Detection and classification of thyroid nodule using Shearlet coefficients and support vector machine
-
2017-06-04 https://doi.org/10.14419/ijet.v6i3.7705
-
, Co Occurrence Matrix, Texture Analysis, Thyroid Nodule, Shearlet Transform. -
Abstract
Thyroid nodules have diversified internal components and dissimilar echo patterns in ultrasound images. Textural features are used to characterize these echo patterns. This paper presents a classification scheme that uses shearlet transform based textural features for the classification of thyroid nodules in ultrasound images. The study comprised of 60 thyroid ultrasound images (30 with benign nodules and 30 with malignant nodules). Total of 22 features are extracted. Support vector machine (SVM) and K nearest neighbor (KNN) are used to differentiate benign and malignant nodules. The diagnostic sensitivity, specificity, F1_score and accuracy of both the classifiers are calculated. A comparative study has been carried out with respect to their performances. The sensitivity of SVM with radial basis function (RBF) kernel is 100% as compared to that of KNN with 96.33%. The proposed features can increase the accuracy of the classifier and decrease the rate of misdiagnosis in thyroid nodule classification.
-
References
[1] D Ghassi, A Donato, Evaluation of the thyroid noduleâ€, Postgraduation Medical Journal, Vol. 85, No. 1002, (2009), pp. 190-195, https://doi.org/10.1136/pgmj.2008.072140.
[2] K T Wong, Anil T Ahuja, “Ultrasound of Thyroid Cancerâ€, Cancer Imaging, BioMed central, Vol. 5, No. 1, (2005), pp. 157-166.
[3] Young Hun Lee, Dong Wook Kim, Hyun Sin in et al. “Differentiation between benign an malignant solid thyroid nodules using an US classification systemâ€, Korean Journal of Radiology, Vol. 12, No.5, (2011), pp. 559-567. https://doi.org/10.3348/kjr.2011.12.5.559.
[4] Stavros Tsantis, Nikos Dimitropoulos, Dionisis Cavouras, George Nikiforidis, “Morphological and wavelet features towards sonographic thyroid nodules evaluationâ€, Computerized Medical Imaging and Graphics, Elsevier, Vol. 33, No. 2, (2009), pp 91-99. https://doi.org/10.1016/j.compmedimag.2008.10.010.
[5] Michalis Savelonas, Dimitris Maroulis, Manolis sangriotis, “A computer aided system for malignancy risk assessment nodules in thyroid US images based on boundary featuresâ€, Computer Methods and programs in Biomedicine, Elsevier, Vol. 96, No. 1 (2009), pp. 25-32.
[6] Grigorescu, S. N., Petkov, N., Kruizinga, P. “Comparison of Texture Features Based on Gabor Filtersâ€, IEEE Transactions on Image processing, Vol. 11, No. 10, (2002), pp. 1160-1167. https://doi.org/10.1109/TIP.2002.804262.
[7] Yuan Y. Tang, Yu Tao, Ernest C.M. Lam, “New method for feature extraction based on fractal behaviorâ€, Pattern Recognition, Vol. 35, No.5 (2002), pp. 1071–1081, https://doi.org/10.1016/S0031-3203(01)00095-4.
[8] Chuan-Yu Chang, Shao-Jer Chen, Ming-Fong Tsai, “Application of Support vector machine based method for feature selection and classification of thyroid nodules in ultrasound imagesâ€, Pattern Recognition, Elsevier, Vol. 43, No. 10, (2010), pp 3494-3506. https://doi.org/10.1016/j.patcog.2010.04.023.
[9] Jie Zhao, Wei Zheng, Li Zhang and Hua Tian, “Segmentation of ultrasound images of thyroid nodule for assisting fine needle aspiration cytologyâ€, Journal on Health Information Science and Systems, Vol. 1, No. 1, (2012), pp. 1-12.
[10] U Rajendra Acharya, Oliver Faust, S Vinitha sree, Filippo Molinari, Jasjit S Suri, “Thyroscreen system: High resolution ultrasound thyroid image characterization int benign and malignant classes using novel combination of texture and discrete wavelet transformâ€, Computer Methods and programs in biomedicine, Elsevier, Vol. 107, No.2, (2012), pp 233-241.
[11] U Rajendra Acharya, G Swapna, S Vinitha Sree, Filippo Molinari, Savita Gupta, Ricardo H Bardales, Agnieszka Witkowska and Jasjit S Suri, “ A review on ultrasound based thyroid cancer tissue characterization and automated classificationâ€, Technology in cancer research and treatment, Vol. 13, No. 4, (2014), pp 288-301.
[12] K Guo , D Labate, “Optimally sparse multidimensional representation using Shearletsâ€, SIAM Journal on Mathematical Analysis, Vol 30, No. 1, (2007), pp 298-318. https://doi.org/10.1137/060649781.
[13] Shichong Zhou, Jun Shi, Jie Zhu, Yin Cai, Ruiling Wang, Shearlet based texture feature extraction for classification of breast tumor in ultrasound imageâ€, Biomedical Signal processing and control ,Elsevier, Vol 8, No. 6, (2013), pp 688-696.
[14] Lina Pedraza , Carlos Vargas, Fabian Narvaez , Oscar Duran , Emma Munoz, Eduardo Romero, “An open access thyroid ultrasound-Image Databaseâ€, Proceedings of SPIE, Vol. 9287 (2015).
[15] Easley, G.R.; Labate, D.; Colonna, F, “Shearlet-based total variation diffusion for denoisingâ€, IEEE Transactions on Image Processing, Vol 18, No. 2, (2009), pp. 260–268. https://doi.org/10.1109/TIP.2008.2008070.
[16] Easley, G.; Labate, D.; Lim, W.Q, “Sparse directional image representations using the discrete shearlet transformâ€, Appllied and Computational Harmonic Analysis, Vol 25, No.1, (2008), pp. 25–46 , https://doi.org/10.1016/j.acha.2007.09.003.
[17] Hadi Rezaeilouyeh, Mohammad H Mahoor, “Automatic Gleason Grading of Prostate Cancer using Shearlet Transform and Multiple Kernel Learningâ€, Journal of Imaging , Vol. 2, No.3, (2016), 25. https://doi.org/10.3390/jimaging2030025.
[18] Corinna Cortes, Vladimir Vapnik. “Support-Vector Networksâ€, Machine Learning, Vol. 20, No 3, (1995), pp. 273-297. https://doi.org/10.1007/BF00994018.
[19] Burges CJS, “A tutorial on support vector machines for pattern recognition, data mining and knowledgeâ€, Discovery 2, (1998), pp 121-167.
[20] Muller K R, Mika S, Raisch G, Tsuda K Scholkopf B , “An introduction to kernel-based learning algorithmsâ€, IEEE Transactions on Neural Networks, Vol. 12, No.2, (2001), pp 181-202. https://doi.org/10.1109/72.914517.
[21] Larode D T KNN. In: Discovering Knowledge in Data: An introduction to data mining, Wiley Interscience, (2004), pp 90-106.
-
Downloads
-
How to Cite
S., N., & M., S. (2017). Detection and classification of thyroid nodule using Shearlet coefficients and support vector machine. International Journal of Engineering & Technology, 6(3), 50-53. https://doi.org/10.14419/ijet.v6i3.7705Received date: 2017-05-03
Accepted date: 2017-05-12
Published date: 2017-06-04