【摘要】：隨著人們生活水平的提高,心血管疾病已經(jīng)成為人類的頭號(hào)殺手,嚴(yán)重威脅著人類的健康。心血管疾病發(fā)病急、隱蔽性強(qiáng)、死亡率高,因此對(duì)心血管疾病的早期診斷和風(fēng)險(xiǎn)評(píng)估尤為重要。左心室心肌的運(yùn)動(dòng)情況能夠反映心臟的供血功能,為多種心臟疾病的診斷提供重要依據(jù)。通過對(duì)左心室的運(yùn)動(dòng)估計(jì),能夠確定每個(gè)心肌點(diǎn)的運(yùn)動(dòng)軌跡,得到對(duì)臨床診斷有參考意義的形變函數(shù)和可視化圖形。點(diǎn)集匹配是常見的左心室運(yùn)動(dòng)估計(jì)方法,但是現(xiàn)有的點(diǎn)集匹配方法僅僅考慮了點(diǎn)間距離,缺乏對(duì)點(diǎn)集形狀的考慮。本文針對(duì)此問題提出了一種基于曲面結(jié)構(gòu)的點(diǎn)集匹配算法,主要包括以下三個(gè)部分:其一,為了描述左心室的曲面結(jié)構(gòu)特征,提出了基于張量投票的曲面特征提取算法。我們將每個(gè)點(diǎn)作為投票點(diǎn),其對(duì)應(yīng)的近似曲面特征方向作為投票方向,向周圍的點(diǎn)進(jìn)行投票,然后每個(gè)點(diǎn)對(duì)接收到的票數(shù)進(jìn)行累積分解,得出糾正后的方向。模擬數(shù)據(jù)以及真實(shí)的左心室數(shù)據(jù)實(shí)驗(yàn)結(jié)果驗(yàn)證了張量投票算法的有效性。其二,針對(duì)現(xiàn)有的點(diǎn)集匹配算法僅僅考慮點(diǎn)間距離,缺乏對(duì)點(diǎn)集形狀的考慮等問題,提出了一種基于曲面結(jié)構(gòu)的點(diǎn)集匹配算法并將其應(yīng)用于心臟的運(yùn)動(dòng)估計(jì)。我們將左心室的曲面特征描述引入到點(diǎn)集匹配算法中,提出了一個(gè)即約束點(diǎn)間距離又約束點(diǎn)集形狀的代價(jià)函數(shù),詳細(xì)推導(dǎo)了擬牛頓法(Quasi-Newton Method,QN)的求解過程以優(yōu)化該代價(jià)函數(shù),得到左心室運(yùn)動(dòng)的變換參數(shù),估計(jì)左心室心肌點(diǎn)的運(yùn)動(dòng)軌跡。多組左心室的實(shí)驗(yàn)結(jié)果證明我們提出的代價(jià)函數(shù)是可行的。其三,針對(duì)QN算法在高維參數(shù)空間出現(xiàn)的發(fā)散問題,提出了用隨機(jī)梯度下降算法(Stochastic Gradient Descent,SGD)來優(yōu)化代價(jià)函數(shù)的方法,推導(dǎo)了SGD算法的梯度和算法流程。針對(duì)SGD算法收斂精度不如QN算法這個(gè)問題,提出了SGD+QN的優(yōu)化算法,先通過SGD方法來控制變換參數(shù),使收斂于一個(gè)較穩(wěn)定狀態(tài),然后運(yùn)用QN算法來進(jìn)一步提高其收斂精度。實(shí)驗(yàn)結(jié)果證明,在高維空間時(shí),SGD+QN的方法即能保證算法的穩(wěn)定性,又能保證算法的精度。本文針對(duì)左心室曲面結(jié)構(gòu)的提取、左心室點(diǎn)集匹配的精確性及穩(wěn)定性三個(gè)方面進(jìn)行了初步研究,研究成果較好地解決了基于點(diǎn)集匹配的左心室運(yùn)動(dòng)估計(jì)方法中存在的一些問題。
[Abstract]:With the improvement of people's living standard, cardiovascular disease has become the leading killer of human beings, which is a serious threat to human health. Cardiovascular disease is urgent, hidden and high mortality, so it is very important for early diagnosis and risk assessment of cardiovascular disease. The left ventricular motion can reflect the blood supply function of the heart and provide important basis for the diagnosis of various heart diseases. By estimating the motion of the left ventricle, the motion track of each myocardial point can be determined, and the deformation function and visual figure which are useful for clinical diagnosis can be obtained. Point set matching is a common method for estimating left ventricular motion, but the existing point set matching methods only consider the distance between points, and lack the consideration of point set shape. In this paper, a point set matching algorithm based on curved surface structure is proposed, which includes the following three parts: firstly, in order to describe the surface features of the left ventricle, a surface feature extraction algorithm based on Zhang Liang voting is proposed. We take each point as the polling point, and the corresponding approximate surface characteristic direction as the voting direction, and vote to the surrounding point, and then each point cumulatively decomposes the number of votes received to get the corrected direction. The experimental results of simulated data and real left ventricular data verify the effectiveness of Zhang Liang voting algorithm. Secondly, a point set matching algorithm based on curved surface structure is proposed and applied to the motion estimation of the heart, aiming at the problem that the existing point set matching algorithm only considers the distance between points and the shape of the point set. In this paper, we introduce the curved surface characteristic description of left ventricle into the point set matching algorithm, and propose a cost function of the constraint point set shape as well as the distance between the constrained points. The quasi Newton method (Quasi-Newton Method,) is derived in detail. In order to optimize the cost function, the transformation parameters of left ventricular motion are obtained, and the trajectory of left ventricular motion point is estimated. The experimental results of multiple groups of left ventricle show that the proposed cost function is feasible. Thirdly, aiming at the divergence of QN algorithm in high-dimensional parameter space, a stochastic gradient descent algorithm (Stochastic Gradient Descent,SGD) is proposed to optimize the cost function, and the gradient and algorithm flow of SGD algorithm are deduced. In order to solve the problem that the convergence accuracy of SGD algorithm is lower than that of QN algorithm, the optimization algorithm of SGD QN is proposed. Firstly, the transformation parameters are controlled by SGD method to make it converge to a more stable state, and then the convergence accuracy is further improved by using QN algorithm. The experimental results show that the, SGD QN method can not only guarantee the stability of the algorithm, but also ensure the accuracy of the algorithm in high dimensional space. In this paper, the extraction of the curved structure of the left ventricle, the accuracy and stability of the point set matching of the left ventricle are studied preliminarily. The research results solve some problems in the estimation method of the left ventricular motion based on the point set matching.
【學(xué)位授予單位】：深圳大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：R54;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前3條

1 舒中力,余霞,辜嘉,舒華忠;一種基于近似樹的三維心血管圖像的匹配算法[J];生物醫(yī)學(xué)工程研究;2004年02期

2 李杰;原s，

本文編號(hào)：2378487