Advertisement

Journal of Digital Imaging

, Volume 26, Issue 2, pp 227–238 | Cite as

Extracting Fuzzy Classification Rules from Texture Segmented HRCT Lung Images

  • Manish Kakar
  • Arianna MencattiniEmail author
  • Marcello Salmeri
Article
  • 293 Downloads

Abstract

Automatic tools for detection and identification of lung and lesion from high-resolution CT (HRCT) are becoming increasingly important both for diagnosis and for delivering high-precision radiation therapy. However, development of robust and interpretable classifiers still presents a challenge especially in case of non-small cell lung carcinoma (NSCLC) patients. In this paper, we have attempted to devise such a classifier by extracting fuzzy rules from texture segmented regions from HRCT images of NSCLC patients. A fuzzy inference system (FIS) has been constructed starting from a feature extraction procedure applied on overlapping regions from the same organs and deriving simple if–then rules so that more linguistically interpretable decisions can be implemented. The proposed method has been tested on 138 regions extracted from CT scan images acquired from patients with lung cancer. Assuming two classes of tissues C1 (healthy tissues) and C2 (lesion) as negative and positive, respectively; preliminary results report an AUC = 0.98 for lesions and AUC = 0.93 for healthy tissue, with an optimal operating condition related to sensitivity = 0.96, and specificity = 0.98 for lesions and sensitivity 0.99, and specificity = 0.94 for healthy tissue. Finally, the following results have been obtained: false-negative rate (FNR) = 6 % (C1), FNR = 2 % (C2), false-positive rate (FPR) = 4 % (C1), FPR = 3 % (C2), true-positive rate (TPR) = 94 %, (C1) and TPR = 98 % (C2).

Keywords

NSCLC IGRT FIS Rule-based classification 

References

  1. 1.
    Xing L, Siebers J, Keall P: Computational challenges for image-guided radiation therapy: framework and current research. Semin Radiat Oncol 17(4):245–257, 2007CrossRefPubMedGoogle Scholar
  2. 2.
    Keall PJ, et al: Four-dimensional radiotherapy planning for DMLC-based respiratory motion tracking. Med Phys 32(4):942–951, 2005CrossRefPubMedGoogle Scholar
  3. 3.
    Padley SPG, Hansell DM, Flower CDR, Jennings P: Comparative accuracy of high resolution computed tomography and chest radiography in the diagnosis of chronic diffuse infiltrative lung disease. Clin Radiol 44(4):222–226, 1991CrossRefPubMedGoogle Scholar
  4. 4.
    Urie MM, Goiten M, Doppke K, Kutcher JG, LoSasso T, Mohan R, Munzenrider JE, Sontag M, Wong JW: The role of uncertainity analysis in treatment planning. Int J Radiat Oncol Biol Phys 21:91–107, 1991CrossRefPubMedGoogle Scholar
  5. 5.
    Ekberg L, Holmberg O, Wittgren L, Bjelkengren G, Landberg T: What margins should be added to the clinical target volume in radiotherapy treatment planning for lung cancer? Radiother Oncol 48:71–77, 1998CrossRefPubMedGoogle Scholar
  6. 6.
    Graham MV, Matthews JW, Harms Sr, WB, Enami B, Glazer HS, Purdy JA: Three dimensional radiation treatment planning study for patients with carcinoma of the lung. Int J Radiat Oncol Biol Phys 29:1105–1117, 1994CrossRefPubMedGoogle Scholar
  7. 7.
    Leunens G, Menten J, Weltens C, Verstraete J, Van der Schueren E: Quality assessment of medical decision making in radiation oncology: variability in target volume delineation for brain tumors. Radiother Oncol 29:169–175, 1997CrossRefGoogle Scholar
  8. 8.
    Tait D, Nahum A: Conformal therapy. Eur J Cancer 26:750–753, 1990CrossRefPubMedGoogle Scholar
  9. 9.
    Hamilton CS, Denham JW, Joseph DJ, Labm DS, Spry NA, Gray AJ, Atkinson CH, Wynne CJ, Abdelaal A, Bydder PV, Chapman PJ, Matthews JHL, Stevens G, Ball D, Kearsley J, Ashcroft JB, Janke P, Gutmann A: Treatment and planning decisions in non-small cell carcinoma of the lung: an Australasian patterns of practice study. Clin Oncol R Coll Radiol 4:141–147, 1992CrossRefPubMedGoogle Scholar
  10. 10.
    Dewas S, Bibault J-E, Blanchard P, Vautravers-Dewas C, Pointreau Y, Denis F, Brauner M, Giraud P: Delineation in thoracic oncology: a perspective study of the effect of training on contour variability and dosimetric consequences. Radiat Oncol 6:118–127, 2011CrossRefPubMedGoogle Scholar
  11. 11.
    Vorwerk H, Beckmann G, Bremer M, Degen M, Dietl B, et al: The delineation of target volumes for radiotherapy of lung cancer patients. Radiother Oncol 91:455–460, 2009CrossRefPubMedGoogle Scholar
  12. 12.
    Giraud P, Elles S, Helfre S, Rycke YD, Servois V, et al: Conformal radiotherapy for lung cancer: different delineation of the gross tumor volume (GTV) by radiologists and radiation oncologists. Radiother Oncol 62:27–36, 2002CrossRefPubMedGoogle Scholar
  13. 13.
    Wiemker R., Rogalla P., Zwatkruis A., and Blaffert T., “Computer aided lung nodule detection on high resolution CT data,” Spie Med. Imag., pp. 677-688, 2002Google Scholar
  14. 14.
    Armato SG, Giger ML, Moran CJ, Blackburn JT, Doi K, MacMahon H: Computerized detection of pulmonary nodules on CT scans. RadioGraphics 19:1303–1311, 1999PubMedGoogle Scholar
  15. 15.
    Armato SG, Altman MB, Wilkie J, Sone S, Li F, Doi K, Roy AS: Automated lung nodule classification following automated nodule detection on CT: A serial approach. Med Phys 19:1188–1197, 2003CrossRefGoogle Scholar
  16. 16.
    Li Q: Recent progress in computer aided diagnosis of lung nodule on this section CT. Comp Med Imag Graph 4–5:248–257, 2007CrossRefGoogle Scholar
  17. 17.
    Goo JM: A computer aided diagnosis for evaluating lung nodules on chest CT: the current status and perspective. Korean J Radiol 12(2):145–155, 2011CrossRefPubMedGoogle Scholar
  18. 18.
    Kakar M, Olsen DR: Automatic segmentation and recognition of lungs and lesion from CT scans of thorax. Comput Med Imag Graph 33(1):72–82, 2009CrossRefGoogle Scholar
  19. 19.
    Seiler PG, Blattmann H, Kirsch S, Muench RK, Schilling C: A novel tracking technique for the continuous precise measurement of tumor positions in conformal radiotherapy. Phys Med Biol 45:103–110, 2000CrossRefGoogle Scholar
  20. 20.
    Sharp GC, Jiang SB, Shimizu S, Shirato H: Tracking errors in a prototype real time tumour tracking system. Phys Med Biol 49:5347–5356, 2004CrossRefPubMedGoogle Scholar
  21. 21.
    Arslan S, Yilmaz A, Bayramgurler B, Uzman O, Nver E, Akkaya E: CT-guided transthoracic fine needle aspiration of pulmonary lesions: accuracy and complications in 294 patients. Med Sci Monit 8:493–497, 2002Google Scholar
  22. 22.
    Geraghty PR, Kee ST, McFarlane G, Razavi MK, Sze DY, Dake MD: CT guided transthoracic needle aspiration biopsy of pulmonary nodules: needle size and pneumothorax rate. Radiology 229:475–481, 2003CrossRefPubMedGoogle Scholar
  23. 23.
    Hosaik JD, Sixel KE, Tirona R, Cheung PC, Pignol JP: Correlation of lung tumor motion with external surrogate indicators of respiration. Int J Radiat Oncol Biol Phys 60:1298–1306, 2004CrossRefGoogle Scholar
  24. 24.
    Berbeco RI, Nishioka S, Shirato H, Chen GT, Jiang SB: Residual motion of lung tumors in gated radiotherapy with external respiratory surrogates. Phys Med Biol 50:3655–3667, 2005CrossRefPubMedGoogle Scholar
  25. 25.
    Watanabe H, et al: The application of a fuzzy discriminant analysis for the diagnosis of valvular heart disease. IEEE Trans on Fuzzy Syst 2(4):267–276, 1994CrossRefGoogle Scholar
  26. 26.
    Stevens CW, Munden RF, Forster KM, Kelly JF, Liao Z, Starkschall G, Tucker S, Komaki R: Respiratory-driven lung tumor motion is independent of tumor size, tumor location, and pulmonary function. Int J Radiat Oncol Biol Phys 51:62–68, 2001CrossRefPubMedGoogle Scholar
  27. 27.
    Colgan R, McClelland RJ, McQuaid D, Evans PM, Hawkes D, Brock J, Landau D, Webb S: Planning lung radiotherapy using 4d CT data and a motion model. Phys Med Biol 53:5815–5832, 2008CrossRefPubMedGoogle Scholar
  28. 28.
    M. Kakar and D.R. Olsen. Hybrid intelligent modeling and prediction of texture segmented lesion from 4DCT scans of thorax. In IEEE Conf. on Fuzzy Systems, Jeju, Korea, 2009Google Scholar
  29. 29.
    Zadeh LA: Fuzzy Sets Inf Control 8:338–353, 1965CrossRefGoogle Scholar
  30. 30.
    Andersson ER: Fuzzy and rough techniques in medical diagnosis and medication. Studies in fuzziness and soft computing. Springer, Heidelberg, 2007Google Scholar
  31. 31.
    Mencattini A, Salmeri M: Breast masses detection using phase portrait analysis and fuzzy inference systems. Int J Comput Assist Radiol Surg, 2011. doi: 10.1007/s11548-011-0659-0
  32. 32.
    A. Ferrero et al. Uncertainty evaluation in a fuzzy classifier for microcalcifications in digital mammography. In IEEE Instrumentation and Measurement Technology Conference (IMTC ’10), Austin, TX, USA, May 2010Google Scholar
  33. 33.
    A. Mencattini et al. A study on a novel scoring system for the evaluation of expected mortality in ICU-patients. In IEEE International Workshop on Medical Measurements and Applications (MEMEA ’11), Bari, Italy, May 2011Google Scholar
  34. 34.
    Chawla NV, Boywer KW, Hall LO, Kegelmeyer WP., “SMOTE: synthetic minority over-sampling technique,” J Artif Intell Res, vol. 321, Jun, 2002Google Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2012

Authors and Affiliations

  • Manish Kakar
    • 1
  • Arianna Mencattini
    • 2
    Email author
  • Marcello Salmeri
    • 2
  1. 1.Division for Cancer and Surgery, Department of Radiation Biology, Institute for Cancer ResearchOslo University HospitalOsloNorway
  2. 2.Department of Electronic EngineeringUniversity of Rome Tor VergataRomeItaly

Personalised recommendations