用自產(chǎn)生和自組織神經(jīng)網(wǎng)絡(luò)對超聲醫(yī)學(xué)圖像進(jìn)行自動分割
AUTOMATIC SEGMENTATION OF MEDICAL ULTRASONIC IMAGE USING SELF-CREATING AND ORGANIZING NEURAL NETWORK
-
摘要: 本文研究用自產(chǎn)生和自組織神經(jīng)網(wǎng)絡(luò)方法進(jìn)行超聲心臟圖像的自動分割。這種無監(jiān)督的聚類方法能夠自動搜索最佳的網(wǎng)絡(luò)輸出節(jié)點數(shù)而獲取圖像中的目標(biāo)數(shù),從而完成對圖像的自動分割。實驗結(jié)果表明,與自組織特征映射方法相比,本文的方法具有許多重要的優(yōu)點。Abstract: The automatic segmentation of ultrasonic heart image using self-creating and organizing neural network has been studied. This kind of unsupervised clustering method can search for the optimal number of output nodes automatically to get the number of textures in the image, and finish the automatic segmentation. Experimental results show that this method has significant benefits over self-organizing neural network method.
-
Manjunath B S, Chellappa R. Unsupervised texture segmentation using Markov random models. IEEE Trans. on PAMI, 1991, PAMI-13(5): 478-482.[2]Jain A K, Farrokhnia F. Unsupervised texture segmentation using Gabor filters[J].Pattern Recognition.1991, 24(12):1167-1186[3]Bouman C, Liu B. Multiple resolution segmentation of textured images. IEEE Trans. on PAMI, 1991, PAMI-13(2): 99-113.[4]Kohonen T. Self-Organization and Associative Memory. 2nd ed., New York: Springer-Verlag,[5]Ch.5: 119-157.[6]Choi D I, Park S H. Self-creating and organizing neural network. IEEE Trans. on NN, 1994,[7]NN-5(4): 561-575. -
計量
- 文章訪問數(shù): 2255
- HTML全文瀏覽量: 168
- PDF下載量: 449
- 被引次數(shù): 0
下載:
