本文選題：多模態(tài) + 混合核函數(shù)��； 參考：《南方醫(yī)科大學(xué)》2014年碩士論文

【摘要】：腦腫瘤是指生長在顱腔內(nèi)的癌性物質(zhì),包括由腦、腦膜、血管、神經(jīng)及腦附件等腦實質(zhì)發(fā)生病變引起的原發(fā)性腫瘤,和由身體其他部位轉(zhuǎn)移侵入顱內(nèi)的繼發(fā)性腫瘤,在人群中發(fā)病率很高,可發(fā)生于任何年齡,以20～50歲最為多見。而且不論其性質(zhì)是良性還是惡性,一旦在顱內(nèi)占據(jù)一定空間,勢必壓迫腦組織,造成顱內(nèi)壓升高、中樞神經(jīng)損害,危及患者的生命。 近年來隨著加劇的環(huán)境污染、過重的生活壓力等因素的影響,腦腫瘤的發(fā)病率呈上升趨勢,最新的腫瘤流行病學(xué)調(diào)查研究結(jié)果表明,腦腫瘤發(fā)病率占全身腫瘤發(fā)病率的1.4%,而死亡比例超過2.4%,仍然是一類發(fā)病率、死亡率較高的腫瘤性疾病,成為威脅人類生命的重要疾病之一。膠質(zhì)瘤是最常見的原發(fā)性惡性腦腫瘤,居中樞神經(jīng)系統(tǒng)腫瘤首位。膠質(zhì)瘤多呈浸潤地彌漫性生長,形狀多變且與周圍組織邊界模糊,需要在全面的神經(jīng)系統(tǒng)檢查的基礎(chǔ)上,采用適當(dāng)?shù)某上穹绞捷o助檢查,使醫(yī)生能夠準(zhǔn)確地診斷并有效地分割腫瘤。 腦腫瘤起病緩慢,逐漸進(jìn)展,病程長短不一,一般表現(xiàn)為由顱內(nèi)高壓引起的頭痛、嘔吐、視神經(jīng)乳頭水腫等癥狀。不同的腫瘤發(fā)病部位,還可以表現(xiàn)為局灶性癥狀和體征如偏癱、失語、精神及意識障礙等麻痹性癥狀以及癲癇、肌肉抽搐等刺激性癥狀。臨床醫(yī)生依靠病史和可靠的查體,在神經(jīng)解剖、生理和各種疾病發(fā)展規(guī)律的診斷學(xué)基礎(chǔ)上,進(jìn)行綜合、客觀地分析,并進(jìn)一步選擇輔助檢查工具,全面分析研究腫瘤的部位、大小、性質(zhì)、血供及對周圍組織的累及程度,對腫瘤做出較為精確的定位與定性鑒別診斷。 腦腫瘤的治療原則上是以手術(shù)治療為主,輔助以放、化療、生物治療等方式。手術(shù)治療的前提就是需要合理有效的手段檢測和監(jiān)測腦腫瘤,盡可能地切除腫瘤,由于惡性腫瘤浸潤性生長,與周圍組織邊界模糊,不同醫(yī)生對同一病人的腫瘤圖像,或者同一個醫(yī)生不同時期對同一病人的腫瘤圖像分割結(jié)果存在差異,因而利用計算機圖像處理技術(shù)有效地識別分割腫瘤,是臨床應(yīng)用發(fā)展的必然趨勢。 臨床上常用于腦部輔助影像檢查的技術(shù)包括計算機斷層掃描(Computed tomography, CT)和磁共振成像(Magnetic Resonance Imaging, MRI)等。這些影像技術(shù)的發(fā)展及廣泛應(yīng)用,大大增加了腦腫瘤的檢出率,給醫(yī)生和患者帶來很大的幫助。 影像學(xué)設(shè)備為計算機處理提供多類圖像,磁共振成像(magnetic resonance imaging, MRI)是一種重要的解剖性影像診斷技術(shù),MRI圖像對軟組織有極好的分辨力。它作為一種無損傷、無輻射、多參數(shù)的成像方式,對組織的形態(tài)及病理改變的顯示有較高的敏感性,目前已經(jīng)成為診斷腦部腫瘤的重要工具。不同模態(tài)MRI圖像側(cè)重表現(xiàn)圖像不同的差異信息,比如,FLAIR模態(tài)中腫瘤與正常組織灰度差異明顯,T1C邊界紋理特征區(qū)別明顯。單一模態(tài)MRI圖像難以充分提供病變組織的可辨識信息,同時,腦膠質(zhì)瘤形狀多變且與周圍水腫區(qū)域邊界模糊,準(zhǔn)確分割圖像中的腫瘤十分困難。臨床上一般由有經(jīng)驗的醫(yī)生結(jié)合多模態(tài)(Multi-modality)MRI圖像,利用計算機輔助軟件,手動一層一層地勾畫腫瘤區(qū)域,主觀性很強,可重復(fù)操作性差。因而利用機器有效地分割腫瘤是臨床應(yīng)用發(fā)展的必然趨勢。 目前常見的腫瘤分割方法主要有基于圖像灰度信息的模糊聚類(FCM)方法、水平集方法、神經(jīng)網(wǎng)絡(luò)方法、AdaBoost迭代方法、以及支持向量機(Support Vector Machine, SVM)方法等。FCM方法實現(xiàn)簡單,運算速度快,但是由于醫(yī)學(xué)圖像信息復(fù)雜,邊緣不清晰,因此,種子點的選取對聚類結(jié)果影響很大,并且FCM方法難以利用圖像的空域信息。對于水平集方法,其最大優(yōu)點在于曲線的拓?fù)渥兓幚碜匀?穩(wěn)定性強,但是曲線初始化要求高,參數(shù)選擇敏感,分割結(jié)果容易陷入局部極值。神經(jīng)網(wǎng)絡(luò)方法學(xué)習(xí)能力強,但神經(jīng)網(wǎng)絡(luò)方法對訓(xùn)練樣本要求較高,容易出現(xiàn)過擬合及局部最優(yōu)的問題,使得其泛化性能變差,尤其在小樣本的情況下。AdaBoost算法分割精度較高,無過擬合現(xiàn)象,但是當(dāng)AdaBoost算法用于分割多模態(tài)MRI圖像時,訓(xùn)練所需樣本量大,訓(xùn)練時間長。以上分割方法各有優(yōu)勢,但離臨床應(yīng)用還存在一定差距。 基于統(tǒng)計學(xué)習(xí)理論的SVM方法表現(xiàn)出很多優(yōu)勢,SVM在樣本相對較少、特征維數(shù)較高的情況下仍能取得很好的推廣能力,同時引入核函數(shù)的SVM可以有效地處理非線性可分?jǐn)?shù)據(jù)。有文獻(xiàn)采用單一高斯核函數(shù)SVM方法,對多模態(tài)MRI圖像取得了較好的應(yīng)用效果。但是高斯核函數(shù)善于利用樣本的局部信息,僅引入單一高斯核函數(shù)可以對組織區(qū)別明顯的圖像,獲得良好的分割結(jié)果,對于邊界模糊、形狀多變的膠質(zhì)瘤,單一高斯核函數(shù)SVM的性能有一定的局限性,而具有局部性質(zhì)和全局性質(zhì)的混合核函數(shù)可以克服此類問題。人臉識別及掌紋識別中已經(jīng)廣泛地證實,參數(shù)最優(yōu)組合的混合核函數(shù)性能優(yōu)于單一核函數(shù)。人臉、掌紋結(jié)構(gòu)簡單、相對固定,而含腫瘤組織的腦部圖像,尤其是膠質(zhì)瘤中的低級膠質(zhì)瘤,呈彌漫的浸潤性生長,信號強度介于正常組織之間,腫瘤形狀、位置、大小多變,與周圍組織邊界模糊,組織紋理結(jié)構(gòu)復(fù)雜,如何充分使用圖像多模態(tài)信息,并尋找SVM模型參數(shù)的最優(yōu)組合,這是目前SVM方法應(yīng)用于腫瘤圖像分割的難點。 本文改進(jìn)現(xiàn)有的多模態(tài)MRI腦腫瘤分割方法,充分利用MRI圖像的多模態(tài)信息,同時結(jié)合支持向量機(Support Vector Machine, SVM)統(tǒng)計學(xué)習(xí)方法的優(yōu)勢,提出一種基于SVM模型參數(shù)優(yōu)化的多模態(tài)MRI圖像腫瘤分割方法。該方法首先分析MRI所成的多模態(tài)圖像,不同模態(tài)的圖像突出的腫瘤組織與正常組織的差異信息不同,有效區(qū)分腫瘤組織與周圍組織的支持向量位置有差異。其次優(yōu)化核函數(shù)支持向量機分類器,支持向量機分類器引入核函數(shù),巧妙地解決非線性可分問題。 核函數(shù)包括局部性核函數(shù)和全局性核函數(shù),不同類型的核函數(shù)側(cè)重的信息不同,性能有差異,結(jié)合局部性高斯核函數(shù)和全局性Sigmoid核函數(shù)的性能優(yōu)勢。然后,對單一模態(tài)訓(xùn)練最優(yōu)混合核函數(shù)SVM子分類器,僅需要小樣本的訓(xùn)練集,且性能優(yōu)于單一高斯核函數(shù)。由于不同模態(tài)圖像選擇的支持向量各有側(cè)重,分割結(jié)果存在差異。通過迭代修改分割錯誤數(shù)據(jù)點的權(quán)值,優(yōu)化選擇SVM模型子分類器權(quán)重系數(shù),得到多模態(tài)加權(quán)組合的SVM分類器模型,增強分割性能并應(yīng)用于多模態(tài)MRI圖像分割。實驗表明本文方法泛化性能良好,可行性和實用性強,可以實現(xiàn)對腦腫瘤的精確分割。 因此本文引入并提出的關(guān)鍵技術(shù)包括：(1)圖像去噪算法；(2)核函數(shù)混合方法；(3)SVM分類器組合方法。 (1)MRI圖像中的噪聲會降低圖像質(zhì)量,影響圖像的視覺觀察效果,使用圖像過程中,機器從圖像中獲取的信息減少,甚至是得到錯誤信息,使得圖像處理的算法結(jié)果準(zhǔn)確度受到影響,因而需要首先對圖像進(jìn)行濾波處理。針對MRI圖像中的加性噪聲,同質(zhì)區(qū)像素只差僅與噪聲有關(guān),引入一種增維型雙邊濾波的快速算法,在保證濾波性能的前提下,使雙邊濾波的快速實現(xiàn),既可以有效防止去噪過程破壞圖像的重要信息,又加快了整體方法的實現(xiàn)。 (2)優(yōu)化混合核函數(shù)的組合系數(shù)。通過自適應(yīng)調(diào)節(jié)新映射空間中各個樣本點的距離,削弱分類器懲罰因子對分類結(jié)果的影響,使得參數(shù)尋優(yōu)過程中可以固定懲罰因子,而不影響分割精度；同時,權(quán)重系數(shù)的優(yōu)化能改變序列最小優(yōu)化(Sequential Minimal Optimization, SMO)算法中的修正因子,從而影響支持向量的選取,以得到更優(yōu)的分類間隔,最終大大提高腦腫瘤的分割精度。 (3)多模態(tài)分類函數(shù)加權(quán)組合,充分利用不同模態(tài)突出差異信息的不同。支持向量機方法是一個很有優(yōu)勢的學(xué)習(xí)方法,但是醫(yī)學(xué)圖像信息復(fù)雜,有限樣本訓(xùn)練的最優(yōu)分類器并不能滿足高精度的要求,因而利用集成學(xué)習(xí)理論,通過構(gòu)造多個差異性大、性能較好而又獨立的子分類器,將其組合來提高最終分類器的泛化性能。利用MRI圖像的多模態(tài)信息,每種模態(tài)都對應(yīng)一個新的樣本集,分別訓(xùn)練子分類器。然后將子分類器組合,優(yōu)化分類結(jié)果。 本文以在線圖像庫MICCAI2012中34例腦膠質(zhì)瘤病人圖像數(shù)據(jù)為實驗樣本,采用本文算法對病人腦部圖像中的腫瘤進(jìn)行分割。通過臨床醫(yī)生判斷和定量分析,本文對腦腫瘤的分割準(zhǔn)確率達(dá)到92.50%,與真值結(jié)果非常接近。由此驗證了本文方法的可行性和實用性。
[Abstract]:Brain tumor is a carcinomatous substance that grows in the cranial cavity, including the primary tumor caused by brain parenchyma, such as brain, meninges, blood vessels, nerves and brain appendages, and secondary tumors that are transferred from other parts of the body, with high incidence in the population, at any age, most common at the age of 20~50, and no matter what it is. The nature is benign or malignant. Once occupying a certain space in the brain, it is bound to constriction brain tissue, causing intracranial pressure to increase, central nervous system damage, and endanger the lives of patients.
In recent years, the incidence of brain tumors is on the rise with the influence of aggravated environmental pollution, heavy life pressure and other factors. The latest oncology epidemiological investigation results show that the incidence of brain tumors is 1.4% of the incidence of whole body tumor, and the proportion of death is over 2.4%, which is still a kind of incidence and high mortality of tumor. Disease is one of the most important diseases that threaten human life. Glioma is the most common primary malignant brain tumor. It is the primary tumor in the middle and central nervous system. Gliomas are mostly infiltrating and diffuse growth, and the shape is changeable with the boundary of the surrounding tissue. It is necessary to use appropriate imaging methods on the basis of comprehensive neural examination. Examination enables doctors to accurately diagnose and effectively segment tumors.
The brain tumor begins slowly, progresses gradually, and the course of the disease is different. It is usually manifested by the symptoms of headache caused by intracranial hypertension, vomiting, and papillary edema of the optic nerve. Different parts of the tumor can also be shown as focal symptoms and signs, such as hemiplegia, aphasia, mental and cognitive disorders, as well as epilepsy, muscle twitching and so on. Sex symptoms. Clinicians rely on medical history and reliable physical examination, based on the diagnostics of neuroanatomy, physiology and the development of various diseases, and make a comprehensive, objective analysis, and further choose an auxiliary examination tool to comprehensively analyze the site, size, nature, blood supply and involvement of the surrounding tissue, and to make a more specific tumor to the tumor. Accurate localization and qualitative differential diagnosis.
The treatment of brain tumors is mainly based on surgical treatment, assisted by radiotherapy, chemotherapy, and biological treatment. The premise of surgical treatment is to detect and monitor brain tumors with reasonable and effective methods and to remove the tumor as much as possible. Because of the invasive growth of malignant tumor, the boundary of the surrounding tissue is blurred, and the tumor map of the same patient is different from the doctor. There is a difference between the image segmentation results of the same patient in different periods of the same doctor, so it is an inevitable trend for the development of clinical application to identify the tumor effectively by using computer image processing technology.
The techniques commonly used in brain assisted imaging include computed tomography (Computed tomography, CT) and magnetic resonance imaging (Magnetic Resonance Imaging, MRI). The development and extensive application of these imaging techniques greatly increase the detection rate of brain tumors and bring great help to doctors and patients.
Imaging equipment provides multi class images for computer processing. Magnetic resonance imaging (MRI) is an important anatomical imaging diagnosis technique. MRI images have excellent resolution to soft tissues. It is a imaging modality without damage, radiation and multiple parameters. It shows the morphological and pathological changes of tissue. High sensitivity has become an important tool for the diagnosis of brain tumors. Different modal MRI images focus on different information of different images. For example, the difference of the gray level between the tumor and the normal tissue in the FLAIR mode is obvious, and the difference of the texture features of the T1C boundary is obvious. The single modal MRI image is difficult to provide the identifiable information of the pathological tissue. At the time, the glioma has a changeable shape and blurred boundary with the surrounding area of edema. It is very difficult to accurately segment the tumor in the image. In general, it is commonly used by experienced doctors to combine multimodal (Multi-modality) MRI images and use computer aided software to manually delineate the swelling area with one layer and one layer. Therefore, the subjectivity is very strong, and the repeatability is poor. It is an inexorable trend to use machine to segment tumor effectively.
At present, the main methods of tumor segmentation are fuzzy clustering (FCM) based on image gray information. The level set method, neural network method, AdaBoost iterative method, and support vector machine (Support Vector Machine, SVM) method are simple and fast, but the edge is not clear because of the complicated medical image information. Therefore, the selection of seed points has great influence on the clustering results, and the FCM method is difficult to make use of the spatial information of the image. For the level set method, its biggest advantage is that the topological change of the curve is natural and strong, but the requirement of the curve initialization is high, the parameter is sensitive to the selection, and the segmentation result is easy to fall into the local extremum. Neural network method is easy to get. The learning ability is strong, but the neural network method requires higher training samples, easy to appear over fitting and local optimal problem, which makes its generalization performance worse. Especially in small sample cases,.AdaBoost algorithm has higher segmentation precision and no overfitting phenomenon, but when AdaBoost algorithm is used to segment multimodal MRI images, the training sample is trained. The above segmentation methods have their own advantages, but there is still a certain gap between them.
The SVM method based on the statistical learning theory shows many advantages. SVM can still obtain good generalization ability when the sample is relatively small and the feature dimension is high. At the same time, the SVM of the kernel function can effectively deal with the nonlinear separable data. A single Gauss kernel function SVM method is used in the literature to obtain a better multimodal MRI image. But the Gauss kernel function is good at using the local information of the sample, only introducing a single Gauss kernel function to distinguish the obvious image of the organization and obtain good segmentation results. It has some limitations for the performance of the single Gauss kernel function SVM, which has a certain local and global properties. The hybrid kernel function can overcome such problems. Face recognition and palmprint recognition have widely confirmed that the performance of the optimal combination of parameters is superior to that of a single kernel. Face, the palmprint structure is simple and relatively fixed, and the brain images containing tumor tissue, especially the low glioma in glioma, are diffuse infiltrating. Long, the signal intensity is between normal tissues, the shape, position and size of tumor are changeable, and the boundary of the surrounding tissue is fuzzy, the texture structure is complex. How to use the multi-modal information of the image fully and find the optimal combination of SVM model parameters is the difficulty of the SVM method applied to the segmentation of the tumor image.
In this paper, we improve the existing multimodal MRI brain tumor segmentation method, make full use of the multi-modal information of MRI image, and combine the advantages of Support Vector Machine (SVM) statistical learning method, and propose a multimode MRI image segmentation method based on the parameter optimization of SVM model. This method first analyzes the multimode of MRI. The difference in the difference between the tumor tissues and the normal tissues of the images of different modes is different, and the difference between the support vector positions of the tumor tissue and the surrounding tissue is distinguished. Secondly, the kernel function support vector machine classifier is optimized, and the support vector machine classifier is introduced into the kernel function, and the nonlinear separable problem is solved skillfully.
The kernel function includes the local kernel function and the global kernel function. The different types of kernel functions are different in information, the performance is different, and the performance advantages of the local Gauss kernel function and the global Sigmoid kernel are combined. Then, the optimal mixed kernel function SVM Subclassifier for single modal training only needs a small sample training set, and the performance is excellent. In the single Gauss kernel function. Because the support vectors selected from different modal images have each particular emphasis, the segmentation results are different. The weight coefficients of the SVM model sub classifier are optimized by iteratively modifying the weights of the error data points, and the SVM classifier model of multimodal weighted combination is obtained, and the segmentation performance is enhanced and applied to the multimodal MRI graph. Experiments show that the proposed method has good generalization performance, feasibility and practicability, and can accurately segment brain tumors.
Therefore, the key technologies introduced and put forward in this paper include: (1) image denoising algorithm; (2) kernel function hybrid method; (3) SVM classifier combination method.
(1) the noise in the MRI image can reduce the image quality and affect the visual observation effect. In the process of using the image, the information obtained by the machine is reduced, and even the error information is obtained. The accuracy of the image processing algorithm is affected by the image processing. Therefore, the image is filtered first. The addition of the image to the MRI image is added. Noise is only related to the noise in the homogeneity region, and a fast algorithm is introduced. The fast realization of the bilateral filtering can not only effectively prevent the de-noising process to destroy the important information of the image, but also accelerate the realization of the whole method.
(2) optimize the combination coefficient of the mixed kernel function. By adjusting the distance of each sample point in the new mapping space adaptively, the influence of the classifier penalty factor on the classification results is weakened, and the penalty factor can be fixed in the process of parameter optimization without affecting the segmentation precision. At the same time, the optimization of the weight coefficient can change the minimum sequence optimization (Sequenti The correction factor in the Al Minimal Optimization (SMO) algorithm affects the selection of support vectors to get better classification intervals, and ultimately greatly improves the segmentation accuracy of brain tumors.
(3) weighted combination of multi-modal classification functions, making full use of different modes to highlight different information. Support vector machine method is a very advantageous learning method, but medical image information is complex and the optimal classifier trained by limited samples can not satisfy the requirement of high precision. Therefore, the integrated learning theory is used to construct a number of different methods. A better and independent Subclassifier is used to improve the generalization performance of the final classifier. Using the multi-modal information of the MRI image, each mode corresponds to a new sample set, and the sub classifier is trained respectively. Then the Subclassifier is combined to optimize the classification results.
In this paper, the image data of 34 patients with glioma in the online image library MICCAI2012 are taken as experimental samples. The algorithm is used to segment the tumor in the brain image of the patient. The segmentation accuracy of the brain tumor is up to 92.50% through the clinician and the quantitative analysis, which is very close to the true value results. This method is verified by this method. Feasibility and practicability.

【學(xué)位授予單位】：南方醫(yī)科大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：R739.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 許新征;丁世飛;史忠植;賈偉寬;;圖像分割的新理論和新方法[J];電子學(xué)報;2010年S1期

2 高宏建;薛艷青;吳水才;艾海明;楊春蘭;白燕萍;盛磊;劉偉;;基于磁共振圖像的腦腫瘤自動識別與分析[J];北京工業(yè)大學(xué)學(xué)報;2012年06期

3 尚曉清;楊琳;趙志龍;;基于非凸正則化項的合成孔徑雷達(dá)圖像分割新算法[J];光子學(xué)報;2012年09期

4 李俊峰;楊豐;黃靖;;一種改進(jìn)的增維型雙邊濾波的快速算法[J];電路與系統(tǒng)學(xué)報;2013年01期

5 晁學(xué)民;周繼萍;;基于組合核函數(shù)支持向量機的人臉識別[J];重慶理工大學(xué)學(xué)報(自然科學(xué));2013年06期

6 孫銳;陳軍;高雋;;基于顯著性檢測與HOG-NMF特征的快速行人檢測方法[J];電子與信息學(xué)報;2013年08期

7 周濤;陸惠玲;陳志強;馬苗;;基于兩階段集成支持向量機的前列腺腫瘤識別[J];光學(xué)精密工程;2013年08期

8 奉國和;;SVM分類核函數(shù)及參數(shù)選擇比較[J];計算機工程與應(yīng)用;2011年03期

9 宣曉;廖慶敏;;基于特征提取的腦部MRI腫瘤自動分割[J];計算機工程;2008年09期

10 陸劍鋒,林海,潘志庚;自適應(yīng)區(qū)域生長算法在醫(yī)學(xué)圖像分割中的應(yīng)用[J];計算機輔助設(shè)計與圖形學(xué)學(xué)報;2005年10期

相關(guān)博士學(xué)位論文 前1條

1 王曉峰;水平集方法及其在圖像分割中的應(yīng)用研究[D];中國科學(xué)技術(shù)大學(xué);2009年

，

本文編號：1813724