本文選題：CT影像 + 肺結(jié)節(jié)　； 參考：《電子科技大學(xué)》2017年碩士論文

【摘要】：隨著我國(guó)空氣質(zhì)量的下降,霧霾天氣的頻繁出現(xiàn),肺部疾病的發(fā)病率呈現(xiàn)擴(kuò)大的趨勢(shì)。隨著醫(yī)療設(shè)備的進(jìn)步與發(fā)展,CT影像成為常見(jiàn)的肺部檢查工具。雖然醫(yī)療設(shè)備的更新給診斷的準(zhǔn)確性帶來(lái)了極大的提高,但另一方面,成像數(shù)量的增大給醫(yī)生帶來(lái)的是更大的工作量。為了解決這一矛盾,20世紀(jì)90年代開(kāi)始出現(xiàn)計(jì)算機(jī)輔助檢測(cè)和診斷相關(guān)研究和應(yīng)用,相關(guān)應(yīng)用也證明了計(jì)算機(jī)輔助檢測(cè)和診斷在降低漏診和誤診等方面有著不可小覷的作用。本文針對(duì)DICOM標(biāo)準(zhǔn)胸部CT序列影像,采用LIDC-IDRI影像庫(kù)作為研究素材,從DICOM標(biāo)準(zhǔn)的影像解析、CT序列影像的肺實(shí)質(zhì)分割、邊界輪廓修補(bǔ)、肺結(jié)節(jié)檢測(cè)提取和肺結(jié)節(jié)識(shí)別分類(lèi)等步驟進(jìn)行相關(guān)算法研究和實(shí)驗(yàn)論證。具體內(nèi)容:(1)對(duì)DICOM影像進(jìn)行結(jié)構(gòu)分析,并解析影像。然后研究使用基于區(qū)域生長(zhǎng)的快速肺實(shí)質(zhì)分割算法對(duì)解析后影像進(jìn)行分割,得到肺實(shí)質(zhì)影像。(2)針對(duì)分割后影像邊界出現(xiàn)的肺結(jié)節(jié)漏分割現(xiàn)象,研究邊界修補(bǔ)相關(guān)算法,引入凸包和近鄰點(diǎn)連接實(shí)現(xiàn)肺實(shí)質(zhì)邊界修補(bǔ)。對(duì)肺實(shí)質(zhì)影像進(jìn)行基于層厚的平均密度投影算法的研究,旨在抑制水平面影像中血管和支氣管等結(jié)構(gòu)的表現(xiàn),從而凸顯肺結(jié)節(jié)和血管、支氣管間的影像結(jié)構(gòu)差異。(3)針對(duì)平均密度投影后的影像分別研究基于GMM的單張和序列的肺結(jié)節(jié)檢測(cè)提取算法,從影像中檢測(cè)提取得到肺結(jié)節(jié)和結(jié)構(gòu)類(lèi)似的影像區(qū)域。(4)為了從提取到的結(jié)構(gòu)中分類(lèi)識(shí)別得到肺結(jié)節(jié),本文研究并使用SVM分類(lèi)器來(lái)對(duì)肺結(jié)節(jié)進(jìn)行分類(lèi)識(shí)別。由于肺結(jié)節(jié)在空間上表現(xiàn)為球形或者類(lèi)球形結(jié)構(gòu),本文對(duì)提取的影像區(qū)域進(jìn)行多平面重建,利用水平面、矢狀面和冠狀面三個(gè)平面上的影像來(lái)反映肺結(jié)節(jié)的形態(tài)結(jié)構(gòu),然后從三個(gè)平面中提取計(jì)算肺結(jié)節(jié)特征,進(jìn)行特征數(shù)據(jù)的歸一化處理。隨后使用LIBSVM工具在MATLAB下研究使用網(wǎng)格搜索算法進(jìn)行SVM核函數(shù)的參數(shù)尋優(yōu),使用提取到的特征數(shù)據(jù)進(jìn)行分類(lèi)器訓(xùn)練,并使用測(cè)試數(shù)據(jù)對(duì)分類(lèi)器進(jìn)行測(cè)試,通過(guò)肺癌輔助診斷系統(tǒng)評(píng)價(jià)指標(biāo)對(duì)分類(lèi)識(shí)別結(jié)果進(jìn)行評(píng)價(jià)。最后本文將研究的算法進(jìn)行實(shí)現(xiàn),開(kāi)發(fā)出一個(gè)計(jì)算機(jī)輔助診斷系統(tǒng)。通過(guò)大量的算法實(shí)驗(yàn),本文算法在肺實(shí)質(zhì)分割中分割成功率達(dá)99%以上,肺結(jié)節(jié)識(shí)別的特異性達(dá)92.9%,相比同類(lèi)識(shí)別算法有較為顯著的優(yōu)勢(shì)。
[Abstract]:With the decline of air quality and the frequent appearance of haze weather, the incidence of lung diseases is increasing. With the progress and development of medical equipment, CT imaging has become a common pulmonary examination tool. Although the renewal of medical equipment has greatly improved the accuracy of diagnosis, on the other hand, the increase of imaging quantity has brought more workload to doctors. In order to solve this contradiction, the research and application of computer-aided detection and diagnosis began to appear in the 1990s. The related applications also proved that computer-aided detection and diagnosis play an important role in reducing missed diagnosis and misdiagnosis. In this paper, DICOM standard chest CT images were analyzed by using LIDC-IDRI image library as research materials. Lung parenchyma segmentation and boundary contour repair were analyzed from DICOM standard CT sequence images. Lung nodule detection and extraction and identification and classification of pulmonary nodules were studied and demonstrated by experiments. The structure of DICOM image is analyzed and the image is analyzed. Then we use the fast segmentation algorithm of lung parenchyma based on region growth to segment the parsed image and get lung parenchyma image. (2) aiming at the lung nodule leakage segmentation phenomenon which appears in the edge of the segmented image, we study the algorithm of boundary repair. The pulmonary parenchyma boundary repair is realized by introducing convex hull and adjacent point connection. The study of the average density projection algorithm based on slice thickness of lung parenchyma images aims to suppress the appearance of blood vessels and bronchi in horizontal images, thereby highlighting pulmonary nodules and blood vessels. (3) for the images with average density projection, the extraction algorithms of lung nodules based on single sheet and sequence of GMM were studied, respectively. In order to classify and recognize pulmonary nodules from the extracted structures, SVM classifier is used to classify and recognize pulmonary nodules. Because the pulmonary nodules are spherical or spherical in space, the extracted image regions are reconstructed in multi-plane, and the morphologic structure of the pulmonary nodules is reflected by the images of horizontal plane, sagittal plane and coronal plane. Then the feature of pulmonary nodule is extracted from three planes, and the feature data is normalized. Then the LIBSVM tool is used to study the parameter optimization of the SVM kernel function using the grid search algorithm under MATLAB, and the extracted feature data is used to train the classifier, and the test data is used to test the classifier. The classification and identification results were evaluated by the evaluation index of lung cancer auxiliary diagnosis system. Finally, the algorithm is implemented and a computer aided diagnosis system is developed. Through a large number of algorithm experiments, the success rate of this algorithm in lung parenchyma segmentation is over 99%, and the specificity of lung nodule recognition is 92.99.This algorithm has a significant advantage over the similar recognition algorithm.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：R734.2;R730.44;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 邢謙謙;王凱;李穆;陸燕琴;曹蕾;;肺部CT圖像的結(jié)節(jié)檢測(cè)和類(lèi)型判別準(zhǔn)則設(shè)計(jì)及應(yīng)用[J];中國(guó)醫(yī)學(xué)影像技術(shù);2016年07期

2 王健峰;張磊;陳國(guó)興;何學(xué)文;;基于改進(jìn)的網(wǎng)格搜索法的SVM參數(shù)優(yōu)化[J];應(yīng)用科技;2012年03期

3 張婧;李彬;田聯(lián)房;陳萍;王立非;;結(jié)合規(guī)則和SVM方法的肺結(jié)節(jié)識(shí)別[J];華南理工大學(xué)學(xué)報(bào)(自然科學(xué)版);2011年02期

4 張書(shū)旭;余輝;楊俊;周凌宏;張海南;林生趣;;平均密度和最大密度投影CT在放療中的應(yīng)用研究[J];中國(guó)輻射衛(wèi)生;2010年03期

5 陳兆學(xué);趙曉靜;聶生東;;一種基于CT圖像的肺實(shí)質(zhì)自動(dòng)分割的簡(jiǎn)易方法[J];計(jì)算機(jī)應(yīng)用與軟件;2010年03期

6 劉陽(yáng);趙大哲;劉積仁;;基于K-L變換和支持向量機(jī)的三維肺結(jié)節(jié)識(shí)別[J];東北大學(xué)學(xué)報(bào)(自然科學(xué)版);2009年09期

7 朱樹(shù)先;張仁杰;;支持向量機(jī)核函數(shù)選擇的研究[J];科學(xué)技術(shù)與工程;2008年16期

8 曹蕾;占杰;余曉鍔;陳武凡;;基于自動(dòng)閾值的CT圖像快速肺實(shí)質(zhì)分割算法[J];計(jì)算機(jī)工程與應(yīng)用;2008年12期

9 王煒;郭小明;王淑艷;劉麗琴;;關(guān)于核函數(shù)選取的方法[J];遼寧師范大學(xué)學(xué)報(bào)(自然科學(xué)版);2008年01期

10 鐘靈;張建州;張九龍;;基于樣條曲線擬合的肺區(qū)輪廓修補(bǔ)算法[J];計(jì)算機(jī)應(yīng)用研究;2007年09期

相關(guān)會(huì)議論文 前1條

1 屈若yN;周寶森;;2004-2010年中國(guó)肺癌死亡分布及趨勢(shì)分析[A];全國(guó)腫瘤流行病學(xué)和腫瘤病因?qū)W學(xué)術(shù)會(huì)議論文集[C];2015年

相關(guān)博士學(xué)位論文 前1條

1 吳龍海;高分辨率CT圖像的肺部病變計(jì)算機(jī)輔助診斷研究[D];中國(guó)科學(xué)技術(shù)大學(xué);2008年

相關(guān)碩士學(xué)位論文 前6條

1 羅旋;基于DICOM序列影像的肺結(jié)節(jié)檢測(cè)算法研究[D];電子科技大學(xué);2015年

2 尚明;肺癌住院患者直接經(jīng)濟(jì)負(fù)擔(dān)及影響因素研究[D];山東大學(xué);2013年

3 邱實(shí);基于CT圖像的肺結(jié)節(jié)分割與檢測(cè)算法研究[D];西安電子科技大學(xué);2012年

4 李越;基于形態(tài)學(xué)及灰度熵的肺結(jié)節(jié)檢測(cè)算法[D];北京交通大學(xué);2011年

5 袁立志;1657例原發(fā)性支氣管肺癌臨床特點(diǎn)分析[D];寧夏醫(yī)科大學(xué);2010年

6 曹雨田;基于CT影像的孤立性肺結(jié)節(jié)識(shí)別與分析研究[D];西安理工大學(xué);2008年

，

本文編號(hào)：1817793