脊椎图像预处理与特征提取研究
|
摘要
随着机器学习技术的快速发展,计算机辅助诊断已经成为临床医疗的重要支撑,在脊椎病变识别中广泛应用。然而,脊椎图像具有边缘模糊、多病变特征难以表达和区分度不明显的特点,使得脊椎多病变分类难以取得理想效果。因此,文章研究的脊椎图像预处理与特征提取方法具有理论指导意义和临床实用价值。
With the rapid development of machine learning technology, computer-aided diagnosis has become an important support for clinical medicine, and is widely used in the recognition of spinal lesions. The classification of multiple lesions of the spine is difficult to achieve ideal results because of the problem that it is difficult to express spine image and the degree of discrimination is not obvious of spine image. Therefore, this paper study of preprocessing and feature extraction of spine image has value of theoretical guidance and clinical practical.
With the rapid development of machine learning technology, computer-aided diagnosis has become an important support for clinical medicine, and is widely used in the recognition of spinal lesions. The classification of multiple lesions of the spine is difficult to achieve ideal results because of the problem that it is difficult to express spine image and the degree of discrimination is not obvious of spine image. Therefore, this paper study of preprocessing and feature extraction of spine image has value of theoretical guidance and clinical practical.
引文
[1]CHOI C,TREVOR A J B,CHRISTENSEN H I.RGB-D edge detection and edge-based registration[C].Tokyo:IEEE/RSJ International Conference on Intelligent Robots and Systems,2014.
[2]SONG Y Q,LIU B,XIE J.Medical image texture features classification based on Gabor wavelet transform[J].Computer Engineering,2010(11):200-202.
[3]TANG J,LIU X,SUN Q.A direct image contrast enhancement algorithm in the wavelet domain for screening mammograms[J].IEEEJournal of Selected Topics in Signal Processing,2009(1):74-80.
[4]FERNANDO B,FROMONT E,MUSELET D,et al.Discriminative feature fusion for image classification[C].Providence:Computer vision and pattern recognition,2012.
[5]MANIVANNAN K,AGGARWAL P,DEVABHAKTUNI V,et al.Particulate matter characterization by gray level cooccurrence matrix based support vector machines[J].Journal of Hazardous Materials,2012(5):94-103.
[2]SONG Y Q,LIU B,XIE J.Medical image texture features classification based on Gabor wavelet transform[J].Computer Engineering,2010(11):200-202.
[3]TANG J,LIU X,SUN Q.A direct image contrast enhancement algorithm in the wavelet domain for screening mammograms[J].IEEEJournal of Selected Topics in Signal Processing,2009(1):74-80.
[4]FERNANDO B,FROMONT E,MUSELET D,et al.Discriminative feature fusion for image classification[C].Providence:Computer vision and pattern recognition,2012.
[5]MANIVANNAN K,AGGARWAL P,DEVABHAKTUNI V,et al.Particulate matter characterization by gray level cooccurrence matrix based support vector machines[J].Journal of Hazardous Materials,2012(5):94-103.