Texture-Based Polyp Detection in Colonoscopy

Ameling, Stefan; Wirth, Stephan; Paulus, Dietrich; Lacey, Gerard; Vilariño, Fernando

doi:10.1007/978-3-540-93860-6_70

Cited by 113 publications

(67 citation statements)

References 7 publications

(4 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this is not a problem for our use-case since the training is done offline, where time is less critical. Our implementation of the random forest classifier uses the version provided by the Weka machine learning library 5 [16], which is a collection of algorithms for machine learning and data mining. We chose the random forest approach, because it is fast and achieves good results [49].…”

Section: Multi-class Global-feature-based Eirmentioning

confidence: 99%

Efficient disease detection in gastrointestinal videos – global features versus neural networks

Pogorelov

Riegler

Eskeland

et al. 2017

Multimed Tools Appl

View full text Add to dashboard Cite

Analysis of medical videos from the human gastrointestinal (GI) tract for detection and localization of abnormalities like lesions and diseases requires both high precision and recall. Additionally, it is important to support efficient, real-time processing for live feedback during (i) standard colonoscopies and (ii) scalability for massive population-based screening, which we conjecture can be done using a wireless video capsule endoscope (camera-pill). Existing related work in this field does neither provide the necessary combination of accuracy and performance for detecting multiple classes of abnormalities simultaneously nor for particular disease localization tasks. In this paper, a complete end-toend multimedia system is presented where the aim is to tackle automatic analysis of GI tract videos. The system includes an entire pipeline ranging from data collection, processing and analysis, to visualization. The system combines deep learning neural networks, information retrieval, and analysis of global and local image features in order to implement multi-class classification, detection and localization. Furthermore, it is built in a modular way, so that it can be easily extended to deal with other types of abnormalities. Simultaneously, the system is developed for efficient processing in order to provide real-time feedback to the doctors and for scalability reasons when potentially applied for massive population-based algorithmic screenings in the future. Initial experiments show that our system has multiclass detection accuracy and polyp localization precision at least as good as state-of-the-art systems, and provides additional novelty in terms of real-time performance, low resource consumption and ability to extend with support for new classes of diseases.

show abstract

Section: Multi-class Global-feature-based Eirmentioning

confidence: 99%

Efficient disease detection in gastrointestinal videos – global features versus neural networks

Pogorelov

Riegler

Eskeland

et al. 2017

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…The process of creating algorithms that will correctly deal with artifacts or removing them from the images imposes additional difficulties. 24,26,27 Another issue arises in the classification phase of the medical images. Yu et al (2016) and Zhang et al (2016) have noted the fact that there is a high inter-class similarity and intra-class variation regarding colon polyps, rendering it difficult for machine learning algorithms to correctly classify the polyps.…”

Section: Limitations Of the Proposed Methodsmentioning

confidence: 99%

Computer-Aided Diagnosis in Colorectal Cancer: Current Concepts and Future Prospects

Ioanovici

Feier

Ţilea

et al. 2017

Journal of Interdisciplinary Medicine

View full text Add to dashboard Cite

Colorectal cancer is an important health issue, both in terms of the number of people affected and the associated costs. Colonoscopy is an important screening method that has a positive impact on the survival of patients with colorectal cancer. The association of colonoscopy with computer-aided diagnostic tools is currently under researchers' focus, as various methods have already been proposed and show great potential for a better management of this disease. We performed a review of the literature and present a series of aspects, such as the basics of machine learning algorithms, different computational models as well as their benchmarks expressed through measurements such as positive prediction value and accuracy of detection, and the classification of colorectal polyps. Introducing computer-aided diagnostic tools can help clinicians obtain results with a high degree of confidence when performing colonoscopies. The growing field of machine learning in medicine will have a big impact on patient management in the future.

show abstract

“…In the work shown in [7], polyps are detected by combining wavelets coefficients extraction and co-ocurrence matrices and then learning via neural networks. A method which combines the use of local binary patterns and grey-level co-ocurrence matrices is presented in [1].…”

Section: Related Workmentioning

confidence: 99%

Integration of Valley Orientation Distribution for Polyp Region Identification in Colonoscopy

Bernal

Sánchez

Vilariño

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This work presents a region descriptor based on the integration of the information that the depth of valleys image provides. The depth of valleys image is based on the presence of intensity valleys around polyps due to the image acquisition. Our proposed description method consists of defining, for each point, a series of radial sectors around it and then accumulate the maxima of the depth of valleys image only if the orientation of the intensity valley coincides with the orientation of the sector above. We apply our descriptor to a prior segmentation of the images and we present promising results on polyp detection, outperforming another approach that also integrate depth of valleys information.

show abstract

Texture-Based Polyp Detection in Colonoscopy

Cited by 113 publications

References 7 publications

Efficient disease detection in gastrointestinal videos – global features versus neural networks

Efficient disease detection in gastrointestinal videos – global features versus neural networks

Computer-Aided Diagnosis in Colorectal Cancer: Current Concepts and Future Prospects

Integration of Valley Orientation Distribution for Polyp Region Identification in Colonoscopy

Contact Info

Product

Resources

About