Signal detection using support vector machines in the presence of ultrasonic speckle

Support Vector Machines are a general algorithm based on guaranteed risk bounds of statistical learning theory. They have found numerous applications, such as in classification of brain PET images, optical character recognition, object detection, face verification, text categorization and so on. In this paper we propose the use of support vector machines to segment lesions in ultrasound images and we assess thoroughly their lesion detection ability. We demonstrate that trained support vector machines with a Radial Basis Function kernel segment satisfactorily (unseen) ultrasound B-mode images as well as clinical ultrasonic images.

[1]  Thorsten Joachims,et al.  Making large scale SVM learning practical , 1998 .

[2]  R. F. Wagner,et al.  Low Contrast Detectability and Contrast/Detail Analysis in Medical Ultrasound , 1983, IEEE Transactions on Sonics and Ultrasonics.

[3]  A P Hoeks,et al.  Improved lesion detection by level-dependent spatial summation. , 1995, Ultrasonic imaging.

[4]  J M Thijssen,et al.  Improvement of lesion detection by echographic image processing: signal-to-noise-ratio imaging. , 1991, Ultrasonic imaging.

[5]  Tomaso A. Poggio,et al.  Example-Based Object Detection in Images by Components , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Roger Fletcher,et al.  Practical methods of optimization; (2nd ed.) , 1987 .

[7]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[8]  Bernhard Schölkopf,et al.  Comparing support vector machines with Gaussian kernels to radial basis function classifiers , 1997, IEEE Trans. Signal Process..

[9]  Gozde Bozdagi Akar,et al.  An adaptive speckle suppression filter for medical ultrasonic imaging , 1995, IEEE Trans. Medical Imaging.

[10]  R. Fletcher Practical Methods of Optimization , 1988 .

[11]  J. M. Thijssen,et al.  Focal Lesions in Medical Images: A Detection Problem , 1988 .

[12]  Ioannis Pitas,et al.  Optimum Nonlinear Signal Detection and Estimation in the Presence of Ultrasonic Speckle , 1992 .

[13]  Gunnar Rätsch,et al.  An introduction to kernel-based learning algorithms , 2001, IEEE Trans. Neural Networks.

[14]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[15]  Tomaso A. Poggio,et al.  A pattern classification approach to dynamical object detection , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[16]  Yee-Hong Yang,et al.  Multiresolution texture segmentation with application to diagnostic ultrasound images , 1993, IEEE Trans. Medical Imaging.

[17]  James F. Greenleaf,et al.  Adaptive speckle reduction filter for log-compressed B-scan images , 1996, IEEE Trans. Medical Imaging.

[18]  Nello Cristianini,et al.  An introduction to Support Vector Machines , 2000 .

[19]  Bruno O. Shubert,et al.  Random variables and stochastic processes , 1979 .

[20]  Michael G. Strintzis,et al.  Nonlinear ultrasonic image processing based on signal-adaptive filters and self-organizing neural networks , 1994, IEEE Trans. Image Process..

[21]  I. Miller Probability, Random Variables, and Stochastic Processes , 1966 .

[22]  William Nick Street,et al.  Breast Cancer Diagnosis and Prognosis Via Linear Programming , 1995, Oper. Res..

[23]  Robert F. Wagner Fundamentals And Applications Of Signal Detection Theory In Medical Imaging , 1986, Other Conferences.

[24]  Federico Girosi,et al.  Support Vector Machines: Training and Applications , 1997 .

[25]  Kevin J. Parker,et al.  Multiple Resolution Bayesian Segmentation of Ultrasound Images , 1994, Other Conferences.

[26]  Yoshua Bengio,et al.  Support vector machines for improving the classification of brain PET images , 1998, Medical Imaging.