本文選題：雙光子鈣成像 + 細(xì)胞識(shí)別與分割　； 參考：《西南大學(xué)》2017年碩士論文

【摘要】：神經(jīng)科學(xué)是一門重點(diǎn)研究腦科學(xué)的綜合性學(xué)科。在最近20年期間,神經(jīng)科學(xué)經(jīng)歷著飛速的發(fā)展,對(duì)類腦人工智能的進(jìn)步及各種神經(jīng)及精神類疾病的治療有著非常重大的意義。其中計(jì)算機(jī)技術(shù)對(duì)于推動(dòng)神經(jīng)科學(xué)的發(fā)展起著不可替代的作用。隨著神經(jīng)活動(dòng)記錄技術(shù)的發(fā)展與新的紀(jì)錄方法的出現(xiàn),腦科學(xué)數(shù)據(jù)的分析成為一重大難題,急需借助計(jì)算機(jī)自動(dòng)化分析技術(shù)來(lái)取代手工分析,提高分析的效率與精度。在過(guò)去的10年中,雙光子鈣成像技術(shù)已經(jīng)被廣泛地應(yīng)用于神經(jīng)元群的功能活動(dòng)成像,并且可以很容易地與細(xì)胞類型特異標(biāo)記物結(jié)合用于分析特定類型神經(jīng)元環(huán)路的功能。為了達(dá)到這一目標(biāo),就需要在單細(xì)胞水平上進(jìn)行神經(jīng)活動(dòng)的分析。然而,人工方式進(jìn)行細(xì)胞的識(shí)別費(fèi)時(shí)并且標(biāo)準(zhǔn)很難統(tǒng)一。因此,通過(guò)計(jì)算機(jī)技術(shù)來(lái)自動(dòng)地、精確地快速識(shí)別單個(gè)神經(jīng)細(xì)胞的位置和輪廓具有重要價(jià)值。在此基礎(chǔ)上,通過(guò)提取單個(gè)神經(jīng)細(xì)胞熒光強(qiáng)度變化來(lái)分析動(dòng)作電位相關(guān)的活動(dòng),以此和行為學(xué)變量聯(lián)合可解析大腦特定皮層區(qū)域的工作機(jī)制�？梢�(jiàn),神經(jīng)細(xì)胞的識(shí)別分割和單個(gè)細(xì)胞鈣信號(hào)事件的探測(cè)是光學(xué)腦功能成像數(shù)據(jù)分析工作中的基礎(chǔ)并具有至關(guān)重要的作用。故本文研究工作主要分為兩個(gè)部分:(1)提出一種新的細(xì)胞識(shí)別與分割方法。該方法主要分為3個(gè)步驟:(a)對(duì)鈣成像數(shù)據(jù)的細(xì)胞圖像,利用多尺度拉普拉斯高斯濾波(Multi_LoG)定位局部極值從而實(shí)現(xiàn)對(duì)細(xì)胞的種子點(diǎn)(中心點(diǎn))的初步探測(cè);(b)利用卷積神經(jīng)網(wǎng)絡(luò)(CNN)算法進(jìn)行細(xì)胞的進(jìn)一步判別,降低探測(cè)結(jié)果的假陽(yáng)性;(c)利用TWANG算法對(duì)細(xì)胞進(jìn)行邊緣檢測(cè),該算法的優(yōu)點(diǎn)是具有精確分割能力的同時(shí)計(jì)算復(fù)雜度低,從而可以進(jìn)行細(xì)胞邊緣的快速分割。本文將此方法應(yīng)用于開源細(xì)胞圖像(benchmark)和來(lái)自第三軍醫(yī)大學(xué)腦研究中心的雙光子鈣成像細(xì)胞圖像,并與一些已發(fā)表論文中的細(xì)胞識(shí)別分割算法比較。(2)對(duì)于鈣成像數(shù)據(jù)的熒光亮度變化曲線,提出一種新的鈣事件探測(cè)方法。首先通過(guò)分析建立反應(yīng)動(dòng)作電位活動(dòng)的鈣事件的相關(guān)特征參數(shù),利用一個(gè)滑動(dòng)的基線窗獲得噪聲水平的估計(jì)值。然后再提取基線相鄰的探測(cè)窗口數(shù)據(jù)中鈣事件的特征信息,并且與多項(xiàng)特征參數(shù)進(jìn)行匹配以判斷該該事件活動(dòng)是否滿足鈣事件的特征條件。在成功判斷的基礎(chǔ)上,進(jìn)一步提取鈣事件的初始點(diǎn),峰值點(diǎn)和結(jié)束點(diǎn)的位置信息。最后在鈣事件數(shù)據(jù)中,將已成功探測(cè)的鈣事件的噪聲水平進(jìn)行再次估計(jì)用作下一步的探測(cè)。以此完成一個(gè)鈣事件的探測(cè)過(guò)程,并通過(guò)這種方式循環(huán)直至整個(gè)鈣成像熒光數(shù)據(jù)的事件探測(cè)完成。本文將此方法應(yīng)用于仿真鈣事件數(shù)據(jù)和來(lái)自第三軍醫(yī)大學(xué)腦研究中心的雙光子鈣成像熒光亮度曲線,并與現(xiàn)已發(fā)表論文中的一些鈣事件探測(cè)算法比較�；谝陨瞎ぷ�,對(duì)本文分析方法進(jìn)行評(píng)估的方案主要是比較這些方法所得到結(jié)果的召回率(Recall),精確率(Precision)和F分?jǐn)?shù)(F-score)這三個(gè)參數(shù)的值。通過(guò)應(yīng)用于開源和仿真數(shù)據(jù),證明本文方法的有效性和正確性;通過(guò)應(yīng)用于真實(shí)數(shù)據(jù),證明本文方法的實(shí)用性和可行性。借助對(duì)上述多項(xiàng)數(shù)據(jù)的應(yīng)用,將對(duì)比方法與本文提出方法產(chǎn)生結(jié)果的平均值進(jìn)行比較并對(duì)其進(jìn)行顯著性差異分析,證明本文方法可在自動(dòng)化的分析過(guò)程中獲得更精確的神經(jīng)細(xì)胞的識(shí)別分割效果和提高其對(duì)應(yīng)的鈣事件探測(cè)精度,這對(duì)于將來(lái)大規(guī)模應(yīng)用在雙光子成像數(shù)據(jù)分析中具有重要作用。
[Abstract]:Neuroscience is a comprehensive subject which focuses on the research of brain science. During the last 20 years, neuroscience has developed rapidly. It has great significance for the progress of brain artificial intelligence and the treatment of various neurologic and mental diseases. With the development of neural activity recording technology and the emergence of new record methods, the analysis of brain science data has become a major problem. It is urgent to replace manual analysis with computer automation analysis technology to improve the efficiency and accuracy of analysis. In the past 10 years, the two-photon calcium imaging technology has been widely used in the group of neurons. Functional activity imaging, and can easily be combined with cell type specific markers to analyze the function of a specific type of neuron loop. In order to achieve this goal, the analysis of neural activity is needed at a single cell level. However, the artificial way of cell recognition is time-consuming and the standard is difficult to unify. Therefore, through Computer technology is of great value to automatically, accurately and quickly identify the location and contour of a single nerve cell. On this basis, the action potential related activities are analyzed by extracting the changes of the fluorescence intensity of a single nerve cell, which can be combined with the behavioral variables to analyze the working mechanism of the specific cortical regions of the brain. The recognition and segmentation of cells and the detection of single cell calcium signal events are the basic and important role in the analysis of optical brain functional imaging data. Therefore, the main research work of this paper is divided into two parts: (1) a new method of cell recognition and segmentation is proposed. This method is divided into 3 steps: (a) fine calcium imaging data Cell image, using the multi-scale Laplasse Gauss filter (Multi_LoG) to locate the local extremum to realize the preliminary detection of the seed point (center point) of the cell; (b) use the convolution neural network (CNN) algorithm to further distinguish the cells and reduce the false positive of the detection results; (c) the edge detection of the cells by the TWANG algorithm, the algorithm This method is applied to open source cell image (benchmark) and the image of two-photon calcium imaging cells from the Third Military Medical University brain research center in this paper, and is compared with the cell recognition and segmentation algorithms in some published papers. (2) a new method of calcium event detection is proposed for the luminance change curve of the calcium imaging data. First, by analyzing the related characteristic parameters of the calcium event of the action potential activity, a sliding baseline window is used to obtain the estimated value of the noise level, and then the calcium event in the detection window data adjacent to the baseline is extracted. The feature information is matched with multiple characteristic parameters to determine whether the event activity meets the characteristics of the calcium event. On the basis of the successful judgment, the initial point, the peak point and the end point of the calcium event are further extracted. Finally, the noise level of the calcium event has been successfully detected in the calcium event data. This method is used to simulate calcium event data and two photon calcium imaging luminance curves from the heart of the Third Military Medical University, and the method is applied to the simulation of calcium event data and the luminance curve of the two photon calcium imaging from the heart of the Third Military Medical University. Compared with some of the calcium event detection algorithms in the published papers, based on the above work, the main evaluation of this method is to compare the recall rate (Recall) of the results obtained by these methods, the value of the three parameters of the accuracy rate (Precision) and the F fraction (F-score). The validity and correctness of the method are proved, and the practicability and feasibility of this method are proved by application of the real data. With the use of the above data, the comparison method is compared with the average value produced by the method presented in this paper, and the significant difference analysis is carried out. It is proved that this method can be obtained in the automated analysis process. The recognition and segmentation of more accurate neural cells and the improvement of its corresponding detection precision of calcium events are important for large-scale application in the future analysis of two-photon imaging data.

【學(xué)位授予單位】：西南大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：R318;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 劉雙雙;黃繼云;肖桂鳳;尹偉;林趙肖楠;盧應(yīng)梅;;雙光子顯微鏡檢測(cè)活體小鼠腦內(nèi)微循環(huán)技術(shù)的建立[J];中國(guó)應(yīng)用生理學(xué)雜志;2015年03期

2 張靜思;孫長(zhǎng)凱;樸花;;雙光子顯微鏡技術(shù)在腦功能研究中的應(yīng)用:腦片、整體腦結(jié)構(gòu)樣品和活體腦[J];大連醫(yī)科大學(xué)學(xué)報(bào);2010年05期

3 史娟;李繼碩;;細(xì)胞內(nèi)鈣成像和鈣測(cè)定的基本原理及應(yīng)用[J];神經(jīng)解剖學(xué)雜志;2006年04期

4 李小紅;基于LOG濾波器的圖像邊緣檢測(cè)算法的研究[J];計(jì)算機(jī)應(yīng)用與軟件;2005年05期

5 姜寶法;《Logistic回歸模型—方法與應(yīng)用》[J];預(yù)防醫(yī)學(xué)文獻(xiàn)信息;2002年05期

6 馬義德,戴若蘭,李廉,吳承虎;生物細(xì)胞圖像分割技術(shù)的進(jìn)展[J];生物醫(yī)學(xué)工程學(xué)雜志;2002年03期

7 劉守忠;陸惠民;顏坤;寧紅;;共聚焦激光掃描顯微鏡系統(tǒng)及其在生物學(xué)研究中的應(yīng)用[J];電子顯微學(xué)報(bào);1993年04期

相關(guān)碩士學(xué)位論文 前2條

1 葉浪;基于卷積神經(jīng)網(wǎng)絡(luò)的人臉識(shí)別研究[D];東南大學(xué);2015年

2 靳艷紅;基于改進(jìn)canny算法的圖像邊緣檢測(cè)的研究[D];重慶師范大學(xué);2011年

，

本文編號(hào)：1855540