Abstract
The automatic classification of bone texture into healthy or osteoporotic cases presents a major challenge since there is no visual difference between the two cases. This classification requires an inspection of the fine granularity in the bone radiographs which is usually difficult with a naked eye. We have proposed a novel method in this paper, that can be used for the classification of bone radiographs into healthy or osteoporotic cases. We mimic the observations of the physicians by preprocessing the bone radiographs with Gabor filters bearing a high frequency. Later, we design and utilize a convolutional neural network wherein filtered images are fed as input to the system which classifies the images into their respective classes. The proposed algorithm has been validated on a bone radiograph challenge dataset. Our results depict that the method proposed in this research exhibits very good results in terms of classification. A comparison of the proposed and the contemporary research methods has also been shown in this paper. The experimental results show that by exploiting high frequency Gabor filters and employing the convolutional neural network architecture, good results in performing the classification of bone radiographs are achieved.
Similar content being viewed by others
References
Ajmal, H., Rehman, S., Farooq, U., U.Ain, Q., Riaz, F., Hasssan, A.: Convolutional neural network based image segmentation: a review. In: Pattern Recognition and Tracking XXIX, vol. 10649, p. 106490N. International Society for Optics and Photonics (2018)
Ajmal, H., Rehman, S., Hussain, F., Abbas, M., Khan, A., Young, R., S.Alam, M.: Comparative study of local binary pattern and its shifted variant for osteoporosis identification. In: Pattern Recognition and Tracking XXIX, vol. 10649, p. 1064908. International Society for Optics and Photonics (2018)
Amira, O.; Xu, S.; Du, F.; Zhang, J.; Zhang, C.; Hamza, R.: Weighted-capsule routing via a fuzzy gaussian model. Pattern Recogn. Lett. 138, 424–430 (2020)
Areeckal, A.S.; Kocher, M.; et al.: Current and emerging diagnostic imaging-based techniques for assessment of osteoporosis and fracture risk. IEEE Rev. Biomed. Eng. 12, 254–268 (2018)
Dong, X.; Zhou, H.; Dong, J.: Texture classification using pair-wise difference pooling-based bilinear convolutional neural networks. IEEE Trans. Image Process. 29, 8776–8790 (2020)
Fan, K.C.; Hung, T.Y.: A novel local pattern descriptor-local vector pattern in high-order derivative space for face recognition. IEEE Trans. Image Process. 23(7), 2877–2891 (2014)
Field, D.: Relations between the statistics of natural images and the response properties of cortical cells. IEEE J. Radio Commun. Eng. 4(12), 2379 (1987)
Gabor, D.: Theory of communication. IEE J. Radio Commun. Eng. 93(26), 429 (1946)
Glaser, D.L.; Kaplan, F.S.: Osteoporosis: definition and clinical presentation. Spine 22(24), 12S–16S (1997)
Granlund, D.H.: In search of a general picture processing operator. Comput. Gr. Image Processing 8, 155 (1978)
Hidaka, A.; Kurita, T.: Consecutive dimensionality reduction by canonical correlation analysis for visualization of convolutional neural networks. J-Stage 2017(48), 160–167 (2017)
Hofbauer, H.; Jalilian, E.; Uhl, A.: Exploiting superior CNN-based iris segmentation for better recognition accuracy. Pattern Recogn. Lett. 120, 17–23 (2019)
Houam, L., Hafiane, A., Jennane, R., Boukrouche, A., Lespessailles, E.: Trabecular bone texture classification using 1d lbp and wavelet coefficients in high-pass bands. In: International Conference on Signal, Image, Vision and their Applications SIVA, Vol. 11, pp. 21–24 (2011)
Hough, S.: Fast and slow bone losers. Drugs Aging 12(1), 1–7 (1998)
Jennane, R., Touvier, J., Bergounioux, M., Lespessailles, E.: A variational model for trabecular bone radiograph characterization. In: 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI), pp. 1283–1286. IEEE (2014)
Kavya, R.; Shivram, J.: Texture based bone-radiograph image analysis for the assessment of osteoporosis. Int. J. Eng. Res. Technol. (2015). https://doi.org/10.17577/IJERTV4IS060767
Kazakia, G.J.; Majumdar, S.: New imaging technologies in the diagnosis of osteoporosis. Rev. Endocrine Metab. Disorders 7(1–2), 67–74 (2006)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Korchiyne, R., Farssi, S.M., Sbihi, A., Touahni, R., Alaoui, M.T.: A combined method of fractal and glcm features for mri and ct scan images classification. arXiv preprint arXiv:1409.4559 (2014)
Laine, A.; Fan, J.: Texture classification by wavelet packet signatures. IEEE Trans. Pattern Anal. Mach. Intell. 15(11), 1186 (2000)
Le Corroller, T.; Halgrin, J.; Pithioux, M.; Guenoun, D.; Chabrand, P.; Champsaur, P.: Combination of texture analysis and bone mineral density improves the prediction of fracture load in human femurs. Osteoporos. Int. 23(1), 163–169 (2012)
Lespessailles, E.; Gadois, C.; Lemineur, G.; Do-Huu, J.; Benhamou, L.: Bone texture analysis on direct digital radiographic images: precision study and relationship with bone mineral density at the os calcis. Calcif. Tissue Int. 80(2), 97–102 (2007)
Li, Q., Cai, W., Wang, X., Zhou, Y., Feng, D.D., Chen, M.: Medical image classification with convolutional neural network. In: 2014 13th International Conference on Control Automation Robotics & Vision (ICARCV), pp. 844–848. IEEE (2014)
Liu, J.; Wang, J.; Ruan, W.; Lin, C.; Chen, D.: Diagnostic and gradation model of osteoporosis based on improved deep u-net network. J. Med. Syst. 44(1), 15 (2020)
Moy, J.P.: Signal-to-noise ratio and spatial resolution in x-ray electronic imagers: Is the mtf a relevant parameter? Med. Phys. 27(1), 86–93 (2000)
Muller, R.; Hildebrand, T.; Ruegsegger, P.: Non-invasive bone biopsy: a new method to analyse and display the three-dimensional structure of trabecular bone. Phys. Med. Biol. 39(1), 145 (1994)
Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 807–814 (2010)
Nemati, R.J., Rehman, S., Awan, A.B., Riaz, F.: A composite framework for segregating x-rays of osteoporotic cases from healthy controls. In: Pattern Recognition and Tracking XXIX, vol. 10649, p. 1064909. International Society for Optics and Photonics (2018)
Ngo, V.Q.; Dinh, T.N.: Bone texture characterization based on contourlet and gabor tranforms. Int. J. Comput. Theory Eng. 8(2), 177 (2016)
Nishiyama, K.K.; Shane, E.: Clinical imaging of bone microarchitecture with hr-pqct. Current Osteoporos. Rep. 11(2), 147–155 (2013)
Ojala, T.; Pietikainen, M.; Harwood, D.: A comparative study of texture measures with classification based on feature distributions. Pattern Recogn. 29, 51 (1996)
Oulhaj, H.; Rziza, M.; Amine, A.; Toumi, H.; Lespessailles, E.; El Hassouni, M.; Jennane, R.: Anisotropic discrete dual-tree wavelet transform for improved classification of trabecular bone. IEEE Trans. Med. Imaging 36(10), 2077–2086 (2017)
Oulhaj, H.; Rziza, M.; Amine, A.; Toumi, H.; Lespessailles, E.; Jennane, R.; El Hassouni, M.: Trabecular bone characterization using circular parametric models. Biomed. Signal Process. Control 33, 411–421 (2017)
Pan, W.; Bouslimi, D.; Karasad, M.; Cozic, M.; Coatrieux, G.: Imperceptible reversible watermarking of radiographic images based on quantum noise masking. Comput. Methods Programs Biomed. 160, 119–128 (2018)
Paul, R., Alahamri, S., Malla, S., Quadri, G.J.: Make your bone great again: A study on osteoporosis classification. arXiv preprint arXiv:1707.05385 (2017)
Pentland, A.A.: Fractal based description of natural scenes. IEEE Trans. Pattern Recognit. Mach. Intell. 6, 661 (1984)
Pohlig, F.; Kirchhoff, C.; Lenze, U.; Schauwecker, J.; Burgkart, R.; Rechl, H.; von Eisenhart-Rothe, R.: Percutaneous core needle biopsy versus open biopsy in diagnostics of bone and soft tissue sarcoma: a retrospective study. Eur. J. Med. Res. 17(1), 29 (2012)
Porter, R.; Canagarajah, N.: Robust rotation-invariant texture classification: wavelet, Gabor filter and GMRF based schemes. IEE Proc. Vis. Image Signal Process. 144(3), 180–188 (1997)
Pramudito, J.; Soegijoko, S.; Mengko, T.; Muchtadi, F.; Wachjudi, R.: Trabecular pattern analysis of proximal femur radiographs for osteoporosis detection. J. Biomed. Pharm. Eng. 1(1), 45–51 (2007)
Riaz, F., Nemati, R., Ajmal, H., Hassan, A., Edifor, E., Nawaz, R.: Osteoporosis classification using texture features. In: 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS), pp. 575–579. IEEE (2019)
Satpathy, A.; Jiang, X.; Eng, H.L.: Lbp-based edge-texture features for object recognition. IEEE Trans. Image Process. 23(5), 1953–1964 (2014)
Selvan, S.; Ramakrishnan, S.: Svd-based modeling for texture classification using wavelets transformation. IEEE Trans. Image Process. 16(11), 2688 (2007)
Sharp, J.T.; Wolfe, F.; Lassere, M.; Boers, M.; Van Der Heijde, D.; Larsen, A.; Paulus, H.; Rau, R.; Strand, V.: Variability of precision in scoring radiographic abnormalities in rheumatoid arthritis by experienced readers. J. Rheumatol. 31(6), 1062–1072 (2004)
Simmons, N.R.: Chest x-ray clues to osteoporosis: criteria, correlations, and consistency. Yale University School of Medicine, Technical report (2009)
Singh, A.; Dutta, M.K.; Jennane, R.; Lespessailles, E.: Classification of the trabecular bone structure of osteoporotic patients using machine vision. Comput. Biol. Med. 91, 148–158 (2017)
Su, B., Liu, Y., Jiang, Y., Fu, J., Quan, G.: Bone induced artifacts elimination using two-step convolutional neural network. In: 15th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine, vol. 11072, p. 1107221. International Society for Optics and Photonics (2019)
Su, R., Chen, W., Wei, L., Li, X., Jin, Q., Tao, W.: Encoded texture features to characterize bone radiograph images. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 3856–3861. IEEE (2018)
Su, R.; Liu, T.; Sun, C.; Jin, Q.; Jennane, R.; Wei, L.: Fusing convolutional neural network features with hand-crafted features for osteoporosis diagnoses. Neurocomputing 385, 300 (2019)
Tafraouti, A., El Hassouni, M., Toumi, H., Lespessailles, E., Jennane, R.: Osteoporosis diagnosis using fractal analysis and support vector machine. In: 2014 Tenth International Conference on Signal-Image Technology and Internet-Based Systems, pp. 73–77. IEEE (2014)
Yang, M., Wang, S., Bakita, J., Vu, T., Smith, F.D., Anderson, J.H., Frahm, J.M.: Re-thinking cnn frameworks for time-sensitive autonomous-driving applications: Addressing an industrial challenge. In: 2019 IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS), pp. 305–317. IEEE (2019)
Yger, F.: Challenge ieee-isbi/tcb: application of covariance matrices and wavelet marginals. arXiv preprint arXiv:1410.2663 (2014)
Zhao, Y.; Huang, D.S.; Jia, W.: Completed local binary count for rotation invariant texture classification. IEEE Trans. Image Process. 21(10), 4492–4497 (2012)
Zheng, K., Makrogiannis, S.: Bone texture characterization for osteoporosis diagnosis using digital radiography. In: 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 1034–1037. IEEE (2016)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Nemati, R.J., Riaz, F., Hassan, A. et al. A Framework for Classification of Gabor Based Frequency Selective Bone Radiographs Using CNN. Arab J Sci Eng 46, 4141–4152 (2021). https://doi.org/10.1007/s13369-021-05339-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13369-021-05339-7