Angular relational signature-based chest radiograph image view classification
In a computer-aided diagnosis (CAD) system, especially for chest radiograph or chest X-ray (CXR) screening, CXR image view information is required. Automatically separating CXR image view, frontal and lateral can ease subsequent CXR screening process, since the techniques may not equally work for both views. We present a novel technique to classify frontal and lateral CXR images, where we introduce angular relational signature through force histogram to extract features and apply three different state-of-the-art classifiers: multi-layer perceptron, random forest, and support vector machine to make a decision. We validated our fully automatic technique on a set of 8100 images hosted by the U.S. National Library of Medicine (NLM), National Institutes of Health (NIH), and achieved an accuracy close to 100%. Our method outperforms the state-of-the-art methods in terms of processing time (less than or close to 2 s for the whole test data) while the accuracies can be compared, and therefore, it justifies its practicality.
KeywordsAutomation Computer-aided diagnosis system Medical imaging Chest radiograph Angular relational signature Force histogram Frontal view Lateral view Classification Multi-layer perception Random forest Support vector machine
Authors would like to give thanks to Dr. Sameer Antani, staff scientist, Lister Hill National Center for Biomedical Communications (LHNCBC) for his advice and the dataset owned by the U.S. National Library of Medicine, National Institutes of Health (NIH), MD.
Compliance with ethical standards
This article does not contain any studies with human participants or animals performed by any of the authors.
Conflict of interest
Authors declare that they have no conflicts of interest.
- 1.(2006) Improving the diagnosis and treatment of smear-negative pulmonary and extrapulmonary tuberculosis among adults and adolescents: recommendations for HIV-prevalent and resource-constrained settings. World Health Organization GenevaGoogle Scholar
- 3.Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, inc., New YorkGoogle Scholar
- 5.Bosch A, Zisserman A, Munoz X (2007) Representing shape with a spatial pyramid kernel. In: ACM international conference on image and video retrieval, pp 401–408Google Scholar
- 9.Karargyris A, Siegelman J, Tzortzis D, Jaeger S, Candemir S, Xue Z, Santosh KC, Vajda S, Antani SK, Folio L, Thoma GR (2016) Combination of texture and shape features to detect pulmonary abnormalities in digital chest X-rays. Int J Comput Assist Radiol Surg 11(1):99–106. https://doi.org/10.1007/s11548-015-1242-x CrossRefPubMedGoogle Scholar
- 13.Matsakis P (1998) Structural spatial relations and image understanding. Ph.D. thesis, Universite de Toulouse III. https://doi.org/10.1007/978-3-642-14755-5
- 15.Matsakis P, Wendling L, Ni J (2010) A general approach to the fuzzy modeling of spatial relationships. In: Methods for handling imperfect spatial information. https://doi.org/10.1007/978-3-642-14755-5_3, pp 49–74
- 17.Platt J (1998) Fast training of support vector machines using sequential minimal optimization. In: Schoelkopf B, Burges C, Smola A (eds) Advances in kernel methods - support vector learning, MIT Press. http://research.microsoft.com/~jplatt/smo.html
- 19.Santosh KC, Candemir S, Jäger S, Karargyris A, Antani SK, Thoma GR, Folio L (2015) Automatically detecting rotation in chest radiographs using principal rib-orientation measure for quality control. Int J Pattern Recognit Artif Intell 29(2). https://doi.org/10.1142/S0218001415570013
- 20.Santosh KC, Vajda S, Antani S, Thoma GR (2016) Edge map analysis in chest X-rays for automatic pulmonary abnormality screening. Int J CARS :1–10. https://doi.org/10.1007/s11548-016-1359-6
- 24.Xue Z, You D, Candemir S, Jaeger S, Antani SK, Long LR, Thoma GR (2015) Chest x-ray image view classification. In: 28Th IEEE international symposium on computer-based medical systems. https://doi.org/10.1109/CBMS.2015.49, pp 66–71
- 25.You D, Antani SK, Demner-fushman D, Thoma GR (2014) A contour-based shape descriptor for biomedical image classification and retrieval. In: Coüasnon B, Ringger EK (eds) Document recognition and retrieval XXI, San Francisco, February 5-6, 2014. SPIE Proceedings, vol 9021, pp 90210L–90210L–12. SPIE. https://doi.org/10.1117/12.2042526