基于CT影像的肺結(jié)節(jié)輔助診斷系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)
發(fā)布時(shí)間：2019-03-07 11:52
【摘要】：癌癥如今已成人類死亡的首要原因之一，而肺癌以高發(fā)病率，高死亡率成為當(dāng)今最致命的癌癥。盡早發(fā)現(xiàn)肺癌是治療肺癌的最好方法。CT是檢查肺癌的最佳手段之一，而精度越來(lái)越高的CT技術(shù)在得到更清晰圖像的同時(shí)，數(shù)據(jù)量也大大增加，醫(yī)生已不堪重負(fù)。速度快，不知疲倦的計(jì)算機(jī)成為幫助醫(yī)生診斷的有效工具。本文對(duì)肺結(jié)節(jié)檢測(cè)的相關(guān)技術(shù)進(jìn)行研究，設(shè)計(jì)并實(shí)現(xiàn)了基于CT影像的肺結(jié)節(jié)輔助診斷系統(tǒng)。 由于良性陰影和惡性陰影都有不同的種類，大小形態(tài)多樣，訓(xùn)練樣本僅僅分為良性和惡性兩大類使各個(gè)類內(nèi)相似程度低。為解決這個(gè)問(wèn)題，，以及眾多分類器利用歐氏距離度量方面存在的缺陷，本文提了出一種結(jié)合模糊C均值（Fuzzy-c means，F(xiàn)CM）聚類算法和馬氏距離的分類器。通過(guò)對(duì)已有樣本進(jìn)一步細(xì)分，增加各小類樣本的相似程度，然后用馬氏距離代替歐氏距離的方法，計(jì)算樣本與小類整體相似度，以提高分類的準(zhǔn)確性。 本文對(duì)ITK和VTK工具包進(jìn)行研究，結(jié)合MFC搭建系統(tǒng)平臺(tái)。通過(guò)對(duì)醫(yī)生診斷肺結(jié)節(jié)的過(guò)程進(jìn)行研究，將整個(gè)系統(tǒng)分為圖像讀取，肺部區(qū)域分割，肺部疑似陰影檢測(cè)，疑似陰影的判別，圖像顯示和圖像標(biāo)記及交互七個(gè)模塊。通過(guò)對(duì)各個(gè)模塊應(yīng)用技術(shù)的研究，設(shè)計(jì)并實(shí)現(xiàn)了相應(yīng)功能。 系統(tǒng)使用ITK和VTK工具包實(shí)現(xiàn)了圖像的讀取，顯示和圖像標(biāo)記及交互功能；利用最優(yōu)閾值法和區(qū)域連通算法進(jìn)行肺部區(qū)域粗分割，再用空洞填充算法和修補(bǔ)算法完成肺部區(qū)域的修補(bǔ)；應(yīng)用可變環(huán)形濾波器對(duì)肺部疑似陰影進(jìn)行檢測(cè)；最后利用本文提出的分類器進(jìn)行良性和惡性的劃分。通過(guò)對(duì)真實(shí)患者的圖像進(jìn)行檢測(cè)，本系統(tǒng)有較好的敏感性。
[Abstract]:Cancer is now one of the leading causes of human death, and lung cancer is the deadliest cancer of the day with high morbidity and mortality. Early detection of lung cancer is the best way to treat lung cancer. Ct is one of the best methods to examine lung cancer. While more and more accurate CT technology can get clearer images, the amount of data increases greatly, and doctors are overburdened. Fast, indefatigable computers have become an effective tool to help doctors diagnose. In this paper, the correlative technology of pulmonary nodule detection is studied, and the assistant diagnosis system based on CT image is designed and realized. Because there are different kinds of benign shadows and malignant shadows, the training samples are divided into two categories: benign and malignant, so the degree of similarity in each category is low. In order to solve this problem and the shortcomings of many classifiers in Euclidean distance measurement, a classifier combining fuzzy C-means (Fuzzy-c means,FCM) clustering algorithm and Mahalanobis distance is proposed in this paper. In order to improve the accuracy of classification, the similarity degree of each sample is increased by further subdivision of the existing samples, and then the Mahalanobis distance is used instead of the Euclidean distance to calculate the global similarity between the samples and the small classes. In this paper, ITK and VTK toolkit is studied, and the system platform is built with MFC. By studying the process of diagnosing pulmonary nodules, the whole system is divided into seven modules: image reading, lung region segmentation, lung suspected shadow detection, suspected shadow discrimination, image display and image marking and interaction. Through the research on the application technology of each module, the corresponding functions are designed and realized. The system uses ITK and VTK toolkit to realize the functions of image reading, display, image marking and interaction. The optimal threshold method and the region-connected algorithm are used to segment the lung region rough, then the cavity filling algorithm and the patch algorithm are used to complete the lung region repair, and the variable ring filter is used to detect the suspected shadow of the lung. Finally, the classifier proposed in this paper is used to classify benign and malignant. By detecting the images of real patients, the system has a good sensitivity.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類號(hào)】：R734.2;R816.41;TP391.41
本文編號(hào)：2436091
[Abstract]:Cancer is now one of the leading causes of human death, and lung cancer is the deadliest cancer of the day with high morbidity and mortality. Early detection of lung cancer is the best way to treat lung cancer. Ct is one of the best methods to examine lung cancer. While more and more accurate CT technology can get clearer images, the amount of data increases greatly, and doctors are overburdened. Fast, indefatigable computers have become an effective tool to help doctors diagnose. In this paper, the correlative technology of pulmonary nodule detection is studied, and the assistant diagnosis system based on CT image is designed and realized. Because there are different kinds of benign shadows and malignant shadows, the training samples are divided into two categories: benign and malignant, so the degree of similarity in each category is low. In order to solve this problem and the shortcomings of many classifiers in Euclidean distance measurement, a classifier combining fuzzy C-means (Fuzzy-c means,FCM) clustering algorithm and Mahalanobis distance is proposed in this paper. In order to improve the accuracy of classification, the similarity degree of each sample is increased by further subdivision of the existing samples, and then the Mahalanobis distance is used instead of the Euclidean distance to calculate the global similarity between the samples and the small classes. In this paper, ITK and VTK toolkit is studied, and the system platform is built with MFC. By studying the process of diagnosing pulmonary nodules, the whole system is divided into seven modules: image reading, lung region segmentation, lung suspected shadow detection, suspected shadow discrimination, image display and image marking and interaction. Through the research on the application technology of each module, the corresponding functions are designed and realized. The system uses ITK and VTK toolkit to realize the functions of image reading, display, image marking and interaction. The optimal threshold method and the region-connected algorithm are used to segment the lung region rough, then the cavity filling algorithm and the patch algorithm are used to complete the lung region repair, and the variable ring filter is used to detect the suspected shadow of the lung. Finally, the classifier proposed in this paper is used to classify benign and malignant. By detecting the images of real patients, the system has a good sensitivity.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類號(hào)】：R734.2;R816.41;TP391.41
【參考文獻(xiàn)】
相關(guān)期刊論文 前7條
1 姜慧研;何煒;;基于胸部CT圖像的肺癌識(shí)別方法的研究[J];電子學(xué)報(bào);2009年08期
2 張婧;李彬;田聯(lián)房;陳萍;;應(yīng)用規(guī)則的肺結(jié)節(jié)識(shí)別系統(tǒng)[J];計(jì)算機(jī)工程與應(yīng)用;2011年17期
3 徐釤;周四清;溫生貴;;Fisher判別在孤立性肺結(jié)節(jié)CT鑒別診斷中的應(yīng)用[J];醫(yī)學(xué)影像學(xué)雜志;2010年12期
4 蘇輝;李惠民;夏國(guó)兵;王寧;;孤立性肺結(jié)節(jié)的CT計(jì)量診斷研究[J];中國(guó)醫(yī)學(xué)計(jì)算機(jī)成像雜志;2011年01期
5 溫鐵祥;楊豐;;基于ITK、VTK和MFC的醫(yī)學(xué)圖像處理系統(tǒng)集成[J];醫(yī)療設(shè)備信息;2007年05期
6 魏穎;郭薇;孫月芳;季策;;基于局部灰度最大和改進(jìn)Mahalanobis距離分類的肺結(jié)節(jié)檢測(cè)算法[J];中國(guó)圖象圖形學(xué)報(bào);2008年09期
7 張思維;陳萬(wàn)青;鄭榮壽;李霓;曾紅梅;李光琳;魏文強(qiáng);趙平;;2003～2007年中國(guó)癌癥死亡分析[J];中國(guó)腫瘤;2012年03期
本文編號(hào)：2436091
本文鏈接：http://www.lk138.cn/yixuelunwen/yundongyixue/2436091.html
最近更新
教材專著
