基于群體智能的真假肺結(jié)節(jié)分類算法研究與實現(xiàn)
發(fā)布時間：2019-03-09 12:19
【摘要】：肺癌是目前已知類型腫瘤中死亡率最高的一種,肺結(jié)節(jié)是早期肺癌的表現(xiàn)形式,肺結(jié)節(jié)檢測是利用計算機(jī)輔助肺癌診斷的重要方式。由于肺組織的復(fù)雜,肺結(jié)節(jié)的種類多種多樣,導(dǎo)致了經(jīng)過圖像預(yù)處理之后仍然存在大量的假結(jié)節(jié)。本文針對檢測過程中,較難區(qū)分真假結(jié)節(jié)的問題,引入群體智能優(yōu)化方法,設(shè)計并實現(xiàn)了肺結(jié)節(jié)分類算法,從以下幾個方面對肺結(jié)節(jié)分類進(jìn)行了討論： (1)肺結(jié)節(jié)的形態(tài)和紋理多樣,單一特征不能取得較好的描述效果。本文對肺結(jié)節(jié)進(jìn)行多特征提取,包括灰度特征、紋理特征、梯度特征以及形狀特征,并且將二維與三維特征相結(jié)合,全面描述圖像特性。 (2)針對肺結(jié)節(jié)數(shù)據(jù)不均衡與特征高維的問題,引入代價敏感支持向量機(jī)(Cost-sensitive SVM),利用其中的RBF核函數(shù),將多維數(shù)據(jù)映射到高維空間,使原來在低維空間中不可分的數(shù)據(jù)變得可分,并提出用多分類器組合分類,進(jìn)一步提高分類效果。 (3)將群體智能優(yōu)化方法應(yīng)用于結(jié)節(jié)分類問題中,利用遺傳算法、粒子群算法、人工蜂群算法等方法實現(xiàn)特征選擇與分類器參數(shù)調(diào)整,有效提高了分類準(zhǔn)確率。 本文設(shè)計和實現(xiàn)的真假肺結(jié)節(jié)分類算法,保證了肺結(jié)節(jié)檢測中對真假結(jié)節(jié)的有效分類,具有良好的實用性。
[Abstract]:Lung cancer is the highest mortality among known types of tumors. Pulmonary nodules are the manifestations of early lung cancer. Detection of lung nodules is an important way of computer-aided diagnosis of lung cancer. Because of the complexity of lung tissue and the variety of pulmonary nodules, there are still a lot of false nodules after image preprocessing. In order to solve the problem that it is difficult to distinguish the true and false nodules in the detection process, this paper introduces the swarm intelligence optimization method, and designs and implements the lung nodule classification algorithm. The classification of pulmonary nodules is discussed from the following aspects: (1) the morphology and texture of pulmonary nodules are diverse and the single feature can not get a good description effect. In this paper, multi-feature extraction of pulmonary nodules is carried out, including gray-scale features, texture features, gradient features and shape features, and the two-dimensional and three-dimensional features are combined to describe the image characteristics in an all-round way. (2) to solve the problem of imbalance and high dimension of pulmonary nodule data, cost-sensitive support vector machine (Cost-sensitive SVM),) is introduced to map multi-dimensional data to high-dimensional space by using the RBF kernel function. In order to further improve the classification effect, the data which were not separable in the low dimensional space were made divisible, and the multi-classifier combination was proposed to further improve the classification effect. (3) the swarm intelligence optimization method is applied to the problem of node classification. Genetic algorithm, particle swarm algorithm and artificial bee swarm algorithm are used to realize feature selection and classifier parameter adjustment, which improves the classification accuracy effectively. The algorithm designed and implemented in this paper ensures the effective classification of true and false nodules in the detection of pulmonary nodules and has good practicability.
【學(xué)位授予單位】：東北大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2012
【分類號】：R563;TP18
本文編號：2437444
[Abstract]:Lung cancer is the highest mortality among known types of tumors. Pulmonary nodules are the manifestations of early lung cancer. Detection of lung nodules is an important way of computer-aided diagnosis of lung cancer. Because of the complexity of lung tissue and the variety of pulmonary nodules, there are still a lot of false nodules after image preprocessing. In order to solve the problem that it is difficult to distinguish the true and false nodules in the detection process, this paper introduces the swarm intelligence optimization method, and designs and implements the lung nodule classification algorithm. The classification of pulmonary nodules is discussed from the following aspects: (1) the morphology and texture of pulmonary nodules are diverse and the single feature can not get a good description effect. In this paper, multi-feature extraction of pulmonary nodules is carried out, including gray-scale features, texture features, gradient features and shape features, and the two-dimensional and three-dimensional features are combined to describe the image characteristics in an all-round way. (2) to solve the problem of imbalance and high dimension of pulmonary nodule data, cost-sensitive support vector machine (Cost-sensitive SVM),) is introduced to map multi-dimensional data to high-dimensional space by using the RBF kernel function. In order to further improve the classification effect, the data which were not separable in the low dimensional space were made divisible, and the multi-classifier combination was proposed to further improve the classification effect. (3) the swarm intelligence optimization method is applied to the problem of node classification. Genetic algorithm, particle swarm algorithm and artificial bee swarm algorithm are used to realize feature selection and classifier parameter adjustment, which improves the classification accuracy effectively. The algorithm designed and implemented in this paper ensures the effective classification of true and false nodules in the detection of pulmonary nodules and has good practicability.
【學(xué)位授予單位】：東北大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2012
【分類號】：R563;TP18
【參考文獻(xiàn)】
相關(guān)期刊論文 前4條
1 郭薇;魏穎;周翰遜;薛定宇;;基于混合分類的肺結(jié)節(jié)檢測算法[J];東北大學(xué)學(xué)報(自然科學(xué)版);2008年11期
2 楊瑞森;肺癌流行病學(xué)和早期診斷新技術(shù)[J];腫瘤防治雜志;2004年07期
3 關(guān)勇;基于支持向量機(jī)的圖像特征選擇研究[J];現(xiàn)代計算機(jī)(專業(yè)版);2004年04期
4 何中市;梁琰;黃學(xué)全;王健;;肺結(jié)節(jié)檢測中特征提取方法研究[J];小型微型計算機(jī)系統(tǒng);2009年10期
，本文編號：2437444
本文鏈接：http://sikaile.net/yixuelunwen/huxijib/2437444.html
最近更新
教材專著
