Graph Convolutional Neural Network For Weakly Supervised Abnormality Localization In Long Capsule Endoscopy Videos

IntroductionManual review and annotation of a capsule endoscopy (CE) video requires a considerable amount of reviewing time. The diagnostic accuracy of this process may decrease over time due to reviewer...

This paper proposes an approach to eliminate redundant images adaptively for Wireless Capsule Endoscopy (WCE) video summarization by considering temporal correlation and feature similarity between adjacent WCE frames. The color and texture features, generated by HSV color histogram model and Gray Level Co-occurrence Matrix, have been taken into account. It is noted that frames from different WCE videos may have different dynamic information ranges. Hence a data-driven threshold termed as W-parametric mean value threshold (W-MVT) is developed to improve robustness of the proposed method. By comparing the color-texture feature similarity of adjacent WCE frames with W-MVT sequentially, the temporal correlated images with certain similarity are grouped into the same clip. Eventually, to consider gradient varying characteristic in one clip, the adaptive K-means clustering algorithm is adopted to keep key frames while remove redundant frames further. Experimental results show that two evaluation indicators-F-measure and compression ratio achieve 81.94% and 80.31%, which validates the effectiveness of the proposed WCE redundant image elimination (WCE-RIE) method.

Deep chroma prediction of Wyner–Ziv frames in distributed video coding of 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.

Purpose: Wireless video capsule endoscopy (VCE) is a new technology that enables us to visualize the entire small bowel mucosa. It involves swallowing a video capsule endoscope, which is painless and relatively safe. Its use has been established for suspected small bowel bleeding, and the role of capsule endoscopy in the investigation of inflammatory bowel disease, iatrogenic disease, polyposis syndromes and celiac disease is evolving. Aim: To describe the overall experience of video capsule endoscopy in a large tertiary care center. Methods: All charts of patient who underwent VCE between 2001 and 2005 were retrospectively reviewed. There were 466 charts available with the complete VCE reports. Results: There were 466 patients who underwent VCE. The mean age was 59.5 years (range 7–90). There were 265 female patients and 201 male patients. The most common indication for the procedure was obscure gastrointestinal bleeding (84.9%), followed by abdominal pain (8.8%), Crohn's (7.1%), diarrhea (5.4%) and abnormal imaging (3.2%). A possible cause of obscure gastrointestinal bleeding was identified in 76.8% of patients. VCE identified a possible cause of abdominal pain and diarrhea in 41.8% and 28% respectively. 16% of patients with diarrhea were found to have newly diagnosed Crohn's. 57.6% of patients with colonic Crohn's disease were found to have small bowel involvement. The etiology of abnormal imaging was found in 60% of patients. Small intestinal mass was identified in 3.6% of patients and 88.3% of these patients presented with obscure gastrointestinal bleeding. Conclusions: VCE is a clear choice for evaluation of obscure gastrointestinal bleeding VCE is an important tool in diagnosing previously unrecognized Crohn's disease. VCE is an important tool in diagnosing upper gastrointestinal involvement in established colonic Crohn's disease. VCE is an important supplementary diagnostic tool in investigating not only obscure gastrointestinal bleeding but also Crohn's disease.

Wireless capsule endoscopy (WCE) is a non-invasive video technology to detect small intestinal diseases, such as bleeding. It provides straight vision of patient's entire gastrointestinal (GI) tract, however examining large amount of images by physician takes longer time thus computer-aided scheme draws attention. In this paper, an effective features extraction scheme is proposed for automatic bleeding frame detection in WCE video. Instead of using red (R), green (G), and blue (B) plane separately a transform plane consisting of red to green pixel intensity ratio is used. Also rather than considering individual pixel, a surrounding neighborhood block of that individual pixel is considered which mitigates individual pixel randomness problem. A simple but consistent block statistic, namely maximum value of a block, is chosen as representative feature for each block. Histogram is found by utilizing all block maxima and frequency of histogram is considered as feature. For the purpose of classification, k-nearest neighbors (KNN) classifier is employed. Extensive experimentation is carried out upon several WCE videos, which are collected from a publicly available database and satisfactory performance result is obtained in comparison to some of the exiting methods.

Wireless Capsule Endoscopy (WCE) is a relatively new technology (FDA approved in 2002) allowing doctors to view most of the small intestine. WCE transmits more than 50,000 video frames per examination and the visual inspection of the resulting video is a highly time-consuming task even for the experienced gastroenterologist. Typically, a medical clinician spends one or two hours to analyze a WCE video. To reduce the assessment time, it is critical to develop a technique to automatically discriminate digestive organs and shots each of which consists of the same or similar shots. In this paper a multi-level WCE video segmentation methodology is presented to reduce the examination time.

Purpose: Carcinoid tumors are a heterogeneous group. Midgut carcinoid accounts for approximately 50% of all carcinoid tumors in adults, the majority of which arise in the ileum. Since the clinical symptoms are often vague and unrecognized until disease becomes advanced, a majority of patients have metastatic disease at time of diagnosis. It is important to determine the location of the primary since, to a considerable degree, it directs management and predicts outcome. The aim of this study was to assess the utility of wireless video capsule endoscopy in identifying a suspected intestinal primary in patients with demonstrated metastatic carcinoid and no detectable primary on standard investigation. Methods: A retrospective chart review was performed and 24 patients with metastatic carcinoid of unknown primary origin were encountered. Patients' baseline characteristics, clinical presentations, radiological evaluations, chemistries, and therapies were all recorded. All patients underwent wireless video capsule endoscopy in search of a primary lesion after having negative localizing or nonspecific findings on EGD/Colonoscopy, Small Bowel Series, CT scan and OctreoScan®. Results: Of the 24 patients, 8 (33.3%) had positive findings on capsule examination, suggesting a primary carcinoid tumor. All had previously diagnosed metastatic carcinoid on needle biopsy. 5 of these (62.5%) had an ileal primary, 1 (12.5%) had a jejeunal primary, and 2 (25%) were simply classified as a mid small bowel primary. In all cases this positive finding changed management. 7 of the 8 patients (87.5%) underwent surgery and had confirmed small bowel carcinoid tumors. 1 patient who had very advanced disease and was not operated upon had a change in his chemotherapy regimen after the positive capsule finding. Of the 16 patients who had negative capsule studies, 6 had metastatic carcinoid diagnosed by liver biopsy, 1 had an orbit biopsy, 1 had a mesenteric mass biopsy, 1 had a lymph node biopsy, and 3 had significantly abnormal chemical markers (urine 5-HIAA, chromogranin A, and serotonin) strongly indicating carcinoid. No primary was found in 12 of the 16 patients, whereas in 4 patients the primary was proven by biopsy to be in the pancreas. Conclusions: We conclude that wireless video capsule endoscopy is useful in detecting carcinoid tumors originating in the small bowel and not detected by any other conventional method. This localization is significantly important in directing treatment and management of these patients.

Wireless capsule endoscopy (WCE) is a non-invasive imaging technique to examine the entire small intestine. This paper presents a novel hierarchical key frame extraction algorithm based on the saliency map to automatically select a small number of key informative frames in the WCE video to assist the diagnostic process. We start from calculating the saliency map and extracting the inside colour, texture and shape features. We then compute the image information entropies with adapted weights on three features; calculate the differences of entropies in the successive frames and extract the first level key frames to divide the video into multi-segments. Finally, the mean shift clustering method is applied on each segment to obtain the final key frames. The proposed technique achieves the fidelity of 95.07% and the compression ratio of 87.9% on average, validating that the proposed scheme is highly promising for the key frame extraction in the WCE video.

Wireless capsule endoscopy (WCE) has been validated to be an important tool in the evaluation of gastrointestinal (GI) tract. Compared with traditional endoscope technologies, its non-invasiveness property meets with great favor of patients. However, from physician's point of view, WCE video suffers from low resolution, limited illumination, irregular movement, more importantly, imbalanced rate of abnormality which brings a lot of challenges for diagnosis. These challenges motivate us to devise an approach to guide the physicians to focus on the informative frames which could be convenient for review of the content of the GI tract. This paper presents a novel approach for automatic selection of the WCE video frames with lumen and coherent motility. We adopt lumen detection based on mean shift to provide robust and reliable selection of lumen. Together with the evaluation of coherent motility, we can provide a full and fast approach to select the informative frames for diagnosis. The experiments on real date are presented to show the performance of our proposed method.

Wireless Capsule Endoscopy (WCE) is a painless and noninvasive technique that allows physicians to visualize the entire small bowel. Before WCE was introduced, examining the entire small bowel was impossible without surgical procedure. Although WCE is a technology breakthrough, the manual video diagnosis session is time consuming and is prone to human cognition errors. Therefore, gastroenterologists urge computer vision researchers to develop computer-aided diagnosis systems to assist the review session. In this paper, we would like to present an ulcer detection scheme that identifies ulcers in WCE video. A saliency map is created by means of channel mixer to highlight suspicious regions. Once the suspicious regions are identified, we extract textural features along the contour and classify them using a trained classifier for ulcer validation.

Wireless video capsule endoscopy (CE) is a new technology that allows visualization of the entire small intestinal mucosa. It is indicated for the evaluation of obscure gastrointestinal bleeding (OGIB) and other disorders of the small intestine. Studies to date suggest that CE is safe and associated with few adverse events. A concern, which has not been studied, is the potential effect of CE on implanted cardiac devices such as implantable cardiac defibrillators (ICD) and other electromedical devices. We previously found CE to be safe in patients with cardiac pacemakers. The primary aim of this study was to evaluate the safety of CE in patients with ICDs who were being evaluated for OGIB. In addition, a secondary aim of the study was to determine whether ICDs had any effect on the images captured by CE. Patients referred for the evaluation of OGIB and who also had an ICD were enrolled into the study after informed consent. Five consecutive patients (four females and one male; mean age: 72 yr; range: 60-81 yr) with ICDs were studied. All patients had transvenous endocardial ICDs located in the chest. Prior to CE, patients had a baseline electrocardiogram (ECG) and ICD interrogation. Thereafter, CE was performed in a hospital setting with telemetry monitoring performed simultaneously. A post-procedure ICD interrogation was carried out to evaluate changes in programmed parameters. A cardiologist and ICD nurse specialist together reviewed both the telemetry monitor and the post-procedure ICD interrogation on each patient. When CE studies were reviewed, observations pertaining to technical difficulties and interference with video imaging were documented. No arrhythmia or other adverse cardiac events were noted during capsule transmission. No interference by the ICD on the CE video images was seen. CE was performed safely in these five patients with ICDs, and was not associated with any adverse cardiac events. ICDs also do not appear to interfere with video capsule imaging.

Evaluation of Deep Learning Models in Search by Example using Capsule Endoscopy Images

Automatic lesion detection in capsule endoscopy based on color saliency: closer to an essential adjunct for reviewing software

The direct view of the inner tract of the small intestine is not feasible until a recently revolutionary imaging technology, wireless capsule endoscopy (WCE), appeared in 2001. However, interpretation of the produced video data for the digestive tract on each patient is left to naked eyes of medical staffs. Such a process is very tedious and time-consuming with the average inspection time about two hours for a whole WCE video. To overcome this big problem, automatic WCE video analysis is required. In this paper, we propose a comparative study of several image based features that may be suitable for WCE video abstract, which may be a good candidate to reduce the burden of physicians. Color, texture and motion features built from images are investigated and compared to show their performance in representing video content for a WCE video abstract. Preliminary experimental results of these features for WCE video abstract are also demonstrated and discussed. It is found that textural and motion features may be suitable candidates for visual frame depiction for WCE video abstract in terms of visual content representation and compression ratio. Clinical validation of our work remains to be implemented in the near future.