Feature extraction for abnormality detection in capsule endoscopy images

2022 ◽  
Vol 71 ◽  
pp. 103219
Author(s):  
Zahra Amiri ◽  
Hamid Hassanpour ◽  
Azeddine Beghdadi
Keyword(s):  
Feature Extraction ◽  
Capsule Endoscopy ◽  
Abnormality Detection

scholarly journals Computer-Aided Diagnosis for Capsule Endoscopy: From Inception to Future

2019 ◽  
Vol 8 (4) ◽  
pp. 12261-12273
Keyword(s):  
Capsule Endoscopy ◽  
Computer Aided Diagnosis ◽  
Current Status ◽  
Human Beings ◽  
Abnormality Detection ◽  
Gi Tract ◽  
Cad Systems ◽  
Cad System ◽  
Computer Aided ◽  
Aided Diagnosis

Background: Gastrointestinal (GI) tract abnormalities are most common across the world, and it is a significant threat to the health of human beings. Capsule endoscopy is a non-sedative, non-invasive and patient-friendly procedure for the diagnosis of GI tract abnormalities. However, it is very time consuming and tiresome task for physicians due to length of endoscopy videos. Thus computer-aided diagnosis (CAD) system is a must. Methods: This systematic review aims to investigate state-of-the-art CAD systems for automatic abnormality detection in capsule endoscopy by examining publications from scientific databases namely IEEE Xplore, Science Direct, Springer, and Scopus. Results: Based on defined search criteria and applied inclusion and exclusion criteria, 44 articles are included out of 187. This study presents the current status and analysis of CAD systems for capsule endoscopy. Conclusion: Publicly available larger dataset and a deep learning based CAD system may help to improve the efficiency of automated abnormality detection in capsule endoscopy.

scholarly journals A Computer-Aided Method for Digestive System Abnormality Detection in WCE Images

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Zahra Amiri ◽  
Hamid Hassanpour ◽  
Azeddine Beghdadi
Keyword(s):  
Feature Extraction ◽  
Detection System ◽  
Main Idea ◽  
Region Of Interest ◽  
Gastrointestinal Diseases ◽  
Support Vector ◽  
Abnormality Detection ◽  
Video Frames ◽  
Roi Extraction ◽  
Wireless Capsule

Wireless capsule endoscopy (WCE) is a powerful tool for the diagnosis of gastrointestinal diseases. The output of this tool is in video with a length of about eight hours, containing about 8000 frames. It is a difficult task for a physician to review all of the video frames. In this paper, a new abnormality detection system for WCE images is proposed. The proposed system has four main steps: (1) preprocessing, (2) region of interest (ROI) extraction, (3) feature extraction, and (4) classification. In ROI extraction, at first, distinct areas are highlighted and nondistinct areas are faded by using the joint normal distribution; then, distinct areas are extracted as an ROI segment by considering a threshold. The main idea is to extract abnormal areas in each frame. Therefore, it can be used to extract various lesions in WCE images. In the feature extraction step, three different types of features (color, texture, and shape) are employed. Finally, the features are classified using the support vector machine. The proposed system was tested on the Kvasir-Capsule dataset. The proposed system can detect multiple lesions from WCE frames with high accuracy.

scholarly journals Automated Hertbeat Abnormality Detection Using Realtime R-Assisted Lightweight Feature Extraction Algorithm

2018 ◽  
Author(s):  
Diptangshu Pandit ◽  
Chengyu Liu ◽  
Li Zhang
Keyword(s):  
Feature Extraction ◽  
Classification Scheme ◽  
Nearest Neighbor ◽  
Abnormality Detection ◽  
K Nearest Neighbor ◽  
Heartbeat Classification ◽  
Ecg Signals ◽  
Feature Extraction Algorithm ◽  
Extraction Algorithm ◽  
Electrocardiogram Ecg

Automated Electrocardiogram (ECG) processing is an important technique which helps in identifying abnormalities in the heart before any formal diagnosis. This research presents a real-time and lightweight R-assisted feature extraction algorithm and a heartbeat classification scheme which achieves highly accurate abnormality detection. In the proposed algorithm, we extract fifteen features from each heartbeat taken from raw Lead-II ECG signals. The features carry medically valuable information such as locations, amplitude and energy of ECG waves (P, Q, R, S, T waves) which are then used for detection of any abnormality that might be present in the heartbeat using various classification algorithms. We have used four popular databases from Physionet and extracted ten thousand ECG signals from each for training the models and benchmarking results. Four classification models i.e. Naïve Bays, k-Nearest Neighbor, Neural Network, Decision Tree were used for abnormality detection validating the efficiency of the system.

Sign in / Sign up

Export Citation Format

Share Document