本文選題：圖像預(yù)處理　切入點(diǎn)：偽影去除　出處：《華中科技大學(xué)》2013年碩士論文

【摘要】：如何準(zhǔn)確認(rèn)識(shí)腦是現(xiàn)代科學(xué)研究中一個(gè)巨大的挑戰(zhàn)，其中神經(jīng)結(jié)構(gòu)是腦功能與疾病發(fā)病機(jī)制研究的重要基礎(chǔ)。隨著顯微成像技術(shù)的發(fā)展，特別是大范圍、高分辨光學(xué)顯微成像技術(shù)的出現(xiàn)，不斷獲取的海量復(fù)雜神經(jīng)解剖結(jié)構(gòu)的圖像數(shù)據(jù)集為腦科學(xué)研究提供了有力的工具。面對(duì)全腦高分辨成像帶來(lái)的海量復(fù)雜數(shù)據(jù)，全自動(dòng)的圖像處理方法成為了知識(shí)挖掘的必要方法和工具。然而，由于樣本制備和成像過(guò)程產(chǎn)生的多種偽影會(huì)使圖像質(zhì)量下降，因此對(duì)海量復(fù)雜神經(jīng)解剖圖像處理方法提出了新的需求。 基于顯微光學(xué)切片斷層成像系統(tǒng)所獲取的數(shù)據(jù)量達(dá)5TB的尼氏染色和8TB的高爾基染色小鼠全腦結(jié)構(gòu)數(shù)據(jù)集，針對(duì)原始切片圖像存在的多種偽影，本文提出了一套用于組織染色顯微光學(xué)圖像的全自動(dòng)偽影去除方法，實(shí)現(xiàn)了對(duì)包含細(xì)胞、血管等結(jié)構(gòu)復(fù)雜圖集的校正。本文對(duì)偽影的去除包括以下幾個(gè)方面：（1）使用移動(dòng)中值濾波的方法對(duì)圖像的均值投影曲線進(jìn)行平滑，，并使用計(jì)算得到的校正系數(shù)去除圖像中的條紋噪聲；（2）使用腦輪廓做掩膜提高非均勻背景提取的準(zhǔn)確性，將原圖與非均勻背景相減校正染色不均勻?qū)е碌膱D像亮度不均勻；（3）使用形態(tài)學(xué)濾波的方法對(duì)圖像中存在的不規(guī)則亮斑進(jìn)行去除；（4）使用分割后腦內(nèi)包埋劑的均值為參考，將各個(gè)斷層統(tǒng)一到相同亮度。 尼氏染色和高爾基染色小鼠全腦數(shù)據(jù)集經(jīng)過(guò)本文方法處理后，全腦各區(qū)域亮度均勻，圖像質(zhì)量較處理前有明顯的提升，校正后的圖像能夠清晰的展示細(xì)胞構(gòu)筑、血管拓?fù)浜蜕窠?jīng)細(xì)胞形態(tài)。亮度均勻的高質(zhì)量全腦圖集可以結(jié)合胞體分割、血管追蹤和細(xì)胞形態(tài)檢測(cè)等方法，用于胞體、血管以及神經(jīng)細(xì)胞類(lèi)型的定量計(jì)算和分析，為神經(jīng)科學(xué)家進(jìn)一步揭示腦工作機(jī)理提供可靠的基礎(chǔ)數(shù)據(jù)集。
[Abstract]:How to accurately understand the brain is a great challenge in modern scientific research, in which the neural structure is an important basis for the study of brain function and the pathogenesis of disease. With the development of microscopic imaging technology, especially in a wide range, With the emergence of high-resolution optical microscopic imaging technology, a large number of image data sets of complex neuroanatomical structures have been continuously acquired, which provides a powerful tool for the research of brain science. In the face of the massive complex data brought by high-resolution imaging of the whole brain, Fully automatic image processing has become a necessary method and tool for knowledge mining. However, because of the variety of artifacts produced in the process of sample preparation and imaging, the image quality is degraded. Therefore, a new demand is put forward for massive complex nerve anatomical image processing. Based on the whole brain structure data set of mice with 5TB and 8TB Golgi staining obtained by the microoptical slice tomography system, a variety of artifacts existed in the original slice images were studied. In this paper, a set of automatic artifact removal methods for tissue staining microscopic optical images is proposed. In this paper, the removal of artifacts includes the following aspects: 1) smoothing the mean projection curve of the image by moving median filter. Using the calculated correction coefficient to remove the fringe noise in the image, the brain contour is used as the mask to improve the accuracy of the non-uniform background extraction. Subtractive correction of the original image with non-uniform background to correct the uneven brightness of the image caused by non-uniform coloring) removal of irregular bright spots in the image by morphological filtering method) use the mean value of the embedded agent in the brain after segmentation as a reference. Unify the faults to the same brightness. After the whole brain data sets of Nieldahl staining and Golgi staining mice were processed by this method, the brightness of all regions of the whole brain was uniform, the image quality was obviously improved compared with that before processing, and the corrected images could clearly show the cellular architecture. High quality global brain atlas with uniform brightness can be combined with cell body segmentation, vascular tracing and cell morphology detection for quantitative calculation and analysis of cell body, blood vessel and nerve cell types. It provides a reliable basic data set for neuroscientists to further reveal the mechanism of brain work.
【學(xué)位授予單位】：華中科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類(lèi)號(hào)】：R310

【共引文獻(xiàn)】

相關(guān)期刊論文 前2條

1 程廣斌;郝立巍;陳武凡;;利用Gibbs距離圖Snake模型分割醫(yī)學(xué)圖像[J];南方醫(yī)科大學(xué)學(xué)報(bào);2008年01期

2 郝立巍;陳武凡;;骨自動(dòng)分割及基于輪廓一致性的分割驗(yàn)證[J];光學(xué)技術(shù);2007年04期

相關(guān)博士學(xué)位論文 前3條

1 郝立巍;醫(yī)學(xué)高維數(shù)據(jù)的臨床環(huán)境實(shí)時(shí)計(jì)算研究[D];第一軍醫(yī)大學(xué);2007年

2 程廣斌;應(yīng)用于數(shù)字化診斷的若干醫(yī)學(xué)圖像分析方法研究[D];南方醫(yī)科大學(xué);2008年

3 王青蒂;適用于大樣本高分辨率三維成像的樹(shù)脂塊連續(xù)薄切片研究[D];華中科技大學(xué);2013年

相關(guān)碩士學(xué)位論文 前1條

1 曹勇;基于同步輻射顯微斷層成像技術(shù)的大鼠脊髓微血管三維形態(tài)學(xué)研究[D];中南大學(xué);2013年

本文編號(hào)：1675492