Small intestine bleeding detection using color threshold and morphological operation in WCE images

<span>Wireless capsule endoscopy (WCE) is a significant modern technique for observing the whole gastroenterological tract to diagnose various diseases like bleeding, ulcer, tumor, Crohn's disease, polyps etc in a non-invasive manner. However, it will make a substantial onus for physicians like human oversight errors with time consumption for manual checking of a vast amount of image frames. These problems motivate the researchers to employ a computer-aided system to classify the particular information from the image frames. Therefore, a computer-aided system based on the color threshold and morphological operation has been proposed in this research to recognize specified bleeding images from the WCE. Besides, A unique classifier, quadratic support vector machine (QSVM) has been employed for classifying the bleeding and non-bleeding images with the statistical feature vector in HSV color space. After extensive experiments on clinical data, 95.8% accuracy, 95% sensitivity, 97% specificity, 80% precision, 99% negative predicted value and 85% F1 score has been achieved, which outperforms some of the existing methods in this regard. It is expected that this methodology would bring a significant contribution to the WCE technology. </span>

Bleeding recognition technique in wireless capsule endoscopy images using fuzzy logic and principal component analysis

Wireless capsule endoscopy is the most innovative technology to perceive the entire gastrointestinal (GI) tract in recent times. It can diagnose inner diseases like bleeding, ulcer, tumor, Crohn's disease, and polyps. in a discretion way. It creates immense pressure and onus for clinicians to perceive a huge number of image frames, which is time-consuming and makes human oversight errors. Therefore a computer-automated system has been introduced for bleeding detection. A unique fuzzy logic technique is proposed to extract the specified bleeding and non-bleeding information from the image data. A particular quadratic support vector machine (QSVM) classifier is employed to classify the obtained statistical features from the bleeding and non-bleeding images incorporating principal component analysis (PCA). After extensive experiments on clinical data, 98% sensitivity, 98.4% accuracy, 98% specificity, 93% precision, 95.4% F1-score, and 99% negative predicted value have been achieved, which outperforms some of the states of art methods in this regard. It is optimistic that the proposed methodology would significantly contribute to bleeding detection techniques and diminish the additional onus of the physicians.

Explainable information retrieval using deep learning for medical images

Image segmentation is useful to extract valuable information for an efficient analysis on the region of interest. Mostly, the number of images generated from a real life situation such as streaming video, is large and not ideal for traditional segmentation with machine learning algorithms. This is due to the following factors (a) numerous image features (b) complex distribution of shapes, colors and textures (c) imbalance data ratio of underlying classes (d) movements of the camera, objects and (e) variations in luminance for site capture. So, we have proposed an efficient deep learning model for image classification and the proof-of-concept has been the case studied on gastrointestinal images for bleeding detection. The Ex plainable Artificial Intelligence (XAI) module has been utilized to reverse engineer the test results for the impact of features on a given test dataset. The architecture is generally applicable in other areas of image classification. The proposed method has been compared with state-of-the-art including Logistic Regression, Support Vector Machine, Artificial Neural Network and Random Forest. It has reported F1 score of 0.76 on the real world streaming dataset which is comparatively better than traditional methods.

The Impact of Novel Anticoagulants on the Upper Gastrointestinal Tract Mucosa

Background and objectives: Although treatment with novel oral non-vitamin K antagonist 3anticoagulants (NOACs) is associated with an overall decrease in hemorrhagic complications compared to warfarin, the incidence of gastrointestinal bleeding remains contradictory. Materials and Methods: After the exclusion of patients with pre-existing pathological lesions in the upper gastrointestinal tract (GIT) on esophageal-gastroduodenoscopy (EGD) at entry, a cohort of 80 patients (mean age of 74.8 ± 2.0 years) was randomly divided into four equivalent groups, treated with dabigatran, rivaroxaban, apixaban, or warfarin. Patients were prospectively followed up for three months of treatment, with a focus on anamnestic and endoscopic signs of bleeding. In addition, bleeding risk factors were evaluated. Results: In none of the patients treated with warfarin or NOACs was any serious or clinically significant bleeding recorded within the follow-up period. The incidence of clinical bleeding and endoscopically detected bleeding in the upper GT after three months of treatment was not statistically different among groups (χ2 = 2.8458; p = 0.41608). The presence of Helicobacter pylori (HP) was a risk factor for upper GIT bleeding (p < 0.05), while the use of proton pump inhibitors (PPIs) was a protective factor (p = 0.206; Spearman’s correlation coefficient = 0.205). We did not record any post-biopsy continued bleeding. Conclusions: No significant GIT bleeding was found in any of the treatment groups, so we consider it beneficial to perform routine EGD before the initiation of any anticoagulant therapy in patients with an increased risk of upper GIT bleeding. Detection and eradication of HP as well as preventive PPI treatment may mitigate the occurrence of endoscopic bleeding. Endoscopic biopsy during the NOAC treatment is safe.

Bleeding Detection in Gastrointestinal Images using Texture Classification and Local Binary Pattern Technique: A Review

Texture analysis has proven to be a breakthrough in many applications of computer image analysis. It has been used for classification or segmentation of images which requires an effective description of image texture. Due to high discriminative power and simplicity of computation, the local binary pattern descriptors have been used for distinguishing different textures and in extracting texture and color in medical images. This paper discusses performance of various texture classification techniques using Contourlet Transform, Discrete Fourier Transform, Local Binary Patterns and Lacunarity analysis. The study reveals that the incorporation of efficient image segmentation, enhancement and texture classification using local binary pattern descriptor detects bleeding region in human intestines precisely.