本文關(guān)鍵詞：基于特征融合的多模MRI腦腫瘤分割　出處：《武漢理工大學(xué)》2015年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： MR圖像 Gabor小波 卷積神經(jīng)網(wǎng)絡(luò) 特征融合 核熵成分分析

【摘要】：在醫(yī)學(xué)影像中,核磁共振成像(Magnetic Resonance Imaging,MRI)是一種重要的成像技術(shù),此成像技術(shù)有著高質(zhì)量的圖像顯示效果,已被廣泛應(yīng)用于醫(yī)學(xué)中對(duì)人體各組織器官病變的診斷中,特別是對(duì)腦部病變組織的檢測(cè)。MRI腦腫瘤分割在實(shí)際的臨床診斷上提供了很大的幫助,如何能夠更快速準(zhǔn)確的分割出腦腫瘤是MRI腦腫瘤研究的難點(diǎn)。又因腦腫瘤核磁共振圖像的可變性和復(fù)雜性,以及腦腫瘤的大小、形狀都各不相同,對(duì)腦腫瘤特征的提取就顯得尤為重要。近年來,關(guān)于此方面的研究也有很多,雖然有很不錯(cuò)的效果,但是在此研究領(lǐng)域還有廣泛的提升空間。本文主要研究MRI腦腫瘤分割:將Gabor小波提取的腦腫瘤特征與卷積神經(jīng)網(wǎng)絡(luò)提取的腦腫瘤特征用特征融合方法形成新的特征,然后在此改進(jìn)算法的基礎(chǔ)上引入了一種新的降維方法——核熵成分分析算法對(duì)融合后的特征進(jìn)行降維,并取得了不錯(cuò)的效果,具體工作內(nèi)容如下:(1)分析了Gabor小波算法的基本原理,使用5個(gè)尺度和8個(gè)方向的40個(gè)Gabor濾波器進(jìn)行卷積,提取特征,并將卷積后的結(jié)果作為特征向量,然后驗(yàn)證了基于SVM(Support Vector Machine)的腦腫瘤分割,并對(duì)分割結(jié)果做后處理,將其在GBM數(shù)據(jù)集上進(jìn)行實(shí)驗(yàn),并對(duì)結(jié)果進(jìn)行分析。(2)分析了卷積神經(jīng)網(wǎng)絡(luò)的基本原理,研究了卷積神經(jīng)網(wǎng)絡(luò)的網(wǎng)絡(luò)結(jié)構(gòu)和訓(xùn)練過程。在卷積層作卷積運(yùn)算,增強(qiáng)了原始信號(hào)強(qiáng)度,降低了噪聲;在降采樣層對(duì)前層圖像作抽樣處理,此方法在保證不降低有用信息的基礎(chǔ)上減少了需要處理的數(shù)據(jù)量。在卷積神經(jīng)網(wǎng)絡(luò)中還使用了參數(shù)減少和權(quán)值共享等方式,提高了運(yùn)算速度。將其應(yīng)用到GBM數(shù)據(jù)集上進(jìn)行實(shí)驗(yàn),并分析其優(yōu)勢(shì)和劣勢(shì)。(3)為了提高分割的精度,提出了將人工選取的特征與機(jī)器學(xué)習(xí)的特征相結(jié)合的方法。展開了特征融合的相關(guān)工作,即將Gabor小波和卷積神經(jīng)網(wǎng)絡(luò)提取的特征根據(jù)特征融合中的串行組合方式串連成一個(gè)列向量作為新的特征向量,同時(shí)基于核熵成分分析對(duì)融合后的新特征作降維處理,然后對(duì)降維前與降維后的特征分別用SVM進(jìn)行分類,根據(jù)實(shí)驗(yàn)結(jié)果分析其優(yōu)劣。
[Abstract]:Magnetic Resonance imaging (MRI) is an important imaging technique in medical imaging. This imaging technique has a high quality image display effect, and has been widely used in the diagnosis of human tissues and organs in medicine. In particular, the detection of brain lesions. MRI brain tumor segmentation in the actual clinical diagnosis provides a great help. How to segment brain tumors more quickly and accurately is a difficult point in the study of brain tumors in MRI. Because of the variability and complexity of MRI images and the size and shape of brain tumors are different. The extraction of brain tumor features is particularly important. In recent years, there are a lot of research on this aspect, although there are very good results. However, there is still wide scope for improvement in this field. This paper focuses on the segmentation of MRI brain tumors:. The features of brain tumors extracted by Gabor wavelet and those extracted by convolution neural network are fused to form new features. Based on the improved algorithm, a new dimensionality reduction method, kernel entropy component analysis algorithm, is introduced to reduce the dimension of the fused features, and good results are obtained. The main work is as follows: (1) the basic principle of Gabor wavelet algorithm is analyzed, and 40 Gabor filters with 5 scales and 8 directions are used for convolution and feature extraction. The convolution result is taken as the feature vector, and then the segmentation of brain tumor based on SVM(Support Vector Machine is verified, and the segmentation result is processed. The basic principle of the convolutional neural network is analyzed by the experiment on the GBM data set and the analysis of the results. The network structure and training process of the convolution neural network are studied. The convolution operation in the convolution layer enhances the intensity of the original signal and reduces the noise. This method can reduce the amount of data needed to be processed on the basis of not reducing the useful information, and using parameter reduction and weight sharing in the convolution neural network. In order to improve the segmentation accuracy, the algorithm is applied to the GBM data set for experiment, and its advantages and disadvantages are analyzed. In this paper, a method of combining artificial selected features with machine learning features is proposed, and the related work of feature fusion is carried out. The feature extracted by Gabor wavelet and convolution neural network is serially connected to a column vector as a new feature vector according to the serial combination in feature fusion. At the same time, the new features are reduced based on kernel entropy component analysis, and then the features before and after dimensionality reduction are classified by SVM, and the advantages and disadvantages are analyzed according to the experimental results.
【學(xué)位授予單位】：武漢理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：R739.41;R445.2;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前8條

1 柴瑞敏;曹振基;;基于Gabor小波與深度信念網(wǎng)絡(luò)的人臉識(shí)別方法[J];計(jì)算機(jī)應(yīng)用;2014年09期

2 吳巍;趙亮;;基于相似性模型的磁共振成像腦瘤檢測(cè)算法[J];華中科技大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年10期

3 楊賢棟;葉少珍;;一種高效檢測(cè)MRI腦腫瘤圖像邊緣的方法[J];福州大學(xué)學(xué)報(bào)(自然科學(xué)版);2010年03期

4 王巖松;金偉其;鐘克洪;;隨機(jī)紋理表面缺陷檢測(cè)方法與應(yīng)用[J];中國(guó)圖象圖形學(xué)報(bào);2009年01期

5 郭依正;陳健美;宋余慶;朱玉全;陸虎;;醫(yī)學(xué)肝臟圖像Gabor小波紋理特征研究[J];計(jì)算機(jī)應(yīng)用與軟件;2008年11期

6 宣曉;廖慶敏;;基于特征提取的腦部MRI腫瘤自動(dòng)分割[J];計(jì)算機(jī)工程;2008年09期

7 劉正光;馬喜妹;鄒亮;;一種基于主動(dòng)輪廓模型的MRI醫(yī)學(xué)圖像序列邊緣提取算法[J];計(jì)算機(jī)應(yīng)用;2006年07期

8 孫權(quán)森,曾生根,王平安,夏德深;典型相關(guān)分析的理論及其在特征融合中的應(yīng)用[J];計(jì)算機(jī)學(xué)報(bào);2005年09期

相關(guān)碩士學(xué)位論文 前1條

1 王東明;基于特征級(jí)融合的目標(biāo)識(shí)別方法研究[D];沈陽(yáng)理工大學(xué);2013年

，

本文編號(hào)：1374413