• Corpus ID: 221447350

SURF-SVM Based Identification and Classification of Gastrointestinal Diseases in Wireless Capsule Endoscopy

  title={SURF-SVM Based Identification and Classification of Gastrointestinal Diseases in Wireless Capsule Endoscopy},
  author={Vanshika Vats and Pooja Goel and Amodini Agarwal and Nidhi Goel},
  journal={arXiv: Image and Video Processing},
Endoscopy provides a major contribution to the diagnosis of the Gastrointestinal Tract (GIT) diseases. With Colon Endoscopy having its certain limitations, Wireless Capsule Endoscopy is gradually taking over it in the terms of ease and efficiency. WCE is performed with a miniature optical endoscope which is swallowed by the patient and transmits colour images wirelessly during its journey through the GIT, inside the body of the patient. These images are used to implement an effective and… 

Figures and Tables from this paper

Towards a better understanding of annotation tools for medical imaging: a survey
This study provides an intensive review of the popular annotation tools and shows their successful usage in annotating medical imaging dataset to guide researchers in this area.


Automatic lesion detection in wireless capsule endoscopy — A simple solution for a complex problem
This paper presents a computationally efficient and effective approach to cope with automatic detection of possible abnormalities in the WCE videos and consequently with the reduction of the time required for the W CE inspection.
An objective comparison of detection and segmentation algorithms for artefacts in clinical endoscopy
A comprehensive analysis of the submissions to the first edition of the Endoscopy Artefact Detection challenge is presented, revealing the shortcomings of current training strategies and highlighting the need for developing new optimal metrics to accurately quantify the clinical applicability of methods.
How Should We Do Capsule Reading
A Comparison of SIFT and SURF
Two different methods for scale and rotation invariant interest point/feature detector and descriptor are presented: Scale Invariant Feature Transform (SIFT) and Speed Up Robust Features (SURF).
New features for wireless capsule endoscopy polyp detection
A new feature descriptor for automatic detection of frames with polyp in Wireless Capsule Endoscopy (WCE) images is presented based on the fact that the polyp disease exhibits discriminating features when the WCE images are decomposed into different resolution levels.
Ratsnake: A Versatile Image Annotation Tool with Application to Computer-Aided Diagnosis
Ratsnake is presented, a publicly available generic image annotation tool providing annotation efficiency, semantic awareness, versatility, and extensibility, features that can be exploited to transform it into an effective CAD system.
Automatic detection of colonic polyps and tumor in wireless capsule endoscopy images using hybrid patch extraction and supervised classification
  • C. SindhuVysak Valsan
  • Computer Science
    2017 International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS)
  • 2017
In this prospective system, feature based classification is performed using Neural Network (NN) classifier for detecting colonic polyps and tumors accurately from the WCE images with an accuracy of about 97.5%.
Weakly-Supervised Lesion Detection in Video Capsule Endoscopy Based on a Bag-of-Colour Features Model
This paper investigates a weakly-supervised approach for lesion detection, which requires image-level instead of pixel-level annotations for training, and offers a considerable advantage with respect to the efficiency of the annotation process.
Software for enhanced video capsule endoscopy: challenges for essential progress
An in-depth critical analysis is presented that aims to inspire and align the agendas of the two scientific groups in the field of small bowel diseases.
WCE Abnormality Detection Based on Saliency and Adaptive Locality-Constrained Linear Coding
A new computer-aided system using novel features is proposed in this paper to classify WCE images automatically and exhibits a promising overall recognition accuracy of 88.61%, validating the effectiveness of the proposed method.