本文選題：自閉癥預(yù)測(cè) + 靜息態(tài)功能連接��； 參考：《北京交通大學(xué)》2017年碩士論文

【摘要】：自閉癥(Autism spectrum disorder,ASD)是一種神經(jīng)發(fā)育障礙疾病,發(fā)病率高達(dá)1%,給社會(huì)及患者的家庭帶來了沉重負(fù)擔(dān)。目前主要以行為量表對(duì)ASD進(jìn)行診斷,具有一定的主觀性。靜息態(tài)功能連接(Resting-state functional connectivity,RSFC)反映了大腦在靜息態(tài)下不同腦區(qū)神經(jīng)活動(dòng)模式之間的時(shí)間相關(guān)性,基于RSFC探索能夠識(shí)別ASD的生物標(biāo)記對(duì)于ASD的客觀輔助診斷和理解其神經(jīng)機(jī)制具有重要意義。本文基于RSFC從靜態(tài)和動(dòng)態(tài)兩方面進(jìn)行了 ASD預(yù)測(cè)研究:一是認(rèn)為RSFC在整個(gè)掃描過程中是靜止的,利用Lasso和elastic net兩種方法對(duì)RSFC的特征選擇進(jìn)行了深入研究;二是假設(shè)RSFC是隨時(shí)間動(dòng)態(tài)變化的,基于動(dòng)態(tài)功能連接方法對(duì)ASD預(yù)測(cè)進(jìn)行了初步探索,具體工作內(nèi)容如下:(1)針對(duì)大部分方法不能有效地選出具有識(shí)別力的RSFC,本文提出利用Lasso選擇有識(shí)別力的RSFC。首先計(jì)算Pearson相關(guān)捕捉到大腦的正負(fù)相關(guān)RSFC,然后進(jìn)行閾值化保留同步化程度較高的正相關(guān)RSFC,進(jìn)一步利用嵌入式特征選擇方法Lasso去除冗余的RSFC只保留最有識(shí)別力的特征子集,最后基于SVM分類得到81.52%的分類準(zhǔn)確率,同時(shí)找出了 19個(gè)具有顯著識(shí)別力的RSFC。(2)針對(duì)Lasso方法無法處理具有組效應(yīng)的變量選擇問題,進(jìn)一步提出基于elastic net的多級(jí)特征選擇方法進(jìn)行ASD預(yù)測(cè)研究。本文依次利用閾值化、t檢驗(yàn)和elastic net逐步篩選出差異越來越顯著的RSFC特征子集。t檢驗(yàn)?zāi)艹醪胶Y選出與臨床癥狀顯著相關(guān)的RSFC;Elastic net能發(fā)揮處理組效應(yīng)變量選擇的優(yōu)勢(shì)對(duì)RSFC作進(jìn)一步篩選。最終ASD預(yù)測(cè)的準(zhǔn)確率達(dá)到84.78%,進(jìn)一步提升了預(yù)測(cè)性能,并確定了 22個(gè)有顯著差異的RSFC。(3)針對(duì)大部分研究主要基于靜態(tài)功能連接方法進(jìn)行ASD預(yù)測(cè),而動(dòng)態(tài)功能連接比靜態(tài)蘊(yùn)含的信息更為豐富,本文基于動(dòng)態(tài)功能連接分別提取了高階功能連接特征和動(dòng)態(tài)網(wǎng)絡(luò)拓?fù)涮卣?節(jié)點(diǎn)連接度)進(jìn)行ASD預(yù)測(cè)。高階功能連接能捕獲各腦區(qū)低階功能連接之間的時(shí)間相關(guān)信息,最終得到81.52%的預(yù)測(cè)準(zhǔn)確率;動(dòng)態(tài)網(wǎng)絡(luò)拓?fù)浞椒芴崛⊥負(fù)浣Y(jié)構(gòu)隨時(shí)間的動(dòng)態(tài)變化信息,預(yù)測(cè)性能還不夠理想。在提出的兩種靜態(tài)功能連接方法中,elastic net方法比Lasso獲得了更好的預(yù)測(cè)性能,有助于尋找到與ASD有關(guān)的生物標(biāo)記以輔助醫(yī)生進(jìn)行臨床診斷。高階功能連接方法也獲得了不錯(cuò)的預(yù)測(cè)性能,雖不及靜態(tài)方法,但給我們提供了另一個(gè)思路去尋找生物標(biāo)記,有利于發(fā)現(xiàn)ASD的隱含神經(jīng)機(jī)制。
[Abstract]:Autistic spectrum disorder (ASD) is a neurodevelopmental disorder with a high incidence of 1, which brings a heavy burden to the society and the families of the patients. At present, the diagnosis of ASD is mainly based on behavior scale, which is subjective. Resting state functional connectivity (RSFCs) reflects the temporal correlation of neural activity patterns in different regions of the brain under resting state. Exploring biomarkers that can identify ASD based on RSFC is of great significance for objective diagnosis and understanding of the neural mechanism of ASD. In this paper, the static and dynamic aspects of ASD prediction are studied based on RSFC. First, it is considered that RSFC is stationary in the whole scanning process, and the feature selection of RSFC is studied deeply by using Lasso and elastic net methods. On the other hand, assuming that RSFC changes dynamically with time, the prediction of ASD is preliminarily explored based on dynamic functional connection method. The main work of this paper is as follows: (1) aiming at the fact that most of the methods can not effectively select the RSFCs with recognition power, this paper proposes to use Lasso to select the discriminative RSFCs. Firstly, Pearson correlation was calculated to capture positive and negative correlation RSFCs in the brain, then threshold retention synchronization of positive correlation RSFCs was performed. Further, the embedded feature selection method Lasso was used to remove redundant RSFC, which only retained the most recognizable subset of features. Finally, 81.52% of the classification accuracy is obtained based on SVM classification. At the same time, 19 RSFC.2s with significant recognition power are found. For Lasso method, it can not deal with variable selection problem with group effect. Furthermore, a multilevel feature selection method based on elastic net is proposed. In this paper, we use the threshold t test and elastic net step by step to screen out the characteristic subset. T test, which is more and more significant. The result shows that RSFCU Elastic net, which is significantly related to clinical symptoms, can play an important role in the selection of effect variables of the treatment group. RSFC was further screened. Finally, the accuracy rate of ASD prediction reaches 84.78, which further improves the prediction performance, and determines 22 RSFC.K3, which have significant differences. In view of the majority of researches, ASD prediction is mainly based on static functional connection method. The dynamic functional connection is more abundant than the static information. Based on the dynamic functional connection, the high-order functional connection feature and the dynamic network topology feature (node connectivity degree) are extracted to predict the ASD. High-order functional connections can capture the time-dependent information among the low-order functional connections in various brain regions, and finally obtain 81.52% prediction accuracy. The dynamic network topology method can extract the dynamic changes of topology structure with time, and the prediction performance is not good enough. In the two static functional connection methods proposed, the modified net method has better predictive performance than Lasso, which is helpful to find the biomarkers associated with ASD-related biomarkers to assist doctors in clinical diagnosis. High-order functional join method also has good predictive performance. Although it is not as good as static method, it provides us with another way to find biomarkers, which is helpful to discover the implicit neural mechanism of ASD.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：R445.2;R749.94

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 陳順森;白學(xué)軍;張日f;;自閉癥譜系障礙的癥狀、診斷與干預(yù)[J];心理科學(xué)進(jìn)展;2011年01期

，

本文編號(hào)：2012982