本文選題：多元模式分析 + 多模態(tài)分析��； 參考：《電子科技大學(xué)》2014年博士論文

【摘要】：通過影像數(shù)據(jù)分析,傳統(tǒng)基于組比較的單元分析發(fā)現(xiàn)神經(jīng)精神疾病大腦結(jié)構(gòu)和功能的改變。但是單元分析方法只能在組水平進(jìn)行推斷,導(dǎo)致這些發(fā)現(xiàn)對(duì)臨床診斷的價(jià)值非常有限。而且,目前多數(shù)神經(jīng)精神疾病的診斷都依據(jù)其臨床癥狀,還沒有客觀的生物學(xué)標(biāo)記物。因此,如果想讓神經(jīng)影像學(xué)的發(fā)現(xiàn)更好地應(yīng)用于臨床診斷,就必須提供個(gè)體水平的預(yù)測(cè)。本文主要以磁共振數(shù)據(jù)為載體,以多元模式分析(Multivariate Pattern Analysis,MVPA)方法學(xué)為手段,介紹了結(jié)構(gòu)特征、功能特征,以及結(jié)構(gòu)-結(jié)構(gòu)、功能-功能、功能-結(jié)構(gòu)特征融合在腦模式識(shí)別研究中的應(yīng)用。同時(shí),在不同程度上對(duì)MVPA方法進(jìn)行了改進(jìn)和創(chuàng)新,將其運(yùn)用到神經(jīng)、精神疾病中進(jìn)行個(gè)體水平的診斷并探測(cè)這些疾病的病理生理機(jī)制。本文內(nèi)容主要包括5個(gè)部分:1.針對(duì)不同治療反應(yīng)的重度抑郁癥患者(Major Depressive Disorder,MDD)的結(jié)構(gòu)磁共振圖像(Magnetic Resonance Imaging,MRI)數(shù)據(jù),提出Searchlight算法與主成分分析(Principal Component Analysis,PCA)相結(jié)合的特征選擇方法。從腦結(jié)構(gòu)MRI中提取灰質(zhì)、白質(zhì)體積作為特征,使用提出的方法進(jìn)行特征選擇并用支持向量機(jī)(Support Vector Machine,SVM)進(jìn)行分類。實(shí)驗(yàn)結(jié)果表明提出的MVPA方法優(yōu)于其它比較流行的方法。采用灰質(zhì)與白質(zhì)體積作為特征信息區(qū)分不同治療反應(yīng)MDD患者的準(zhǔn)確率均為82.9%。另外,采用灰質(zhì)體積特征信息從健康對(duì)照中區(qū)分難治型、易治型MDD的準(zhǔn)確率分別為85.7%和82.4%;采用白質(zhì)體積作為特征信息從健康對(duì)照中區(qū)分難治型、易治型MDD的準(zhǔn)確率分別為85.7%和91.2%。額、頂、顳、枕葉和小腦一些區(qū)域的灰質(zhì)和白質(zhì)體積對(duì)MDD具有較高的診斷和預(yù)后能力。該方法可能為MDD的診斷和預(yù)后提供了一個(gè)新途徑。2.針對(duì)社交焦慮障礙(Social Anxiety Disorder,SAD)的靜息態(tài)功能MRI數(shù)據(jù),提出使用大尺度功能腦網(wǎng)絡(luò)對(duì)其建立診斷模型的方法。通過靜息態(tài)功能MRI數(shù)據(jù)構(gòu)建大尺度功能連接網(wǎng)絡(luò)并將其作為分類特征。然后,采用F分值法進(jìn)行特征排序并利用SVM進(jìn)行分類。實(shí)驗(yàn)結(jié)果表明對(duì)SAD患者的正確區(qū)分率為82.5%,敏感度為85%,特異度為80%。同時(shí),發(fā)現(xiàn)用于區(qū)分SAD病人的一致連接主要位于幾個(gè)靜息態(tài)網(wǎng)絡(luò)內(nèi)部或者之間的連接,包括:默認(rèn)網(wǎng)絡(luò)、視覺網(wǎng)絡(luò)、感覺運(yùn)動(dòng)網(wǎng)絡(luò)、情感網(wǎng)絡(luò)以及小腦區(qū)。此外,右側(cè)眶額皮層在分類過程中占了最高的權(quán)重。這些發(fā)現(xiàn)為確定SAD潛在的生物學(xué)標(biāo)記物提供了一定的依據(jù)。3.針對(duì)傳統(tǒng)基于LASSO特征選擇法的局限性,提出高階圖匹配的特征選擇方法,并用老年癡呆癥(Alzheimer's Disease,AD)神經(jīng)影像學(xué)(Alzheimer's Disease Neuroimaging Initiative,ADNI)數(shù)據(jù)進(jìn)行驗(yàn)證�；贚ASSO的特征選擇法對(duì)每個(gè)樣本的目標(biāo)向量進(jìn)行獨(dú)立的估計(jì)而沒有考慮與其它樣本的聯(lián)系,從而忽略了訓(xùn)練集目標(biāo)向量之間的幾何關(guān)系。同時(shí),預(yù)測(cè)向量與目標(biāo)向量應(yīng)該有相似的幾何關(guān)系。將這個(gè)問題看作預(yù)測(cè)圖與目標(biāo)圖之間的圖匹配問題,通過提出二元關(guān)系正則項(xiàng)和三元關(guān)系正則項(xiàng)解決了LASSO特征選擇法的不足。本文采用灰質(zhì)體積和皮層厚度作為分類特征,由高階圖匹配方法對(duì)兩種特征分別進(jìn)行特征選擇并用多核學(xué)習(xí)法進(jìn)行特征融合。該方法對(duì)AD和輕度認(rèn)知障礙(Mild Cognitive Impairment,MCI)分類分別得到了92.17%和81.57%的準(zhǔn)確率,優(yōu)于基于LASSO的特征選擇法,這驗(yàn)證了方法的有效性。4.針對(duì)創(chuàng)傷后應(yīng)激障礙(Post-traumatic Stress Disorder,PTSD)的靜息態(tài)功能MRI數(shù)據(jù),提出融合多水平特征對(duì)其進(jìn)行分類的方法。從靜息態(tài)功能MRI中提取出3個(gè)水平(區(qū)域內(nèi),區(qū)域間和全腦)的特征,采用t檢驗(yàn)與SVM遞歸特征消除(Recursive Feature Elimination,RFE)相結(jié)合的方法進(jìn)行特征選擇,并用多核SVM融合多水平功能特征進(jìn)行分類。實(shí)驗(yàn)結(jié)果表明每個(gè)水平的特征都能成功的區(qū)分PTSD病人,通過多水平特征的融合可以進(jìn)一步提高分類的性能。所提出的模型對(duì)PTSD分類得到的準(zhǔn)確率為92.5%,比只使用2個(gè)水平特征和1個(gè)水平特征的準(zhǔn)確率分別至少高5%和17.5%。而且,發(fā)現(xiàn)邊緣系統(tǒng)和前額葉皮層為分類提供了最具有區(qū)分力的特征。該研究可能為改善PTSD的臨床診斷提供了一個(gè)補(bǔ)充的方法。5.針對(duì)以往多模態(tài)數(shù)據(jù)分類問題中特征選擇的局限性,提出約束模態(tài)間關(guān)系的多模態(tài)多任務(wù)特征選擇方法,并使用ADNI數(shù)據(jù)進(jìn)行驗(yàn)證。傳統(tǒng)的多模態(tài)分類問題中的特征選擇法往往在每個(gè)模態(tài)內(nèi)部單獨(dú)進(jìn)行,并沒有考慮到不同模態(tài)之間特征選擇的關(guān)系。因此,提出將每個(gè)模態(tài)中進(jìn)行的特征選擇作為一個(gè)任務(wù),在特征選擇時(shí)對(duì)模態(tài)間的關(guān)系進(jìn)行約束,并保持模態(tài)內(nèi)部選擇特征的稀疏性。在特征方面,從正電子發(fā)射斷層成像(Positron Emission Tomography,PET)中提取出區(qū)域平均代謝強(qiáng)度,結(jié)構(gòu)MRI中提取出區(qū)域平均灰質(zhì)體積作為分類特征。由提出的方法進(jìn)行特征選擇并用多核SVM進(jìn)行多模態(tài)特征融合。實(shí)驗(yàn)結(jié)果表明,對(duì)AD的分類準(zhǔn)確率達(dá)到了94.37%,MCI的分類準(zhǔn)確率達(dá)到了78.80%,MCI轉(zhuǎn)化組和非轉(zhuǎn)化組的分類準(zhǔn)確率達(dá)到了67.83%。這些結(jié)果顯著優(yōu)于傳統(tǒng)的特征選擇方法,這證實(shí)了所提出方法的優(yōu)越性。
[Abstract]:Through the analysis of the image data, the traditional unit analysis based on the group comparison found the changes in the brain structure and function of the neuropsychiatric disorders. But the method of unit analysis can only be inferred at the level of the group, resulting in the very limited value of these findings to the clinical diagnosis. And the diagnosis of most psychic diseases is based on its clinical symptoms, There is no objective biological marker. Therefore, if we want to make the findings of neuroimaging better applied to clinical diagnosis, it is necessary to provide the prediction of individual level. This paper mainly uses the magnetic resonance data as the carrier and the Multivariate Pattern Analysis (MVPA) methodology as a means to introduce the structural features and functional characteristics. And the application of structure structure, structure, function, function, functional structure feature fusion in brain pattern recognition research. At the same time, the MVPA method is improved and innovating to different degrees. It is applied to the individual level diagnosis and detection of the pathophysiological mechanism of these diseases in the nerve and mental diseases. The main contents of this paper include 5 parts. 1. in view of the structural magnetic resonance imaging (Magnetic Resonance Imaging, MRI) data of Major Depressive Disorder (MDD) in patients with different therapeutic responses (Magnetic Resonance Imaging, MRI), a feature selection method combining Searchlight algorithm with principal component analysis (Principal Component Analysis) is proposed. As a feature, the proposed method is used for feature selection and classification with Support Vector Machine (SVM). The experimental results show that the proposed MVPA method is superior to other popular methods. The accuracy of using gray matter and white matter volume as the characteristic information to distinguish different treatment responses to MDD patients is 82.9%.. The accuracy rates of MDD were 85.7% and 82.4%, respectively, with the gray matter volume information from the healthy control area. The white matter volume was used as the characteristic information from the healthy control middle area. The accuracy rate of the MDD was 85.7% and 91.2%. respectively. The gray matter and white matter volume in the top, temporal, occipital and cerebellum areas were MDD It has a high diagnostic and prognostic ability. This method may provide a new approach for the diagnosis and prognosis of MDD,.2. for the resting state functional MRI data of social anxiety disorder (Social Anxiety Disorder, SAD), and proposes a recipe for the establishment of a diagnostic model using a large scale functional brain network. The construction of large scale work through the resting state function MRI data. We can connect the network and use it as a classification feature. Then, the F segmentation method is used to sort the features and use SVM to classify them. The experimental results show that the correct discrimination rate for SAD patients is 82.5%, the sensitivity is 85%, the specificity is 80%., and the consistent connection used to distinguish the SAD patients is mainly located within or between several resting networks. The connection, including the default network, the visual network, the sensory network, the emotional network and the cerebellum. In addition, the right orbital frontal cortex accounts for the highest weight in the classification process. These findings provide a certain basis for determining the potential biological markers of SAD based on the limitations of the.3. based on the LASSO feature selection method. The matching feature selection method is validated with Alzheimer's Disease (AD) neuroimaging (AD) neuroimaging (Alzheimer's Disease Neuroimaging Initiative, ADNI) data. The feature selection method based on LASSO is used to estimate the target vectors of each sample independently without considering the connection with other samples, thus neglecting the training. At the same time, the geometric relationship between the target vectors and the prediction vector should be similar to the target vector. The problem is regarded as a graph matching problem between the prediction graph and the target graph. The deficiency of the LASSO feature selection method is solved by putting forward the regular term of the two element relation and the regular term of the three element relation. This paper uses the gray matter volume and the cortex. As a classification feature, the two features are selected by the high order graph matching method and the multi kernel learning method is used for feature fusion. The accuracy of the method for AD and Mild Cognitive Impairment (MCI) classification is 92.17% and 81.57% respectively, which is superior to the LASSO based feature selection method, which verifies the method. The effectiveness of.4. is based on the resting state function MRI data of post traumatic stress disorder (Post-traumatic Stress Disorder, PTSD), and proposes a method of classifying it with multi level features. 3 levels (intra, interregional and whole brain) are extracted from the resting state function MRI, and t test and SVM recursion feature elimination (Recursive Featur) are used. E Elimination, RFE) combines the feature selection method and classifies the multilevel function features with multi core SVM fusion. The experimental results show that the characteristics of each level can successfully distinguish the PTSD patients. The classification performance can be further improved by the fusion of multilevel features. The accuracy rate of the proposed model for PTSD classification can be further improved. For 92.5%, the accuracy rate of only 2 horizontal and 1 horizontal features is at least 5% and 17.5%., respectively, and it is found that the edge and prefrontal cortex provide the most regional characteristics for classification. This study may provide a supplementary method for improving the clinical diagnosis of PTSD,.5. for the problem of the previous multi-modal data classification problem. In the limitation of feature selection, a multi modal and multi task feature selection method that constrains the inter modal relationship is proposed, and the ADNI data is used to verify. The feature selection method in the traditional multi-modal classification problem is often carried out separately in each mode, and does not take into account the relationship between different modes. The feature selection in the mode is used as a task to restrict the relationship between the modes and maintain the sparsity of the selection characteristics in the mode. In the characteristic aspect, the average metabolic intensity of the region is extracted from the Positron Emission Tomography (PET), and the regional average is extracted from the structure MRI. The gray matter volume is classified as the classification feature. The method is selected by the proposed method and multimodal SVM is used to fuse the multi-modal features. The experimental results show that the classification accuracy of AD is 94.37%, the classification accuracy of MCI reaches 78.80%, and the classification accuracy of the MCI transformation group and the non transformation group reaches 67.83%. these results are significantly better than the traditional ones. The method of feature selection confirms the superiority of the proposed method.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2014
【分類號(hào)】：R445.2;R741

【共引文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳志曄;李金鋒;劉夢(mèng)雨;馬林;;2型糖尿病患者腦部皮層及皮層下獎(jiǎng)賞環(huán)路研究[J];南方醫(yī)科大學(xué)學(xué)報(bào);2013年09期

2 黃牧坤;石磊;嚴(yán)華成;曾曉暉;張營;關(guān)慧;趙樹進(jìn);;Ghrelin基因Leu90Gln多態(tài)性與中國漢族人散發(fā)性阿爾茨海默病的關(guān)系[J];廣東醫(yī)學(xué);2013年17期

3 周治明;趙建農(nóng);郭大靜;張維;吳偉;張波莉;吳媛;王晚千;周紅俐;;輕微型肝性腦病神經(jīng)元自發(fā)活動(dòng)異常功能磁共振研究[J];第三軍醫(yī)大學(xué)學(xué)報(bào);2013年24期

4 蔣偉雄;劉華生;廖堅(jiān);廖云杰;唐艷;王維;;多變量模式分析在反社會(huì)人格障礙中的應(yīng)用[J];電子科技大學(xué)學(xué)報(bào);2014年02期

5 魏煥能;朱建坤;王秋蘭;;阿爾茨海默病的診治與護(hù)理進(jìn)展[J];西部中醫(yī)藥;2014年07期

6 任漪清;魏文石;;阿爾茨海默病的診斷進(jìn)展[J];世界臨床藥物;2014年07期

7 楊舒然;程宇琪;許秀峰;;重性抑郁障礙的腦結(jié)構(gòu)影像學(xué)研究進(jìn)展[J];國際精神病學(xué)雜志;2014年03期

8 王文余;錢銘怡;戴廣南;;社交焦慮高、低分者事后反復(fù)回想的信息加工差異[J];北京大學(xué)學(xué)報(bào)(自然科學(xué)版);2014年06期

9 吳磊;吳文;;基于體素的形態(tài)測(cè)量學(xué)在抑郁癥研究中的應(yīng)用[J];廣東醫(yī)學(xué);2014年05期

10 萬婧;王健;尹訓(xùn)濤;糜漫天;;2型糖尿病與癡呆亞型相關(guān)機(jī)制的研究進(jìn)展[J];重慶醫(yī)學(xué);2014年31期

相關(guān)博士學(xué)位論文 前10條

1 廖偉;基于磁共振成像的腦連接方法學(xué)及應(yīng)用研究[D];電子科技大學(xué);2011年

2 丁菊容;基于磁共振成像的腦網(wǎng)絡(luò)技術(shù)及臨床應(yīng)用研究[D];電子科技大學(xué);2012年

3 王美豪;語言功能腦區(qū)與運(yùn)動(dòng)性失語靜息態(tài)功能連接的功能磁共振研究[D];鄭州大學(xué);2013年

4 周廣玉;功能性消化不良患者大腦結(jié)構(gòu)和功能異常研究[D];西安電子科技大學(xué);2013年

5 龍丹;基于多模態(tài)磁共振信息的早期帕金森病影像標(biāo)記及計(jì)算機(jī)輔助診斷研究[D];浙江大學(xué);2012年

6 曾育琦;雷公藤氯內(nèi)酯醇通過改善突觸可塑性、調(diào)節(jié)Aβ代謝、抑制神經(jīng)炎癥反應(yīng)減輕5XFAD轉(zhuǎn)基因小鼠的認(rèn)知損害[D];福建醫(yī)科大學(xué);2013年

7 陳俊;重性精神障礙谷氨酸能系統(tǒng)相關(guān)基因的分子遺傳學(xué)及功能影像學(xué)研究[D];北京協(xié)和醫(yī)學(xué)院;2012年

8 楊海晨;心境障礙患者輕躁狂癥狀的臨床與靜息態(tài)腦功能磁共振研究[D];中南大學(xué);2013年

9 張琳;神經(jīng)退行性疾病病理及潛在治療藥物研究[D];中南大學(xué);2013年

10 宋承遠(yuǎn);α-synuclein A53T轉(zhuǎn)基因帕金森小鼠模型DNA甲基化研究[D];中南大學(xué);2013年

相關(guān)碩士學(xué)位論文 前10條

1 賴昀;基于彌散張量成像的腦白質(zhì)纖維追蹤算法研究[D];蘇州大學(xué);2013年

2 方林;首發(fā)偏執(zhí)型精神分裂癥患者靜息態(tài)腦功能fMRI研究[D];南京醫(yī)科大學(xué);2013年

3 劉光耀;原發(fā)全面強(qiáng)直陣攣癲癇全腦比率低頻振幅的靜息態(tài)fMRI研究[D];蘭州大學(xué);2013年

4 吳曉寧;基于阿爾茨海默病的大腦皮層厚度網(wǎng)絡(luò)的研究[D];蘭州大學(xué);2013年

5 王亞丹;HPLC用于Aβ雙水相富集檢測(cè)及解聚藥物的篩選[D];鄭州大學(xué);2013年

6 任璐;偏頭痛患者的靜息態(tài)功能磁共振研究[D];河北醫(yī)科大學(xué);2013年

7 郭曉光;EGCG對(duì)阿爾茨海默病模型大鼠海馬c-Abl/p73信號(hào)通路的影響[D];河北醫(yī)科大學(xué);2013年

8 羅曉莉;銀杏葉提取物對(duì)東莨菪堿致小鼠學(xué)習(xí)記憶障礙的作用[D];廣西師范大學(xué);2013年

9 程青格;反式白藜蘆醇對(duì)Aβ_(25-35)誘導(dǎo)阿爾茨海默病大鼠海馬神經(jīng)元的保護(hù)作用[D];遵義醫(yī)學(xué)院;2013年

10 李莉;Presenilins條件性雙基因敲除小鼠超微結(jié)構(gòu)的增齡性變化及運(yùn)動(dòng)能力的研究[D];華東師范大學(xué);2013年

，

本文編號(hào)：2117127