【摘要】：隨著醫(yī)學(xué)水平的不斷提高,最為普遍的肺部成像技術(shù)——CT技術(shù)也愈發(fā)先進(jìn),導(dǎo)致每位就診人員的肺部CT數(shù)據(jù)成倍增加,加之患者數(shù)量大幅上升,產(chǎn)生海量的CT圖像。數(shù)據(jù)的爆炸式增多是導(dǎo)致對(duì)肺癌診斷的漏檢、誤診率居高不下的主要原因。目前,由于CAD系統(tǒng)的使用,在一定程度上減少了泛診,節(jié)約了醫(yī)生的時(shí)間與精力,成為醫(yī)生必不可少的“助手”。針對(duì)CAD系統(tǒng)診斷流程的繁瑣性,以及最終對(duì)結(jié)節(jié)分類(lèi)的不準(zhǔn)確性,本文主要進(jìn)行了以下兩方面的研究:1.由于結(jié)節(jié)外形的多樣性以及特征的復(fù)雜性,在一定程度上會(huì)導(dǎo)致結(jié)節(jié)的過(guò)分割,過(guò)分割會(huì)使有效信息丟失,直接影響診斷的準(zhǔn)確度。但如果將原始CT圖像(512*512大小)作為任何學(xué)習(xí)網(wǎng)絡(luò)的輸入,其學(xué)習(xí)過(guò)程的復(fù)雜性是不可想象的,甚至是無(wú)法完成的。在本文中,首次將目標(biāo)追蹤應(yīng)用于肺部圖像。本文提出的基于超像素的追蹤算法是在粒子濾波框架下進(jìn)行的,首先構(gòu)建一個(gè)基于超像素的肺實(shí)質(zhì)外觀模板,然后建立待追蹤圖像的置信圖并設(shè)置自適應(yīng)大小的追蹤窗體。在追蹤的過(guò)程中實(shí)時(shí)更新模板以保證模板的準(zhǔn)確性。保留序列圖像中每張CT最優(yōu)狀態(tài)時(shí)的追蹤信息。對(duì)原始CT圖像進(jìn)行追蹤,快速準(zhǔn)確地定位了肺部感興趣區(qū)域肺實(shí)質(zhì),有效節(jié)約了時(shí)間成本,為后期的分類(lèi)做了必要準(zhǔn)備。追蹤算法可以快速定位出肺部感興趣區(qū)域,有效削弱了CT圖像中除肺實(shí)質(zhì)外多余信息的干擾,降低了深度學(xué)習(xí)應(yīng)用于肺部疾病診斷的復(fù)雜性。2.傳統(tǒng)分類(lèi)方法BP神經(jīng)網(wǎng)絡(luò)、支持向量機(jī)(SVM)、自生成神經(jīng)網(wǎng)絡(luò)(SGNN)等,需人工提取特征,由于不同人有不同的主觀標(biāo)準(zhǔn),因此提取的特征集相差很大。且分類(lèi)器結(jié)構(gòu)簡(jiǎn)單,無(wú)法運(yùn)用于大樣本數(shù)據(jù)集,針對(duì)上述問(wèn)題,本文將深度信念網(wǎng)絡(luò)引入對(duì)結(jié)節(jié)的良惡性診斷中。由于深度信念網(wǎng)絡(luò)擁有多層非線(xiàn)性結(jié)構(gòu),對(duì)復(fù)雜的數(shù)據(jù)關(guān)系有極強(qiáng)的非線(xiàn)性映射能力,且學(xué)習(xí)過(guò)程是由有監(jiān)督學(xué)習(xí)與無(wú)監(jiān)督學(xué)習(xí)交替完成,能更好的完成特征學(xué)習(xí)與分類(lèi)任務(wù)。在本文中,運(yùn)用上述追蹤方法,得到肺部感興趣區(qū)域,將所有的感興趣區(qū)域圖像進(jìn)行雙線(xiàn)性插值,統(tǒng)一圖像尺寸,形成深度學(xué)習(xí)網(wǎng)絡(luò)的輸入數(shù)據(jù)。接著根據(jù)數(shù)據(jù)集,自定義5層的深度信念網(wǎng)絡(luò)。對(duì)數(shù)據(jù)進(jìn)行訓(xùn)練與測(cè)試,在訓(xùn)練過(guò)程中對(duì)網(wǎng)絡(luò)涉及到的重要參數(shù)隱藏層節(jié)點(diǎn)數(shù)、批數(shù)據(jù)大小以及樣本循環(huán)次數(shù)等參數(shù)進(jìn)行分析和調(diào)優(yōu),更有效的實(shí)現(xiàn)對(duì)結(jié)節(jié)的分類(lèi)。
[Abstract]:With the continuous improvement of medical level, the most common lung imaging technology-CT technology is also more advanced, resulting in a doubling of the lung CT data of each patient, coupled with a large increase in the number of patients, resulting in a large number of CT images. The explosion of data is the main reason leading to the missed diagnosis of lung cancer and the high misdiagnosis rate. At present, because of the use of CAD system, the extensive diagnosis has been reduced to a certain extent, the time and energy of doctors have been saved, and it has become an indispensable "assistant" of doctors. In view of the tedious diagnostic process of CAD system and the inaccuracy of classification of nodules in the end, the following two aspects are studied in this paper: 1. Because of the variety of the appearance and the complexity of the features of the nodules, the excessive segmentation of the nodules will lead to the loss of effective information, which directly affects the accuracy of the diagnosis. However, if the original CT image (512? 512) is used as the input of any learning network, the complexity of the learning process is unimaginable or even impossible to complete. In this paper, target tracking is applied to lung image for the first time. The hyperpixel-based tracking algorithm proposed in this paper is carried out in the framework of particle filtering. Firstly, a hyperpixel-based pulmonary parenchyma appearance template is constructed, and then the confidence map of the image to be tracked is established and the tracking form with adaptive size is set up. Update the template in real time during the tracking process to ensure the accuracy of the template. Preserves tracking information for each CT optimal state in a sequential image. After tracing the original CT images, the lung parenchyma of the region of interest was located quickly and accurately, which effectively saved the time cost and made the necessary preparation for the later classification. The tracking algorithm can quickly locate the region of interest of the lungs, effectively weaken the interference of excess information in CT images except pulmonary parenchyma, and reduce the complexity of deep learning applied to the diagnosis of pulmonary diseases. 2. Traditional classification methods, such as BP neural network, support vector machine (SVM), self-generating neural network (SGNN) and so on, need to extract features manually. Because different people have different subjective criteria, the extracted feature sets vary greatly. The classifier is simple in structure and can not be applied to large sample data sets. In order to solve these problems, this paper introduces the depth belief network into the diagnosis of benign and malignant nodules. Because the deep belief network has multi-layer nonlinear structure and strong nonlinear mapping ability to complex data relations, and the learning process is completed alternately by supervised learning and unsupervised learning, the task of feature learning and classification can be completed better. In this paper, the above tracking method is used to obtain the region of interest of the lung. All the images of the region of interest are interpolated bilinear to unify the image size and form the input data of the depth learning network. Then, according to the data set, a 5-layer depth belief network is defined. The data are trained and tested. In the training process, the number of hidden layer nodes, batch data size and the number of cycles of samples are analyzed and optimized to realize the classification of nodules more effectively. 3) the number of hidden layer nodes, the size of batch data and the number of cycles of samples are analyzed and optimized in the process of training and testing.
【學(xué)位授予單位】：太原理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：R734.2;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前4條

1 張洋;;基于雙線(xiàn)性插值法的圖像縮放算法的設(shè)計(jì)與實(shí)現(xiàn)[J];電子設(shè)計(jì)工程;2016年03期

2 張娟;毛曉波;陳鐵軍;;運(yùn)動(dòng)目標(biāo)跟蹤算法研究綜述[J];計(jì)算機(jī)應(yīng)用研究;2009年12期

3 顧曉暉;馬曉宇;陳卉;;LIDC中肺結(jié)節(jié)注釋信息的提取及數(shù)據(jù)庫(kù)的建立[J];數(shù)理醫(yī)藥學(xué)雜志;2009年02期

4 呂俊,張興華;幾種快速BP算法的比較研究[J];現(xiàn)代電子技術(shù);2003年24期

，

本文編號(hào)：2468446