostic and visual quality of these medical videos, respectively. The evaluation of the metrics is based on three major performance metrics that include, correlation between the subjective and objective scores, relative statistical performance and computation time. Results show that the metrics information fidelity criterion (IFC), visual information fidelity-(VIF) and especially pixel based VIF stand out as best performing metrics. Furthermore, our paper reports the performance of HEVC compression on medical videos and according to the results, it performs optimally in preserving the diagnostic and visual quality of WCE videos at Quantization Parameter (QP) values of up to 35 and 37 respectively.

Erratum to: Advances in Wireless Video Capsule Endoscopy

Erratum to: Advances in Wireless Video Capsule Endoscopy

Short article: Small intestinal mucosal injury in patients taking chemotherapeutic agents for solid cancers.

Chemotherapy for cancer is a systemic treatment often associated with side effects than can be debilitating and, in some cases, life-threatening. Few data are available on intestinal enterotoxicity. Wireless video capsule endoscopy (VCE) is a noninvasive method of imaging the small intestine. This study presents the results of VCE in patients with solid tumors undergoing antineoplastic regimens with agents, notably for toxicity for the gastrointestinal mucosa (i.e. carboplatin, cyclophosphamide, 5-fluorouracil, methotrexate, and cisplatin). The capsule endoscopy procedure was performed 4-13 days after the end of the antineoplastic course. Each patient received a polyethylene-glycol solution (1000 mg×2 in 2 l of water) for bowel preparation and fasted for 10 h before ingestion of the capsule. Videos were evaluated by one operator, supervised by a second operator, and conclusions were drawn by an expert reader. Twenty (age range: 38-77 years) patients were evaluated. The cecum was reached in 70% before exhaustion of the battery. The video capsule showed small widespread intestinal ulcerations in 25% and erosions in only one patient. The villus architecture appeared normal in all. VCE detected metastases in one patient with a melanoma. Few patients had more than one lesion. All capsules were passed in the stool. Our results suggest that chemotherapy in patients with solid cancers is associated with minimal visual small bowel injury. Factors other than damage of the intestinal mucosa causing loss of epithelium are likely involved in gastrointestinal toxicity and related symptoms.

Deep learning for polyp recognition in wireless capsule endoscopy images.

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. 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. 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. 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.