Combining Local Features and Multi-instance Learning for Ultrasound Image Classification
-
摘要: 利用全局特征对超声图像进行描述具有一定的局限性,而且对图像进行手工标注的成本过高, 为解决上述问题,本文提出了一种利用局部特征描述超声图像,并结合多示例学习对超声图像进行分类的新方法. 粗略定位图像中的感兴趣区域 (Region of interest, ROI),并提取局部特征,将感兴趣区域看作由局部特征构成的示例包, 采用自组织映射(Self-organizing map, SOM)的方法对示例特征进行矢量量化,采用Bag of words方法将示例特征映射到示例包空间,进而采用传统的支持向量机对示例包进行分类.本文提出的方法在临床超声图像上进行了实验,实验结果表明,该方法具有良好的泛化能力和较高的准确性.Abstract: The method to describe ultrasound images using global features has some limitation. And it has a high cost to manually annotate the region of interest (ROI). To solve the above problems, local features are used to describe ultrasound images. A multi-instance learning method for ultrasound image classification is proposed. The ROI is roughly located and local features are extracted. The ROI is considered as a bag which is composed of local features. The self-organizing map (SOM) method is used for vector quantization and the bag of words method is used to map instance features to bag features. Then the classical support vector machine is used to classify the bags. The method proposed by this paper is tested by clinical ultrasound images. The results show that the method has a good generalization ability and has a high accuracy.
-
Key words:
- Image classification /
- local feature /
- multi-instance learning /
- ultrasound image
-
[1] Chen D R, Lai H W. Three-dimensional ultrasonography for breast malignancy detection. Expert Opinion on Medical Diagnostics, 2011, 5(3): 253-261 [2] Cheng H D, Shan J, Ju W, Guo Y H, Zhang L. Automated breast cancer detection and classification using ultrasound images: a survey. Pattern Recognition, 2010, 43(1): 299-317 [3] Moon W K, Shen Y W, Huang C S, Chiang L R, Chang R F. Computer-aided diagnosis for the classification of breast masses in automated whole breast ultrasound images. Ultrasound in Medicine and Biology, 2011, 37(4): 539-548 [4] Garra B S, Krasner B H, Horii S C, Ascher S, Mun S K, Zeman R K. Improving the distinction between benign and malignant breast lesions: the value of sonographic texture analysis. Ultrasonic Imaging, 1993, 15(4): 267-285 [5] Ren J C. ANN vs. SVM: which one performs better in classification of MCCs in mammogram imaging. Knowledge-Based Systems, 2012, 26: 144-153 [6] Sahiner B, Chan H P, Roubidoux M A, Hadjiiski L M, Helvie M A, Paramagul C, Bailey J, Nees A V, Blane C. Malignant and benign breast masses on 3D US volumetric images: effect of computer-aided diagnosis on radiologist accuracy. Radiology, 2007, 242(3): 716-724 [7] Wagner R F, Smith S W, Sandrik J M, Lopez H. Statistics of speckle in ultrasound B-scans. IEEE Transactions on Sonics and Ultrasonics, 1983, 30(3): 156-163 [8] Liu B, Cheng H D, Huang J H, Tian J W, Tang X L, Liu J F. Fully automatic and segmentation-robust classification of breast tumors based on local texture analysis of ultrasound images. Pattern Recognition, 2010, 43(1): 280-298 [9] Dietterich T G, Lathrop R H, Lozano-Perez T. Solving the multiple-instance problem with axis-parallel rectangles. Artificial Inteligence, 1997, 89(1-2): 31-71 [10] Garcia S, Derrac J, Cano J R, Herrera F. Prototype selection for nearest neighbor classification: taxonomy and empirical study. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(3): 417-435 [11] Bergeron C, Moore G, Zaretzki J, Breneman C M, Bennett K P. Fast bundle algorithm for multiple-instance learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(6): 1068-1079 [12] Zhu L, Zhao B, Gao Y. Multi-class multi-instance learning for lung cancer image classification based on bag feature selection. In: Proceedings of the 5th International Conference on Fuzzy Systems and Knowledge Discovery. Shandong, China: IEEE, 2008. 487-492 [13] Zhou Z H, Zhang M L. Solving multi-instance problems with classifier ensemble based on constructive clustering. Knowledge and Information Systems, 2007, 11(2): 155-170 [14] Li J, Xu D, Gao W. Removing label ambiguity in learning-based visual saliency estimation. IEEE Transactions on Image Processing, 2012, 21(4): 1513-1525 [15] Zhang Q, Goldman S A. EM-DD: an improved multi-instance learning technique. In: Proceedings of the 2002 Neural Information Processing Systems. Cambridge: MIT Press, 2002, 14: 1073-1080 [16] Ding J R, Cheng H D, Ning C P, Huang J H, Zhang Y T. Quantitative measurement for thyroid cancer characterization based on elastography. Journal of Ultrasound in Medicine, 2011, 30(9): 1259-1266 [17] Weidmann N, Frank E, Pfahringer B. A two-level learning method for generalized multi-instance problems. In: Proceedings of the 2003 European Conference Machine Learning. Cavtat-Dubrovnik, Croatia. 2003. 468-479 [18] Wang J, Zucker J D. Solving the multiple-instance problem: a lazy learning approach. In: Proceedings of the 17th International Conference on Machine Learning. San Francisco: Morgan Kaufmann, 2000. 1119-1126 [19] Li F F, Perona P. A Bayesian hierarchical model for learning natural scene categories. In: Proceedings of the 2005 IEEE Computer Vision and Pattern Recognition. San Diego, CA, USA: IEEE, 2005. 524-531
点击查看大图
计量
- 文章访问数: 1751
- HTML全文浏览量: 82
- PDF下载量: 1868
- 被引次数: 0