Morphological and wavelet features towards sonographic thyroid nodules evaluation
作者： Stavros Tsantis , Nikos Dimitropoulos , Dionisis Cavouras , George Nikiforidis
DOI: 10.1016/J.COMPMEDIMAG.2008.10.010
关键词:
摘要: This paper presents a computer-based classification scheme that utilized various morphological and novel wavelet-based features towards malignancy risk evaluation of thyroid nodules in ultrasonography. The study comprised 85 ultrasound images-patients were cytological confirmed (54 low-risk 31 high-risk). A set 20 (12 based on boundary shape 8 wavelet local maxima located within each nodule) has been generated. Two powerful pattern recognition algorithms (support vector machines probabilistic neural networks) have designed developed order to quantify the power differentiation introduced features. comparative also held, estimate impact speckle had onto procedure. diagnostic sensitivity specificity both classifiers was made by means receiver operating characteristics (ROC) analysis. In speckle-free feature set, area under ROC curve 0.96 for support classifier whereas networks 0.91. with speckle, corresponding areas curves 0.88 0.86 respectively two classifiers. proposed can increase accuracy decrease rate missing misdiagnosis cancer control.
elsevier.com
sci-hub.se 参考文章(36)
Vojislav Kecman, Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models ,(2001)
William Nick Street, Cancer diagnosis and prognosis via linear-programming-based machine learning University of Wisconsin at Madison. ,(1994)
Kenneth L Becker, None, Principles and Practice of Endocrinology and Metabolism ,(1990)
Donald F. Specht, Probabilistic neural networks Neural Networks. ,vol. 3, pp. 109- 118 ,(1990) , 10.1016/0893-6080(90)90049-Q
Purdue University. Department of Computer Sciences, On Symmetry Detection IEEE Transactions on Computers. ,vol. 34, pp. 663- 666 ,(1985) , 10.1109/TC.1985.1676605
ANDRÉ J VAN HERLE, PHILIP RICH, BRITT-MARIE E LJUNG, MICHAEL W ASHCRAFT, DAVID H SOLOMON, EMMETT B KEELER, The Thyroid Nodule Annals of Internal Medicine. ,vol. 96, pp. 221- 232 ,(1982) , 10.7326/0003-4819-96-2-221
David A.K. Watters, Anil T. Ahuja, Rhodri M. Evans, Wilson Chick, Walter W.K. King, Constantine Metreweli, Arthur K.C. Li, Role of ultrasound in the management of thyroid nodules The American Journal of Surgery. ,vol. 164, pp. 654- 657 ,(1992) , 10.1016/S0002-9610(05)80728-7
Stéphane Jaffard, Yves Meyer, Wavelet Methods for Pointwise Regularity and Local Oscillations of Functions ,(1996)
S. Mallat, S. Zhong, Characterization of signals from multiscale edges ,(2011)
Stavros Tsantis, Dionisis Cavouras, Ioannis Kalatzis, Nikos Piliouras, Nikos Dimitropoulos, George Nikiforidis, Development of a support vector machine-based image analysis system for assessing the thyroid nodule malignancy risk on ultrasound. Ultrasound in Medicine and Biology. ,vol. 31, pp. 1451- 1459 ,(2005) , 10.1016/J.ULTRASMEDBIO.2005.07.009