Journal of Digital Imaging

, Volume 28, Issue 1, pp 99–115 | Cite as

Texture Feature Analysis for Computer-Aided Diagnosis on Pulmonary Nodules

  • Fangfang Han
  • Huafeng Wang
  • Guopeng Zhang
  • Hao Han
  • Bowen Song
  • Lihong Li
  • William Moore
  • Hongbing Lu
  • Hong Zhao
  • Zhengrong Liang
Article

Abstract

Differentiation of malignant and benign pulmonary nodules is of paramount clinical importance. Texture features of pulmonary nodules in CT images reflect a powerful character of the malignancy in addition to the geometry-related measures. This study first compared three well-known types of two-dimensional (2D) texture features (Haralick, Gabor, and local binary patterns or local binary pattern features) on CADx of lung nodules using the largest public database founded by Lung Image Database Consortium and Image Database Resource Initiative and then investigated extension from 2D to three-dimensional (3D) space. Quantitative comparison measures were made by the well-established support vector machine (SVM) classifier, the area under the receiver operating characteristic curves (AUC) and the p values from hypothesis t tests. While the three feature types showed about 90 % differentiation rate, the Haralick features achieved the highest AUC value of 92.70 % at an adequate image slice thickness, where a thinner or thicker thickness will deteriorate the performance due to excessive image noise or loss of axial details. Gain was observed when calculating 2D features on all image slices as compared to the single largest slice. The 3D extension revealed potential gain when an optimal number of directions can be found. All the observations from this systematic investigation study on the three feature types can lead to the conclusions that the Haralick feature type is a better choice, the use of the full 3D data is beneficial, and an adequate tradeoff between image thickness and noise is desired for an optimal CADx performance. These conclusions provide a guideline for further research on lung nodule differentiation using CT imaging.

Keywords

Lung CADx Lung nodule analysis Haralick features Gabor features LBP features 

Notes

Acknowledgments

This work was partly supported by the NIH/NCI under grant nos. CA143111 and CA082402, and a PSC-CUNY award 65230-0043. This work was also supported by the National Science Foundation of China under grant nos. 61071213, 61172002, 81071220, and 81230035, the National Key Technologies R&D Program of China under grant no. 2011BAI12B03, the Fundamental Research Funds for the Central Universities under grant no. N120518001, and Liaoning Natural Science Foundation 2013020021.

References

  1. 1.
  2. 2.
    Swensen SJ, Jett JR, Sloan JA, Midthun DE, Hartman TE, Sykes A-M, Aughenbaugh GL, Zink FE, Hillman SL, Noetzel GR, Marks RS, Clayton AC, Pairolero PC: Screening for lung cancer with low-dose spiral computed tomography. Am J Respir Crit Care Med 165(4):508–513, 2002PubMedCrossRefGoogle Scholar
  3. 3.
    MacMahon H, Austin JHM, Gamsu G, Herold CJ, Jett JR, Naidich DP, Patz EF, Swensen SJ: Guidelines for management of small pulmonary nodules detected on ct scans: a statement from the Fleischner society. Radiology 237:395–400, 2005PubMedCrossRefGoogle Scholar
  4. 4.
    Matsuki Y, Nakamura K, Watanabe H, Aoki T, Nakata H, Katsuragawa S, Doi K: Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high-resolution CT: evaluation with receiver operating characteristic analysis. Am J Roentgenol 178:657–663, 2002CrossRefGoogle Scholar
  5. 5.
    Cardillo G, Regal M, Sera F, Di Martino M, Carbone L, Facciolo F, Martelli M: Videothoracoscopic management of the solitary pulmonary nodule: a single-institution study on 429 cases. Ann Thorac Surg 75:1607–1612, 2003PubMedCrossRefGoogle Scholar
  6. 6.
    Li F, Aoyama M, Shiraishi J, Abe H, Li Q, Suzuki K, Engelmann R, Sone S, MacMahon H, Doi K: Radiologists’ performance for differentiating benign from malignant lung nodules on high-resolution CT using computer estimated likelihood of malignancy. Am J Roentgenol 183:1209–1215, 2004CrossRefGoogle Scholar
  7. 7.
    Gould MK, Fletcher J, Iannettoni MD, Lynch WR, Midthun DE, Naidich DP, Ost DE: Evaluation of patients with pulmonary nodules: when is it lung cancer? ACCP Evid Based Clin Pract Guidelines Chest 132:108S–130S, 2007Google Scholar
  8. 8.
    McNitt-Gray MF, Hart EM, Wyckoff N, Wyckoff N, Sayre JW, Goldin JG, Aberle DR: A pattern classification approach to characterizing solitary pulmonary nodules imaged on high resolution CT: preliminary results. Med Phys 26(6):880–888, 1999PubMedCrossRefGoogle Scholar
  9. 9.
    Li Q, Li F, Shiraishi J, Katsuragawa S, Sone S, Doi K: Investigation of new psychophysical measures for evaluation of similar images on thoracic computed tomography for distinction between benign and malignant nodules. Med Phys 30(10):2584–2593, 2003PubMedCrossRefGoogle Scholar
  10. 10.
    Zinovev D, Raicu D, Furst J, Armato III, SG: Predicting radiological panel opinions using a panel of machine learning classifiers. Algorithms 2:1473–1502, 2009CrossRefGoogle Scholar
  11. 11.
    Yankelevitz DF, Reeves AP, Kostis WJ, et al: Small pulmonary nodules: volumetrically determined growth rates based on CT evaluation. Radiology 217:251–256, 2000PubMedCrossRefGoogle Scholar
  12. 12.
    Goodman LR, Gulsun M, Washington L, Nagy PG, Piacsek KL: Inherent variability of CT lung nodule measurements in vivo using semiautomated volumetric measurements. Am J Roentgenol 186:989–994, 2006CrossRefGoogle Scholar
  13. 13.
    Iwano S, Nakamura T, Kamioka Y, Ishigaki T: Computer-aided diagnosis: a shape classification of pulmonary nodules imaged by high-resolution CT. Comput Med Imaging Graph 29:565–570, 2005PubMedCrossRefGoogle Scholar
  14. 14.
    Way TW, Hadjiiski LM, Sahiner B, Chan H-P, Cascade PN, Kazerooni EA, Bogot N, Zhou C: Computer-aided diagnosis of pulmonary nodules on CT scans: segmentation and classification using 3D active contours. Med Phys 33(7):2323–2337, 2006PubMedCentralPubMedCrossRefGoogle Scholar
  15. 15.
    Saito H, Minamiya Y, Kawai H, Nakagawaa T, Ito a M, Hosonoa Y, Motoyamaa S, Hashimotob M, Ishiyamab K, Ogawa J-I: Usefulness of circumference difference for estimating the likelihood of malignancy in small solitary pulmonary nodules on CT. Lung Cancer 58:348–354, 2007PubMedCrossRefGoogle Scholar
  16. 16.
    El-Baz A, Gimel’farb GL, Falk R, El-Ghar MA: Appearance Analysis for Diagnosing Malignant Lung Nodules. Proc. of IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI’10), Rotterdam, The Netherlands, April 14–17, 2010, 193–196Google Scholar
  17. 17.
    El-Baz A, Nitzken M, Khalifa F, Elnakib A, Gimel’farb G, Falk R, El-Ghar MA: 3D shape analysis for early diagnosis of malignant lung nodules. Inf Process Med Imaging 22:772–783, 2011Google Scholar
  18. 18.
    El-Baz A, Nitzken M, Vanbogaert E, Gimel’farb GL, Falk R, El-Ghar MA: A Novel Shape-Based Diagnostic Approach for Early Diagnosis of Lung Nodules. Proceedings of the 8th IEEE International Symposium on Biomedical Imaging, 2011, 137–140Google Scholar
  19. 19.
    El-Baz A, Gimel'farb GL, El-Ghar MA, Falk R: Appearance-Based Diagnostic System for Early Assessment of Malignant Lung Nodules. In: Proc. IEEE International Conference on Image Processing (ICIP’12), Orlando, Florida, USA, September 30-October 3, 2012, 1463–1466Google Scholar
  20. 20.
    Vittitoe NF, Baker JA, Floyd CE: Fractal texture analysis in computer-aided diagnosis of solitary pulmonary nodules. Acad Radiol 4:96–101, 1997PubMedCrossRefGoogle Scholar
  21. 21.
    Sluimer IC, van Waes PF, Viergever MA, van Ginneken B: Computer-aided diagnosis in high resolution CT of the lungs. Med Phys 30(12):3081–3090, 2003PubMedCrossRefGoogle Scholar
  22. 22.
    SK Vijai Anand: Segmentation and Coupled Textural Feature Classification for Lung Tumor Prediction. IEEE International Conference on Communication Control and Computing Technologies, 2010, 518–524Google Scholar
  23. 23.
    Arai K, Herdiyeni Y, Okumura H: Comparison of 2D and 3D local binary pattern in lung cancer diagnosis. Int J Adv Comput Sci Appl 3(4):89–95, 2012Google Scholar
  24. 24.
    Haralick RM, Shanmugam K, Dinstein I: Textural features for image classification. IEEE Trans Syst Man Cybern SMC-3(6):610–621, 1973CrossRefGoogle Scholar
  25. 25.
    Gabor D: Theory of communication. J Inst Electr Eng 93(26):429–457, 1946Google Scholar
  26. 26.
    Wang L, He D: Texture classification using texture spectrum. Pattern Recogn 23:905–910, 1990CrossRefGoogle Scholar
  27. 27.
    Samuel G, Armato III, Mclennan G, Bidaut L, McNitt-Gray MF, Meyer CR, Reeves AP, Zhao B, Henschke CI, Hoffman EA, Kazerooni EA, MacMahon H, van Beek EJR, Yankelevitz D, Biancardi AM, Bland PH, Brown MS, Engelmann RM, Laderach GE, Max D, Pais RC, Qing DP-Y, Roberts RY, Smith AR, Starkey A, Batra P, Caligiuri P, Farooqi A, Gladish GW, Jude CM, Munden RF, Petkovska I, Quint LE, Schwartz LH, Sundaram B, Dodd LE, Fenimore C, Gur D, Petrick N, Freymann J, Kirby J, Hughes B, Casteele AV, Gupte S, Sallam M, Heath MD, Kuhn MH, Dharaiya E, Burns R, Fryd DS, Salganicoff M, Anand V, Shreter U, Vastagh S, Croft BY, Clarke LP: The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans. Med Phys 38:915–931, 2011CrossRefGoogle Scholar
  28. 28.
    Abdi H, Williams LJ: Principal component analysis. Wiley Interdiscip Rev Comput Stat 2:433–459, 2010CrossRefGoogle Scholar
  29. 29.
    Kamarainen J-K, Kyrki V, Kälviäinen H: Invariance properties of gabor filter-based features—overview and applications. IEEE Trans Image Process 15(5):1088–1099, 2006PubMedCrossRefGoogle Scholar
  30. 30.
    Kruizinga P, Petkov N, Grigorescu SE: Comparison of Texture Features Based on Gabor Filters. Proceedings of the 10th International Conference on Image Analysis and Processing, Venice, Italy, September 27–29, 1999, 142–147Google Scholar
  31. 31.
    Petkov N, Kruizinga P: Computational models of visual neurons specialised in the detection of periodic and aperiodic oriented visual stimuli: bar and grating cells. Biol Cybern 76:83–96, 1997PubMedCrossRefGoogle Scholar
  32. 32.
    Jones JP, Palmer LA: An evaluation of the two-dimensional gabor filter model of simple receptive fields in cat striate cortex. J Neurophysiol 58:1233–1258, 1987PubMedGoogle Scholar
  33. 33.
    Ojala T, Pietikäinen M, Harwood D: A comparative study of texture measures with classification based on feature distributions. Pattern Recogn 29(1):51–59, 1996CrossRefGoogle Scholar
  34. 34.
    Ahonen T, Hadid A, Pietikäinen M: Face description with local binary patterns: application to face recognition. IEEE Trans Pattern Anal Mach Intell 28(12):2037–2041, 2006PubMedCrossRefGoogle Scholar
  35. 35.
    Heikkilä M, Pietikäinen M, Schmid C: Description of interest regions with local binary patterns. Pattern Recogn 42(3):425–436, 2009CrossRefGoogle Scholar
  36. 36.
    Philips C, Li D, Furst J, Raicu D: An Analysis of Co-Occurrence and Gabor Texture Classification in 2D and 3D. CARS 2008 Proceedings. Barcelona, SpainGoogle Scholar
  37. 37.
    Zhang G, Wang T, Lu H, Zhang J, Liu X, Liang Z: CAD Based on 3D Texture Analysis for Virtual Colonoscopy. The 22nd International Congress and Exhibition, CARS 2008 Computer Assisted Radiology and Surgery, June 25–28, 2008, Barcelona, Spain: 17Google Scholar
  38. 38.
    Han F, Wang H, Song B, Zhang G, Lu H, et al: A New 3D Texture Feature Based Computer-Aided Diagnosis Approach to Differentiate Pulmonary Nodules. Proc. SPIE 8670, Medical Imaging 2013: Computer-Aided Diagnosis, 86702Z, February 28, 2013Google Scholar
  39. 39.
    Philips C, Li D, Raicu D, Furst J: Directional Invariance of Co-Occurrence Matrices within the Liver. International Conference on Biocomputation, Bioinformatics, and Biomedical Technologies, 2008, 29–34Google Scholar
  40. 40.
    Suykens J, Vandewalle J: Least squares support vector machine classifiers. Neural Process Lett 9(3):293–300, 1999CrossRefGoogle Scholar
  41. 41.
    Fritsch FN, Carlson RE: Monotone piecewise cubic interpolation. Soc Ind Appl Math 17(2):238–246, 1980Google Scholar
  42. 42.
    Han H, Li L, Han F, Zhang H, Moore W, Liang Z: Vector Quantization-Based Automatic Detection of Pulmonary Nodules in Thoracic CT Images. In Proc. of IEEE Nuclear Science Symposium and Medical Imaging Conference, Seoul, Korea, October 27 - November 2, 2013Google Scholar
  43. 43.
    Fan L, Song B, Gu X, Liang Z: Improved Computer-Aided Colonic Polyp Detection Using a Modified SVM Classifier with Adaptive Kernel. Conf Record IEEE NSS-MIC, in CD-ROM, 2012Google Scholar
  44. 44.
    Zhang G, Liang Z, Song B, Zhu H, Lu H: A Virtual Pathology Model for Differentiation of Colonic Polyp Types for CT Colonography. The 98th Annual Meeting of the Radiological Society of North America (RSNA), 2012, 414Google Scholar
  45. 45.
    Song B, Zhang G, Zhu H, Zhu W, Lu H, Liang Z: A Feasibility Study of High Order Volumetric Texture Features for Computer Aided Diagnosis of Polyps via CT Colonography. Conf Record IEEE NSS-MIC, in CD-ROM, 2012Google Scholar
  46. 46.
    Wang J, Li T, Hongbing L, Liang Z: Penalized weighted least-squares approach to sinogram noise reduction and image reconstruction for low-dose x-ray CT. IEEE Trans Med Imaging 25(10):1272–1283, 2006PubMedCentralPubMedCrossRefGoogle Scholar
  47. 47.
    Liu Y, Ma J, Fan Y, Liang Z: Adaptive-weighted total variation minimization for low-dose X-ray computed tomography image reconstruction. Phys Med Biol 57:7923–7956, 2012PubMedCentralPubMedCrossRefGoogle Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2014

Authors and Affiliations

  • Fangfang Han
    • 1
    • 2
  • Huafeng Wang
    • 1
  • Guopeng Zhang
    • 3
  • Hao Han
    • 1
  • Bowen Song
    • 1
    • 4
  • Lihong Li
    • 5
  • William Moore
    • 1
  • Hongbing Lu
    • 3
  • Hong Zhao
    • 2
    • 7
  • Zhengrong Liang
    • 1
    • 6
  1. 1.Department of RadiologyState University of New YorkStony BrookUSA
  2. 2.Northeastern UniversityShenyangChina
  3. 3.Department of Biomedical EngineeringFourth Military Medical UniversityXi’anChina
  4. 4.Department of Applied Mathematics and StatisticsState University of New YorkStony BrookUSA
  5. 5.Department of Engineering Science and PhysicsCity University of New York/CSIStaten IslandUSA
  6. 6.State University of New YorkStony BrookUSA
  7. 7.Neusoft CompanyShenyangChina

Personalised recommendations