Contextual computer-aided detection: improving bright lesion detection in retinal images and coronary calcification identification in CT scans
- PMID: 21689964
- DOI: 10.1016/j.media.2011.05.004
Contextual computer-aided detection: improving bright lesion detection in retinal images and coronary calcification identification in CT scans
Abstract
Contextual information plays an important role in medical image understanding. Medical experts make use of context to detect and differentiate pathologies in medical images, especially when interpreting difficult cases. The majority of computer-aided diagnosis (CAD) systems, however, employ only local information to classify candidates, without taking into account global image information or the relation of a candidate with neighboring structures. In this paper, we present a generic system for including contextual information in a CAD system. Context is described by means of high-level features based on the spatial relation between lesion candidates and surrounding anatomical landmarks and lesions of different classes (static contextual features) and lesions of the same type (dynamic contextual features). We demonstrate the added value of contextual CAD for two real-world CAD tasks: the identification of exudates and drusen in 2D retinal images and coronary calcifications in 3D computed tomography scans. Results show that in both applications contextual CAD is superior to a local CAD approach with a significant increase of the figure of merit of the Free Receiver Operating Characteristic curve from 0.84 to 0.92 and from 0.88 to 0.98 for exudates and drusen, respectively, and from 0.87 to 0.93 for coronary calcifications.
Copyright © 2011 Elsevier B.V. All rights reserved.
Similar articles
-
Relationship between coronary artery disease and epicardial adipose tissue quantification at cardiac CT: comparison between automatic volumetric measurement and manual bidimensional estimation.Acad Radiol. 2010 Jun;17(6):727-34. doi: 10.1016/j.acra.2010.01.015. Epub 2010 Apr 3. Acad Radiol. 2010. PMID: 20363161
-
Coronary CTA: stenosis classification and quantification, including automated measures.J Cardiovasc Comput Tomogr. 2009 Nov-Dec;3 Suppl 2:S109-15. doi: 10.1016/j.jcct.2009.10.010. Epub 2009 Oct 30. J Cardiovasc Comput Tomogr. 2009. PMID: 20129518 Review.
-
Commercially available computer-aided detection system for pulmonary nodules on thin-section images using 64 detectors-row CT: preliminary study of 48 cases.Acad Radiol. 2009 Aug;16(8):924-33. doi: 10.1016/j.acra.2009.01.030. Epub 2009 Apr 25. Acad Radiol. 2009. PMID: 19394873
-
Detection of coronary calcifications from computed tomography scans for automated risk assessment of coronary artery disease.Med Phys. 2007 Apr;34(4):1450-61. doi: 10.1118/1.2710548. Med Phys. 2007. PMID: 17500476
-
[Arteriography, endoscopy and periscopy: simultaneous digital imaging].Bull Mem Acad R Med Belg. 2000;155(3-4):189-94. Bull Mem Acad R Med Belg. 2000. PMID: 11143791 Review. French.
Cited by
-
A Neoteric Feature Extraction Technique to Predict the Survival of Gastric Cancer Patients.Diagnostics (Basel). 2024 May 1;14(9):954. doi: 10.3390/diagnostics14090954. Diagnostics (Basel). 2024. PMID: 38732368 Free PMC article.
-
Machine Learning for Assessment of Coronary Artery Disease in Cardiac CT: A Survey.Front Cardiovasc Med. 2019 Nov 26;6:172. doi: 10.3389/fcvm.2019.00172. eCollection 2019. Front Cardiovasc Med. 2019. PMID: 32039237 Free PMC article. Review.
-
A Review on Recent Developments for Detection of Diabetic Retinopathy.Scientifica (Cairo). 2016;2016:6838976. doi: 10.1155/2016/6838976. Epub 2016 Sep 29. Scientifica (Cairo). 2016. PMID: 27777811 Free PMC article. Review.
-
Automatic differentiation of color fundus images containing drusen or exudates using a contextual spatial pyramid approach.Biomed Opt Express. 2016 Feb 2;7(3):709-25. doi: 10.1364/BOE.7.000709. eCollection 2016 Mar 1. Biomed Opt Express. 2016. PMID: 27231583 Free PMC article.
-
Efficient Small Blob Detection Based on Local Convexity, Intensity and Shape Information.IEEE Trans Med Imaging. 2016 Apr;35(4):1127-37. doi: 10.1109/TMI.2015.2509463. Epub 2015 Dec 17. IEEE Trans Med Imaging. 2016. PMID: 26685229 Free PMC article.
Publication types
MeSH terms
Grants and funding
LinkOut - more resources
Full Text Sources
Medical
Miscellaneous