Automatic Extraction and Categorization of Lung Abnormalities from HRCT Data in MDR/XDR TB Patients

  • Saher Lahouar
  • Clifton E. Barry3rd
  • Praveen Paripati
  • Sandeep Somaiya
  • Yentram Huyen
  • Alexander Rosenthal
  • Michael Tartakovsky
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 145)

Abstract

An ancient disease, tuberculosis (TB) remains one of the major causes of disability and death worldwide. In 2006, 9.2 million new cases of TB emerged and killed 1.7 million people. We report on the development of tools to help in the detection of lesions and nodules from High Resolution Computed Tomography (HRCT) scans and changes in total lesion volumes across a study. These automated tools are designed to assist radiologists, clinicians and scientists assess patients’ responses to therapies during clinical studies. The tools are centered upon a rule-based system that initially segments the lung from HRCT scans and then categorizes the different components of the lung as normal or abnormal. A layered segmentation process, utilizing a combination of adaptive thresholding, three-dimensional region growing and component labeling is used to successively peel off outside entities, isolating lung and trachea voxels. Locating the Carina allows logical labeling of the trachea and left/right lungs. Shape and texture analysis are used to validate and label normal vascular tree voxels. Remaining abnormal voxels are clustered on density, gradient and texture-based criteria. Several practical problems that arise due to large changes in lung morphology due to TB and patients’ inability to hold their breath during scan operations need to be addressed to provide a viable computational solution. Comparisons of total common volumes of lesions by size for a given patient across multiple visits are in concordance with expert radiologist’s manual measurements.

Keywords

Lung Abnormalities HRCT Pulmonary Tuberculosis MDR/XDR TB Automatic Extraction Lung Nodules 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ceresa, M., Artaechevarria, X., Munoz-Barrutia, A., Ortiz-de-Solorzano, C.: Automatic leakage detection and recovery for airway tree extraction in chest CT images. In: 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, April 14-17, pp. 568–571 (2010)Google Scholar
  2. 2.
    Gao, Q., Wang, S., Zhao, D., Liu, J.: Accurate Lung Segmentation For X-ray CT Images. In: Third International Conference on Natural Computation, ICNC 2007, August 24-27, vol. 2, pp. 275–279 (2007)Google Scholar
  3. 3.
    Guo, S., Wu, X.: Automatic Segmentation and Quantitative Diagnosis of Pulmonary Parenchyma in Thoracic CT. In: The 1st International Conference on Bioinformatics and Biomedical Engineering, ICBBE 2007, July 6-8, pp. 668–670 (2007)Google Scholar
  4. 4.
    Hu, S., Hoffman, E.A., Reinhardt, J.M.: Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images. IEEE Transactions Medical Imaging 20(6), 490–498 (2001)CrossRefGoogle Scholar
  5. 5.
    Kim, H.S., Yoon, H.-S., Trung, K.N., Lee, G.S.: Automatic Lung Segmentation in CT Images Using Anisotropic Diffusion and Morphology Operation. In: 7th IEEE International Conference on Computer and Information Technology, CIT 2007, October 16-19, pp. 557–561 (2007)Google Scholar
  6. 6.
    Kim, H., Maekado, M., Tan, J.K., Ishikawa, S., Tsukuda, M.: Automatic extraction of ground-glass opacity shadows on CT images of the thorax by correlation between successive slices. In: 17th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2005, November 16, p. 607– 612 (2005)Google Scholar
  7. 7.
    Kim, H., Nakashima, T., Itai, Y., Maeda, S., Tan, J.K., Ishikawa, S.: Automatic detection of ground glass opacity from the thoracic MDCT images by using density features. In: International Conference on Control, Automation and Systems, ICCAS 2007, October 17-20, pp. 1274–1277 (2007)Google Scholar
  8. 8.
    Kim, R., Dasovich, G., Bhaumik, R., Brock, R., Furst, J.D., Raicu, D.S.: An investigation into the relationship between semantic and content based similarity using LIDC. In: Proceedings of the International Conference on Multimedia Information Retrieval (MIR 2010), pp. 185–192. ACM, New York (2010)Google Scholar
  9. 9.
    Li, Q., Li, F., Suzuki, K., Shiraishi, J., Abe, H., Engelmann, R., Nie, Y., MacMahon, H., Doi, K.: Computer-Aided Diagnosis in Thoracic CT. Seminars in Ultrasound, CT, and MRI 26(5), 357–363 (2005); Update of Chest Imaging-Part IGoogle Scholar
  10. 10.
    NIAID, (2010) weblink, http://www.niaid.nih.gov/topics/tuberculosis/Pages/Default.aspx (accessed August 31, 2010)
  11. 11.
    Rubin, G.D.: Data explosion: the challenge of multidetector-row CT. European Journal of Radiology 36(2), 74–80 (2000)CrossRefGoogle Scholar
  12. 12.
    Sluimer, I., Schilham, A., Prokop, M., van Ginneken, B.: Computer analysis of computed tomography scans of the lung: a survey. IEEE Transactions on Medical Imaging 25(4), 385–405 (2006)CrossRefGoogle Scholar
  13. 13.
    Tong, J., Zhao, D.-Z., Wei, Y., Zhu, X.-H., Wang, X.: Computer-Aided Lung Nodule Detection Based on CT Images. In: IEEE/ICME International Conference on Complex Medical Engineering, CME 2007, May 23-27, pp. 816–819 (2007)Google Scholar
  14. 14.
    Tong, J., Zhao, D.-Z., Yang, J.-Z., Wang, X.: Automated Detection of Pulmonary Nodules in HRCT Images. In: The 1st International Conference on Bioinformatics and Biomedical Engineering, ICBBE 2007, July 6-8, pp. 833–836 (2007)Google Scholar
  15. 15.
    van Rikxoort, E.M., de Hoop, B., van de Vorst, S., Prokop, M., van Ginneken, B.: Automatic Segmentation of Pulmonary Segments From Volumetric Chest CT Scans. IEEE Transactions on Medical Imaging 28(4), 621–630 (2009)CrossRefGoogle Scholar
  16. 16.
    van Rikxoort, E.M., Prokop, M., de Hoop, B., Viergever, M.A., Pluim, J., van Ginneken, B.: Automatic Segmentation of Pulmonary Lobes Robust Against Incomplete Fissures. IEEE Transactions on Medical Imaging 29(6), 1286–1296 (2010)CrossRefGoogle Scholar
  17. 17.
    van Rikxoort, E.M., Goldin, J.G., van Ginneken, B., Galperin-Aizenberg, M., Ni, C., Brown, M.S.: Interactively learning a patient specific k-nearest neighbor classifier based on confidence weighted samples. In: 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, April 14-17, pp. 556–559 (2010)Google Scholar
  18. 18.
    Zhou, J., Chang, S., Metaxas, D.N., Zhao, B., Ginsberg, M.S., Schwartz, L.H.: An Automatic Method for Ground Glass Opacity Nodule Detection and Segmentation from CT Studies. In: 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2006, August 30-September 3, pp. 3062–3065 (2006)Google Scholar
  19. 19.
    This research was partially supported by the Intramural Research Program of the National Institutes of Health, National Institute of Allergy and Infectious Diseases, and the Bill & Melinda Gates Foundation and Wellcome Trust through the Grand Challenges in Global Health Initiative (PI, Douglas Young, Imperial College, London)Google Scholar
  20. 20.
    This research was primarily supported by the National Institutes of Health, National Institute of Allergy and Infectious Diseases, Office of Cyber Informatics and Computational Biology funding to NET ESOLUTIONS CORPORATION (NETE)Google Scholar
  21. 21.
    This research utilizes proprietary computational algorithms and software tools developed by the NET ESOLUTIONS CORPORATION (NETE) teamGoogle Scholar

Copyright information

© Springer-Verlag GmbH Berlin Heidelberg 2012

Authors and Affiliations

  • Saher Lahouar
    • 1
  • Clifton E. Barry3rd
    • 3
  • Praveen Paripati
    • 1
  • Sandeep Somaiya
    • 1
  • Yentram Huyen
    • 2
  • Alexander Rosenthal
    • 2
  • Michael Tartakovsky
    • 2
  1. 1.NET ESOLUTIONS CORPORATIONMcLeanUSA
  2. 2.Office of Cyber Infrastructure and Computational Biology (OCICB)NIAID, NIHBethesdaUSA
  3. 3.Tuberculosis Research Section, Laboratory of Clinical Infectious Diseases, Division of Intramural ResearchNational Institute of Allergy and Infectious Diseases (NIAID), National Institutes of Health (NIH)BethesdaUSA

Personalised recommendations