本文選題：腦MR圖像分割 + SMM��； 參考：《華僑大學(xué)》2017年碩士論文

【摘要】：近幾十年,醫(yī)學(xué)影像技術(shù)飛速發(fā)展,特別是核磁共振成像技術(shù)(Magnetic Resonance Imaging,MRI)。該技術(shù)可以檢測(cè)人體各個(gè)部位的疾病,應(yīng)用極其廣泛。醫(yī)學(xué)圖像分析為醫(yī)生提供有效的參考信息,而醫(yī)學(xué)圖像分割是醫(yī)學(xué)圖像分析的基礎(chǔ)工作。大腦對(duì)于人體至關(guān)重要,它直接控制著人體的運(yùn)動(dòng)、感覺以及實(shí)現(xiàn)人體的很多高級(jí)功能。因此,腦MR圖像分割在醫(yī)學(xué)領(lǐng)域尤為重要。而腦MR圖像的高噪聲、灰度不均勻、邊緣模糊等特點(diǎn)為其分割帶來(lái)了挑戰(zhàn)。另外,專家參與圖像分割的方式消耗時(shí)間長(zhǎng),而圖像數(shù)量巨大,因此急需實(shí)現(xiàn)腦MR圖像分割的自動(dòng)化�；诨旌夏Ｐ偷膱D像分割方法借助圖像的灰度直方圖,將圖像中像素的灰度值擬合成某些特定的分布。其中,高斯混合模型(Gaussian Mixture Model,GMM)具有直觀、實(shí)現(xiàn)簡(jiǎn)便、符合很多數(shù)據(jù)的分布等特點(diǎn),因而得到了廣泛應(yīng)用。而尾部較高的學(xué)生t分布代替高斯分布后,混合模型在圖像分割過程中對(duì)噪聲更魯棒,因此t混合模型(Student’s t Mixture Model,SMM)又引起了許多學(xué)者的關(guān)注。為了應(yīng)對(duì)以上腦MR圖像分割中的面對(duì)的挑戰(zhàn),本文在SMM的基礎(chǔ)上做出了兩點(diǎn)改進(jìn),并將改進(jìn)后的模型用于腦MR圖像分割:1)基于一種新的馬爾可夫隨機(jī)場(chǎng)(Markov Random Field,MRF)的表示方法,設(shè)計(jì)并實(shí)現(xiàn)了一種結(jié)合MRF和SMM的腦MR圖像分割方法。該方法利用MRF將圖像中像素的空間關(guān)系信息引入混合模型,因此得到的分割結(jié)果對(duì)噪聲更魯棒。而且本文推導(dǎo)出該模型求解的期望最大化算法(Expectation Maximization Algorithm,EM算法),該算法能直接得到模型中參數(shù)的封閉解,避免了復(fù)雜的計(jì)算操作。實(shí)驗(yàn)表明該方法的表現(xiàn)優(yōu)于其它流行的腦MR圖像分割方法及其它同樣基于MRF的混合模型方法。2)針對(duì)傳統(tǒng)的SMM用于圖像分割時(shí)需要人為設(shè)定分割數(shù)目的缺點(diǎn),本文提出一種基于截?cái)嗟依死走^程的無(wú)限t混合模型(Truncated Dirichlet Process Student’s t Mixture Model,tDPSMM)的腦MR圖像分割方法。該方法用截?cái)嗟依死走^程作為模型的先驗(yàn)信息,達(dá)到了使模型自動(dòng)確定分割數(shù)目的目標(biāo),而且保證了該無(wú)限混合模型推理、計(jì)算的簡(jiǎn)便性。本文也推導(dǎo)出該模型下的EM算法,最終利用貝葉斯最大后驗(yàn)概率準(zhǔn)則將模型應(yīng)用于腦MR圖像分割。與其它無(wú)限混合模型方法及經(jīng)典的腦MR圖像分割方法進(jìn)行對(duì)比實(shí)驗(yàn)后,我們發(fā)現(xiàn)該方法能更快速準(zhǔn)確地實(shí)現(xiàn)腦MR圖像分割。
[Abstract]:In recent decades, medical imaging technology has developed rapidly, especially magnetic Resonance imaging. This technique can detect diseases in various parts of human body and is widely used. Medical image analysis provides effective reference information for doctors, and medical image segmentation is the basic work of medical image analysis. The brain is very important to the human body. It directly controls the movement, sensation and many advanced functions of the human body. Therefore, brain Mr image segmentation is particularly important in the field of medicine. However, the high noise, uneven grayscale and edge blur of Mr images bring challenges to the segmentation of Mr images. In addition, the way that experts participate in image segmentation takes a long time, and the number of images is huge, so it is urgent to realize the automation of brain Mr image segmentation. The method of image segmentation based on mixed model is based on the gray histogram of the image, and the gray value of the pixel in the image is combined to some special distribution. Among them, Gao Si mixed model Gaussian Mixture Model-GMMM has been widely used because of its intuitionistic, simple implementation and consistent with the distribution of many data. When the student t distribution with higher tail is replaced by Gao Si distribution, the mixed model is more robust to noise in the image segmentation process, so the t mixed model (Students t Mixture Model SMMM) has attracted many scholars' attention. In order to meet the challenges in brain Mr image segmentation, two improvements are made on the basis of SMM, and the improved model is applied to segment brain Mr image at 1: 1) based on a new representation method of Markov random field Markov Random field (MRF). A brain Mr image segmentation method combining MRF and SMM is designed and implemented. In this method, the spatial relation information of pixels in the image is introduced into the mixed model by MRF, so the segmentation result is more robust to noise. Moreover, this paper deduces the expectation maximization Maximization algorithm EM algorithm, which can directly obtain the closed solution of the parameters in the model, and avoid the complicated calculation operation. Experiments show that the performance of this method is better than that of other popular brain Mr image segmentation methods and other mixed model methods based on MRF. In this paper, a method of brain Mr image segmentation based on truncated Dirichlet Process Student's t Mixture Model DPS MMM is proposed. The method uses truncated Delikley process as the prior information of the model, and achieves the goal of automatically determining the number of segments of the model, and ensures the simplicity of reasoning and calculation of the infinite mixed model. The EM algorithm based on this model is also derived in this paper. Finally, the model is applied to the segmentation of brain Mr image by using Bayesian maximum a posteriori probability criterion. Compared with other infinite mixed model methods and classical brain Mr image segmentation methods, we find that this method can achieve the segmentation of brain Mr images more quickly and accurately.
【學(xué)位授予單位】：華僑大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：R445.2;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 施紅英;沈毅;;混合模型在醫(yī)學(xué)研究中的應(yīng)用與展望[J];國(guó)際流行病學(xué)傳染病學(xué)雜志;2006年06期

2 谷達(dá),谷寧;在結(jié)構(gòu)混合模型基礎(chǔ)上的放大新概念[J];國(guó)外醫(yī)藥(抗生素分冊(cè));1996年03期

3 車平;;一種利用混合模型研究基因與疾病間關(guān)聯(lián)的方法[J];東北師大學(xué)報(bào)(自然科學(xué)版);2009年02期

4 胡良平;混合模型及其在藥理研究中的應(yīng)用[J];數(shù)理統(tǒng)計(jì)與管理;1999年06期

5 趙景義;余紅梅;;參數(shù)混合模型在長(zhǎng)期生存者資料分析中的應(yīng)用[J];中國(guó)衛(wèi)生統(tǒng)計(jì);2010年03期

6 李冬田;;用混合模型法鑒定小DNA病毒B19陽(yáng)性血清的實(shí)驗(yàn)室標(biāo)準(zhǔn)[J];國(guó)外醫(yī)學(xué)(微生物學(xué)分冊(cè));1990年06期

7 李莉;余紅梅;劉桂芬;趙景義;;長(zhǎng)期生存者資料分析中半?yún)?shù)混合模型的應(yīng)用[J];山西醫(yī)科大學(xué)學(xué)報(bào);2009年09期

8 宮本一;具有親緣關(guān)系矩陣的混合模型的方差組分迭代估計(jì)——應(yīng)用于計(jì)算BLUP的方差比值和遺傳參數(shù)[J];遺傳學(xué)報(bào);1992年05期

9 劉宏艷;胡治國(guó);彭聃齡;;積極與消極情緒關(guān)系的理論及研究[J];心理科學(xué)進(jìn)展;2008年02期

10 吳曉林,施啟順,柳小春,彭英林,蔣雋,楊仕柳,肖兵南;用混合模型定位一個(gè)復(fù)雜家豬家系13號(hào)染色體QTL的研究[J];遺傳學(xué)報(bào);2002年01期

相關(guān)會(huì)議論文 前10條

1 沈樂君;;基于混合模型的多目標(biāo)實(shí)時(shí)跟蹤算法[A];2013體育計(jì)算機(jī)應(yīng)用論文集[C];2013年

2 紀(jì)琳;黃震宇;;中頻振動(dòng)混合模型理論的應(yīng)用局限性分析[A];現(xiàn)代振動(dòng)與噪聲技術(shù)（第九卷）[C];2011年

3 汪傳建;李曉光;王大玲;于戈;;一種基于混合模型的文本分類器的研究與實(shí)現(xiàn)[A];第二十一屆中國(guó)數(shù)據(jù)庫(kù)學(xué)術(shù)會(huì)議論文集（研究報(bào)告篇）[C];2004年

4 徐斌;馬盡文;;一種柯西混合模型上梯度型BYY和諧學(xué)習(xí)算法[A];第十三屆全國(guó)信號(hào)處理學(xué)術(shù)年會(huì)（CCSP-2007）論文集[C];2007年

5 蘭永紅;吳敏;佘錦華;;基于二維混合模型的最優(yōu)重復(fù)控制[A];第二十六屆中國(guó)控制會(huì)議論文集[C];2007年

6 張勝利;張沅;;混合模型方法對(duì)QTL的檢測(cè)及定位效果[A];生命科學(xué)與生物技術(shù)：中國(guó)科協(xié)第三屆青年學(xué)術(shù)年會(huì)論文集[C];1998年

7 馬凌;周江;王文鼐;;突發(fā)性業(yè)務(wù)流的Gamma泊松混合模型及排隊(duì)性能研究[A];中國(guó)通信學(xué)會(huì)第五屆學(xué)術(shù)年會(huì)論文集[C];2008年

8 沈文豪;聶大仕;謝菲;;氣升式內(nèi)環(huán)流反應(yīng)器的液相流動(dòng)混合模型[A];第一屆全國(guó)化學(xué)工程與生物化工年會(huì)論文摘要集(上)[C];2004年

9 趙廣建;，

本文編號(hào)：1778411