本文選題：細(xì)胞運(yùn)動(dòng)分析　切入點(diǎn)：多模式　出處：《南京理工大學(xué)》2016年博士論文

【摘要】：生物醫(yī)學(xué)圖像在醫(yī)療診斷和疾病治療中的作用日益顯著,細(xì)胞圖像的研究是醫(yī)學(xué)圖像中一個(gè)重要的分支。從細(xì)胞圖像序列中提取細(xì)胞的特征信息及運(yùn)動(dòng)軌跡,是醫(yī)學(xué)分析中一項(xiàng)重要的基本工作。近年來,盡管相關(guān)領(lǐng)域的研究者取得了很多有益的成果,但因信息量大,細(xì)胞的形狀復(fù)雜且易變,細(xì)胞運(yùn)動(dòng)的隨機(jī)性以及受到獲取技術(shù)、圖像質(zhì)量等因素的影響,要準(zhǔn)確計(jì)量細(xì)胞數(shù)目及獲取其運(yùn)動(dòng)軌跡,仍然存在許多理論與技術(shù)上的難點(diǎn)。針對以上問題,本論文從分析多細(xì)胞存在的不同運(yùn)動(dòng)模式著手,充分利用時(shí)空信息,提出了若干種具有一定工程應(yīng)用前景的隨機(jī)性多細(xì)胞運(yùn)動(dòng)分析方法,改進(jìn)了檢測與跟蹤的準(zhǔn)確率。論文的主要研究內(nèi)容如下:1.針對所研究圖像序列中多細(xì)胞粘連問題,給出了一種基于閾值的混合細(xì)胞檢測算法,仿真結(jié)果表明,基于該圖像序列的查全率(Recall)和準(zhǔn)確率(Precision)可達(dá)98.32%和97.03%左右。針對密集情形下出現(xiàn)的多細(xì)胞重疊問題,給出了一種改進(jìn)分水嶺混合檢測算法,仿真結(jié)果表明,該方法可以很好地將重疊細(xì)胞分割為單個(gè)細(xì)胞,且?guī)缀醪粫?huì)出現(xiàn)細(xì)胞區(qū)域標(biāo)定不正確或者區(qū)域分割不完整的現(xiàn)象,基于該圖像序列的準(zhǔn)確率可達(dá)到96%。2.針對多細(xì)胞跟蹤中存在的目標(biāo)分裂、碰撞等引起的狀態(tài)耦合問題,給出了一種擴(kuò)展多模型粒子濾波多細(xì)胞運(yùn)動(dòng)分析方法。首先結(jié)合閾值處理和孔洞填充技術(shù)設(shè)計(jì)了細(xì)胞混合檢測方法。其次基于細(xì)胞相互作用存在的三種事件(獨(dú)立、碰撞、分裂),構(gòu)建細(xì)胞運(yùn)動(dòng)模型,并應(yīng)用角速度和面積特征參數(shù)對目標(biāo)狀態(tài)進(jìn)行增廣。最后通過計(jì)算面積和距離特征信息的差異性測量,給出了一種細(xì)胞數(shù)據(jù)關(guān)聯(lián)策略。仿真結(jié)果表明了設(shè)計(jì)方法的有效性。3.針對多細(xì)胞數(shù)目時(shí)變和動(dòng)力學(xué)特性差異等問題,給出了一種基于圖像背景提取的蟻群多細(xì)胞運(yùn)動(dòng)分析方法。利用非參數(shù)核密度估計(jì)方法產(chǎn)生先驗(yàn)蟻群分布,通過多蟻群重構(gòu)建立多峰信息素場,利用蟻群快速聚類算法實(shí)現(xiàn)細(xì)胞身份管理與狀態(tài)提取。仿真結(jié)果表明了設(shè)計(jì)方法的有效性。4.針對低信噪比圖像序列中多細(xì)胞近鄰問題,給出了一種多任務(wù)蟻群近鄰細(xì)胞運(yùn)動(dòng)分析方法。利用近似平均法方法提取細(xì)胞的前景圖像,結(jié)合K均值聚類方法產(chǎn)生初始子蟻群。設(shè)計(jì)了蟻群的協(xié)作與競爭模式,并構(gòu)建多峰信息素場。通過合并相似子蟻群和去除虛假目標(biāo)子蟻群進(jìn)行多細(xì)胞狀態(tài)估計(jì)。仿真結(jié)果表明,該方法與其他跟蹤算法相比具有較高的準(zhǔn)確性。5.針對低信噪比圖像序列中細(xì)胞密度變化問題,給出了一種多模式蟻群變密度細(xì)胞運(yùn)動(dòng)分析方法。利用當(dāng)前幀區(qū)域平均似然度,并結(jié)合前一幀細(xì)胞動(dòng)力學(xué)特性產(chǎn)生蟻群初始分布。基于細(xì)胞的稀疏與密集事件,設(shè)計(jì)蟻群的協(xié)作模式及交互競爭模式。利用蟻群之間的交互信息設(shè)計(jì)了蟻群工作模式實(shí)時(shí)更新策略。仿真結(jié)果表明了設(shè)計(jì)方法的有效性。
[Abstract]:Biomedical images play an increasingly important role in medical diagnosis and disease treatment. The study of cell images is an important branch of medical images.It is an important work in medical analysis to extract the characteristic information and motion track of cells from cell image sequences.In recent years, although researchers in related fields have made a lot of useful achievements, because of the large amount of information, the complex and changeable shape of cells, the randomness of cell movement and the influence of acquisition technology, image quality and so on,There are still many theoretical and technical difficulties to accurately measure the number of cells and obtain their motion trajectories.In order to solve the above problems, this paper begins with the analysis of the different motion patterns of multicellular, makes full use of space-time information, and puts forward several stochastic multicellular motion analysis methods with a certain engineering application prospect.The accuracy of detection and tracking is improved.The main contents of this thesis are as follows: 1.In order to solve the problem of multi-cell adhesion, a threshold based hybrid cell detection algorithm is proposed. The simulation results show that the recall rate and accuracy rate of the image sequence can reach 98.32% and 97.03% respectively.An improved watershed hybrid detection algorithm is proposed to solve the multi-cell overlap problem in dense case. The simulation results show that the proposed method can divide overlapping cells into single cells.And there is almost no phenomenon that cell region calibration is incorrect or region segmentation is incomplete. The accuracy rate based on the image sequence can reach 96.2.Aiming at the state coupling problems caused by target splitting and collision in multi-cell tracking, an extended multi-model particle filter multi-cell motion analysis method is presented.At first, a method of cell mixed detection was designed by combining threshold processing and hole filling technique.Secondly, based on the three events of cell interaction (independence, collision, division), the model of cell motion is constructed, and the target state is augmented by the parameters of angular velocity and area characteristic.Finally, a cell data association strategy is proposed by measuring the difference between the calculated area and the distance characteristic information.The simulation results show that the design method is effective.In order to solve the problem of time-varying number of multi-cell and difference of dynamic characteristics, a multi-cell motion analysis method of ant colony based on image background extraction is presented.The nonparametric kernel density estimation method is used to generate the prior ant colony distribution, the multi-peak pheromone field is established by the multi-ant colony reconstruction, and the cell identity management and state extraction are realized by the ant colony fast clustering algorithm.Simulation results show the effectiveness of the design method.In order to solve the problem of multi-cell nearest neighbor in low signal-to-noise ratio (SNR) image sequence, a multi-task ant colony nearest neighbor cell motion analysis method is presented.The foreground image of cells was extracted by the approximate averaging method and the initial ant colony was generated by K-means clustering method.The cooperation and competition model of ant colony is designed, and the multi-peak pheromone field is constructed.Multi-cell state estimation was carried out by merging similar ant colonies and removing false target ant colonies.Simulation results show that the method has higher accuracy than other tracking algorithms.In order to solve the problem of cell density change in low SNR image sequence, a multi-mode ant colony variable density cell motion analysis method is presented.The initial distribution of ant colony is generated by using the average likelihood degree of the current frame region and the cellular dynamics of the previous frame.Based on the sparse and dense events of cells, the cooperation mode and the interactive competition mode of ant colony are designed.Based on the interaction information between ant colonies, the real-time updating strategy of ant colony working mode is designed.Simulation results show the effectiveness of the design method.
【學(xué)位授予單位】：南京理工大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：R318;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 唐孝威,劉國琴;細(xì)胞運(yùn)動(dòng)的研究[J];世界科技研究與發(fā)展;2000年05期

2 劉專;郭坤琨;;相場動(dòng)力學(xué)模型研究細(xì)胞運(yùn)動(dòng)中的形態(tài)變化[J];化學(xué)學(xué)報(bào);2013年08期

3 楊雪;細(xì)菌尾蛋白揭開細(xì)胞運(yùn)動(dòng)的神秘面紗[J];世界科學(xué);1996年03期

4 ;新書介紹[J];生物化學(xué)與生物物理學(xué)報(bào);1999年03期

5 李丹亞;;闡明體內(nèi)糖密碼的研究[J];國外醫(yī)學(xué)情報(bào);1984年21期

6 周蓉;;一維細(xì)胞運(yùn)動(dòng)的數(shù)值模擬[J];運(yùn)城學(xué)院學(xué)報(bào);2010年05期

7 周蓉;CHOI Y S;;二維細(xì)胞運(yùn)動(dòng)模型的數(shù)值模擬(英文)[J];生物數(shù)學(xué)學(xué)報(bào);2011年02期

8 張杰;李焱;武峗;楊勁;楊珂;郭海英;;Wnt5a信號(hào)途徑與其介導(dǎo)的細(xì)胞運(yùn)動(dòng)研究進(jìn)展[J];生命科學(xué);2013年03期

9 李甲初;劉康達(dá);;腦信號(hào)蛋白與細(xì)胞運(yùn)動(dòng)及腫瘤[J];生命的化學(xué);2007年06期

10 苗龍;;細(xì)胞運(yùn)動(dòng)、細(xì)胞遷移與細(xì)胞骨架研究進(jìn)展[J];生物物理學(xué)報(bào);2007年04期

相關(guān)會(huì)議論文 前2條

1 趙亮;丁彥青;;LASP-1通過對細(xì)胞骨架的調(diào)節(jié)影響腫瘤細(xì)胞運(yùn)動(dòng)能力[A];第九屆全國腫瘤轉(zhuǎn)移學(xué)術(shù)大會(huì)暨2011年黑龍江省醫(yī)學(xué)會(huì)腫瘤學(xué)年會(huì)摘要集[C];2011年

2 陳鋼;周蒙滔;施紅旗;余正平;朱椰凡;俞富祥;;抑制PI3K/Akt信號(hào)傳導(dǎo)對EpHRINA1介導(dǎo)的肝癌細(xì)胞運(yùn)動(dòng)、侵襲能力的影響[A];2008年浙江省外科學(xué)術(shù)年會(huì)論文匯編[C];2008年

相關(guān)重要報(bào)紙文章 前1條

1 記者 吳長鋒 通訊員 楊保國;中美科學(xué)家合作發(fā)現(xiàn)癌細(xì)胞遷移新機(jī)制[N];科技日報(bào);2014年

相關(guān)博士學(xué)位論文 前5條

1 汪世婕;CD147調(diào)控Rac1信號(hào)介導(dǎo)的肝癌細(xì)胞運(yùn)動(dòng)的機(jī)制研究[D];第四軍醫(yī)大學(xué);2015年

2 白嘎麗瑪;大腸桿菌QseB/QseC信號(hào)途徑影響染色體復(fù)制起始和細(xì)胞運(yùn)動(dòng)[D];內(nèi)蒙古大學(xué);2016年

3 崔洪勇;CD147-Annexin A2相互作用調(diào)控腫瘤細(xì)胞運(yùn)動(dòng)的分子機(jī)制研究[D];第四軍醫(yī)大學(xué);2015年

4 魯明麗;多細(xì)胞隨機(jī)性方法運(yùn)動(dòng)分析研究[D];南京理工大學(xué);2016年

5 丁翔;IQGAP1蛋白通過提高細(xì)胞運(yùn)動(dòng)能力促進(jìn)肝細(xì)胞癌侵襲轉(zhuǎn)移[D];中南大學(xué);2006年

相關(guān)碩士學(xué)位論文 前4條

1 王江玲;PYK2與連接蛋白Leupaxin之間的相互關(guān)系以及它們對T細(xì)胞活化和功能作用的研究[D];華中科技大學(xué);2012年

2 崔婷婷;ANXA2敲除對結(jié)腸癌caco2細(xì)胞運(yùn)動(dòng)相關(guān)形態(tài)的研究[D];陜西師范大學(xué);2012年

3 張曉紅;M-CSF在NIH3T3細(xì)胞核內(nèi)的表達(dá)及其對細(xì)胞運(yùn)動(dòng)的影響[D];南華大學(xué);2006年

4 謝楠;ANXA2表達(dá)對caco2細(xì)胞運(yùn)動(dòng)有關(guān)的微形態(tài)和蛋白表達(dá)的調(diào)控的研究[D];陜西師范大學(xué);2012年

，

本文編號(hào)：1722170