DETECTION OF NORMALITY/PATHOLOGY ON CHEST RADIOGRAPHS USING LBP

Juan Manuel Carrillo-de-Gea, Ginés García-Mateos

2010

Abstract

Since the discovery of X-rays and their applications, medical imaging has been a great help for radiologists in the diagnosis of diseases. In recent years, there has been a great effort in the computer vision community in the research of systems for the analysis and extraction of useful information from medical images. In this scenario, we have designed, implemented and validated a novel method to detect normality/pathology in chest radiographs, which constitutes the core of a computer-aided detection (CADe) system. Although the problem addressed is very complex and little explored, our approach is completely automatic, starting from the location of areas of interest using template matching techniques. The main novelty of our contribution is the application of a transformation known as local binary patterns (LBP) to these areas. LBP histograms are then used as input features for a classification system, which is ultimately responsible for the decision of normality/pathology. The results of our preliminary experiments are quite promising. With success rates in the best cases close to 90%, we believe that increased performance could be obtained with bigger training sets and more advanced classification systems, which will make these systems to be fully viable in the near future.

References

  1. Campadelli, P. and Casiraghi, E. (2005). Lung Field Segmentation in Digital Postero-Anterior Chest Radiographs. In PRIA, volume 3687 of LNCS, pages 736- 745. Springer Heidelberg.
  2. Fleckenstein, P. and Tranum-Jensen, J. (2001). Anatomy in Diagnostic Imaging. Blackwell Science, 2 edition.
  3. Hao, B., Leung, C. K.-S., Camorlinga, S., Reed, M. H., Bunge, M. K., Wrogemann, J., and Higgins, R. J. (2008). A Computer-Aided Change Detection System for Paediatric Acute Intracranial Haemorrhage. In C3S2E 7808, pages 109-111, New York. ACM.
  4. Iakovidis, D. K., Keramidas, E. G., and Maroulis, D. (2008). Fuzzy Local Binary Patterns for Ultrasound Texture Characterization. In IAR, volume 5112 of LNCS, pages 750-759. Springer Heidelberg.
  5. Kallergi, M. (2005). Evaluation Strategies for MedicalImage Analysis and Processing Metodologies. In Medical Image Analysis Methods, chapter 12, pages 433-471. CRC Press.
  6. Ojala, T., Pietikäinen, M., and Harwood, D. (1996). A comparative study of texture measures with classification based on feature distributions. Pattern Recognition, 29(1):51-59.
  7. Oliver, A., Llad, X., Freixenet, J., and Mart, J. (2007). False Positive Reduction in Mammographic Mass Detection Using Local Binary Patterns. In MICCAI 7807, volume 4791 of LNCS, pages 286-293. Springer Heidelberg.
  8. Papadopoulos, A. N., Plissiti, M. E., and Fotiadis, D. I. (2005). Medical-Image Processing and Analysis for CAD Systems. In Medical Image Analysis Methods, The Electrical Engineering and Applied Signal Processing Series, chapter 2, pages 51-86. CRC Press, Boca Raton, FL, USA.
  9. Park, M., Jin, J. S., and Wilson, L. S. (2004). Detection of Abnormal Texture in Chest X-rays with Reduction of Ribs. In VIP 7805, pages 71-74, Darlinghurst, Australia. Australian Computer Society, Inc.
  10. Sørensen, L., Shaker, S. B., and de Bruijne, M. (2008). Texture Classification in Lung CT Using Local Binary Patterns. In MICCAI 7808, volume 5241 of LNCS, pages 934-941. Springer Heidelberg.
Download


Paper Citation


in Harvard Style

Manuel Carrillo-de-Gea J. and García-Mateos G. (2010). DETECTION OF NORMALITY/PATHOLOGY ON CHEST RADIOGRAPHS USING LBP . In Proceedings of the First International Conference on Bioinformatics - Volume 1: BIOINFORMATICS, (BIOSTEC 2010) ISBN 978-989-674-019-1, pages 167-172. DOI: 10.5220/0002747001670172


in Bibtex Style

@conference{bioinformatics10,
author={Juan Manuel Carrillo-de-Gea and Ginés García-Mateos},
title={DETECTION OF NORMALITY/PATHOLOGY ON CHEST RADIOGRAPHS USING LBP},
booktitle={Proceedings of the First International Conference on Bioinformatics - Volume 1: BIOINFORMATICS, (BIOSTEC 2010)},
year={2010},
pages={167-172},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002747001670172},
isbn={978-989-674-019-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Bioinformatics - Volume 1: BIOINFORMATICS, (BIOSTEC 2010)
TI - DETECTION OF NORMALITY/PATHOLOGY ON CHEST RADIOGRAPHS USING LBP
SN - 978-989-674-019-1
AU - Manuel Carrillo-de-Gea J.
AU - García-Mateos G.
PY - 2010
SP - 167
EP - 172
DO - 10.5220/0002747001670172