本文選題：手術(shù)導(dǎo)航　切入點(diǎn)：腫瘤圖像　出處：《北京工業(yè)大學(xué)》2016年博士論文　論文類(lèi)型：學(xué)位論文

【摘要】：計(jì)算機(jī)輔助手術(shù)(Computer Aid/Assisted Surgery,CAS)是依靠圖像引導(dǎo)的介入性手術(shù),是醫(yī)學(xué)研究領(lǐng)域目前的熱點(diǎn)之一。它通過(guò)術(shù)前手術(shù)規(guī)劃,術(shù)中配準(zhǔn)對(duì)手術(shù)進(jìn)行引導(dǎo),術(shù)后評(píng)估等一系列過(guò)程,對(duì)病灶進(jìn)行定位、診斷,引導(dǎo)醫(yī)生對(duì)病灶進(jìn)行相關(guān)的專(zhuān)業(yè)處理,解決常規(guī)手術(shù)中難定位的問(wèn)題,同時(shí)減少手術(shù)并發(fā)癥。在腫瘤手術(shù)中,由于腫瘤附著器官的復(fù)雜結(jié)構(gòu)如腦腫瘤周?chē)苌窠?jīng)密布,以及腫瘤組織本身的浸潤(rùn)性,使得臨床對(duì)高精度的計(jì)算機(jī)輔助腫瘤手術(shù)有著迫切的需求。本文針對(duì)腫瘤手術(shù)導(dǎo)航中的關(guān)鍵問(wèn)題——手術(shù)引導(dǎo)的精確度進(jìn)行研究,針對(duì)術(shù)前腫瘤病灶定位診斷及術(shù)中配準(zhǔn)這兩大影響手術(shù)精確度的主要因素均提出了新的解決方案。目的是為臨床醫(yī)生完成高精度的腫瘤外科手術(shù)提供新的契機(jī),確保手術(shù)安全,減少病人痛苦,并在最短時(shí)間內(nèi)到達(dá)靶點(diǎn)病灶完成手術(shù)。本論文主要研究?jī)?nèi)容與成果如下:腫瘤自動(dòng)分割與診斷算法研究腫瘤的精確自動(dòng)分割及早期診斷,可以提供靶區(qū)病灶位置,規(guī)避重要器官及血管神經(jīng),輔助術(shù)前手術(shù)規(guī)劃,解決傳統(tǒng)手工勾勒費(fèi)時(shí)及精確度低的問(wèn)題。然而長(zhǎng)期以來(lái),由于問(wèn)題的復(fù)雜性,腫瘤分割一直存在精度低及誤診斷的問(wèn)題,而手工勾勒費(fèi)時(shí),對(duì)勾勒者專(zhuān)業(yè)要求高且缺乏自動(dòng)性。針對(duì)上述問(wèn)題,本文提出了新的方法:1.從綜合多種模式腫瘤圖像的角度出發(fā),提出一種基于傳統(tǒng)卷積神經(jīng)網(wǎng)絡(luò)(Convolutional Neural Networks,CNNs)的腦腫瘤自動(dòng)分割與診斷算法。該算法針對(duì)傳統(tǒng)腦腫瘤分割算法使用單一圖像模式及分割精度低的問(wèn)題,設(shè)計(jì)了新的CNNs架構(gòu)模型。該模型可以自動(dòng)學(xué)習(xí)多模態(tài)圖像中的有用特征,綜合利用多模態(tài)圖像的信息。實(shí)驗(yàn)結(jié)果表明,本文所提出方法的分割與診斷精確度優(yōu)于傳統(tǒng)算法,可為醫(yī)生的臨床診斷及術(shù)前手術(shù)規(guī)劃提供可靠信息。2.在傳統(tǒng)CNNs基礎(chǔ)上,提出多通道CNNs算法。首先,該算法摒棄了傳統(tǒng)機(jī)器學(xué)習(xí)類(lèi)算法手動(dòng)設(shè)計(jì)特征的特征提取方式,采用自學(xué)習(xí)的方法提取多模態(tài)圖像的明顯特征。其次,由于腫瘤組織邊界的浸潤(rùn)性及低對(duì)比性,該算法克服了傳統(tǒng)CNNs方法僅利用圖像邊界即局部信息的弊端,綜合利用腫瘤圖像的全局及局部信息。實(shí)驗(yàn)結(jié)果表明,該算法分割與診斷的精確度優(yōu)于目前最流行的腫瘤分割算法,也優(yōu)于傳統(tǒng)的CNNs算法。腫瘤圖像配準(zhǔn)算法研究術(shù)中實(shí)時(shí)采集的醫(yī)學(xué)圖像與術(shù)前手術(shù)規(guī)劃圖像之間的配準(zhǔn),是影響手術(shù)導(dǎo)航的關(guān)鍵指標(biāo)。而腫瘤的易變形、持續(xù)生長(zhǎng)等特征,對(duì)術(shù)中配準(zhǔn)提出了新的挑戰(zhàn)。本文提出了一種用于存在大變形情況的配準(zhǔn)框架,解決了傳統(tǒng)方法在此情況下失效的弊端。同時(shí)改進(jìn)傳統(tǒng)的相似性測(cè)度,在保證配準(zhǔn)精度的前提下,提高算法的收斂速度。1.提出一種深度迭代配準(zhǔn)框架及基于CNNs分類(lèi)器的初始預(yù)配準(zhǔn)算法。針對(duì)傳統(tǒng)配準(zhǔn)框架,僅調(diào)用一次初始預(yù)配準(zhǔn),固定次數(shù)非剛性配準(zhǔn)的弊端,提出深度迭代配準(zhǔn)框架。即在后續(xù)每次非剛性配準(zhǔn)迭代中,再次調(diào)用初始預(yù)配準(zhǔn),以充分利用兩次配準(zhǔn)達(dá)到提高配準(zhǔn)精度的目的。針對(duì)傳統(tǒng)初始預(yù)配準(zhǔn)方法無(wú)法處理存在大變形的情況,本論文提出分別求解初始預(yù)配準(zhǔn)仿射變換中的旋轉(zhuǎn)、平移、尺度參數(shù)。其中旋轉(zhuǎn)參數(shù),首先離線(xiàn)訓(xùn)練CNNs分類(lèi)器,使其能識(shí)別多達(dá)360類(lèi)旋轉(zhuǎn)角度;尺度參數(shù),使用圖像大小信息將固定及移動(dòng)圖像尺寸達(dá)到一致;平移參數(shù),首先通過(guò)統(tǒng)計(jì)學(xué)方法計(jì)算每張圖像的形心,通過(guò)形心位置信息使兩張圖像達(dá)到一致。實(shí)驗(yàn)結(jié)果證明,本文方法能夠替代傳統(tǒng)框架處理存在大的變形下的配準(zhǔn)問(wèn)題。2.提出一種高效的相似性測(cè)度算法。主成分分析(Principle Component Analysis,PCA)用來(lái)提取配準(zhǔn)中固定以及移動(dòng)圖像最主要的特征點(diǎn),避免由額外噪聲帶來(lái)的誤差。將PCA與傳統(tǒng)相似性測(cè)度諸如Spearman及Pearson等相關(guān)系數(shù)相結(jié)合組成新的相似性測(cè)度。實(shí)驗(yàn)結(jié)果證明該算法能夠在保證配準(zhǔn)精度的同時(shí)進(jìn)一步提高算法的收斂速度。
[Abstract]:Computer assisted surgery (Computer Aid/Assisted, Surgery, CAS) by interventional image-guided surgery, is one of the current hot spots in the field of medical research. It is through the preoperative planning, intraoperative registration of surgical guidance, evaluation and a series of process after operation, location of lesions, diagnosis, treatment of the lesions to guide doctors the relevant professional, solve the routine operation difficult to locate the problem at the same time, reduce the postoperative complications. In tumor operation, due to the complex structure of the tumor attachment organs such as brain tumor blood vessels around the nerve and tumor tissue with infiltration of itself, making the clinical on the high precision of computer aided surgery have urgent needs in this paper. Aiming at the key problems in navigation surgery - surgical guidance accuracy study for the preoperative diagnosis and intraoperative tumor lesion location registration of the two operation The main factors are the accuracy of the new solution is put forward. The purpose is to provide a new opportunity for clinicians to complete tumor surgery with high precision, to ensure the safety of the operation, reduce the pain of patients, and in the shortest time to reach the target point of focus to complete the operation. The main research contents and results are as follows: automatic segmentation of tumor and diagnosis the precise automatic segmentation algorithm of tumor and early diagnosis, can provide the target location, avoid the important organs and blood vessels and nerves, assist in surgery planning, to solve the traditional problems of low accuracy and time-consuming hand sketched. However, due to the complexity of the problem, there has been a tumor segmentation accuracy is low and the problem of false diagnosis, and a hand sketched outline of their time-consuming, high professional requirements and lack of initiative. Aiming at the above problems, this paper puts forward a new method: 1. from the mixed pattern of tumor image angle Of a traditional convolution based on neural network (Convolutional Neural Networks, CNNs) automatic segmentation of brain tumors and the diagnosis algorithm. The algorithm for brain tumor segmentation of traditional single image segmentation model and the low accuracy of the algorithm, design a new CNNs frame model. The model can automatically learn the useful features of multimodal in the image, the comprehensive utilization of multi modality image information. The experimental results show that the proposed segmentation algorithm is superior to the traditional method and the diagnostic accuracy of the surgical planning, to provide reliable information for clinical diagnosis and surgery for.2. before the doctor on the basis of traditional CNNs, the multichannel CNNs algorithm. Firstly, the algorithm discards the traditional feature machine learning algorithm design manual feature extraction method, the extraction characteristic of multi modality images by using the method of self-learning. Secondly, due to the infiltration of tumor tissue boundary circle And low contrast, the algorithm overcomes the disadvantages of traditional CNNs method only uses the image boundary disadvantages of local information, comprehensive utilization of global and local tumor image information. The experimental results show that the segmentation and the diagnostic accuracy of the algorithm is superior to the most popular tumor segmentation algorithm is better than the traditional CNNs algorithm. The registration between surgical planning the image of the medical image and the real-time image registration algorithm of tumor surgery in the study before, is the key index of surgical navigation. While tumor deformation, sustained growth characteristics, put forward a new challenge on intraoperative registration. This paper proposes a framework for the registration of large deformation situation, solve the traditional method of failure problems. At the same time improved the traditional similarity measure, under the premise of ensuring the accuracy of registration, improve the speed of convergence of the algorithm.1. proposed an iterative depth registration box Frame and initial registration algorithm based on CNNs classifier. The traditional registration framework, called only once the initial pre registration, the number of drawbacks of fixed non rigid registration, advanced iterative registration framework. In each subsequent iteration in the non rigid registration, call the initial registration, in order to make full use of the two to improve the accuracy of registration registration the purpose of the initial registration. The traditional methods cannot deal with the existence of large deformation, this paper respectively solve the initial pre registration of affine transformation, rotation, translation and scale parameters. The rotation parameters from the first line to train the CNNs classifier, which can identify up to 360 kinds of rotation angle; scale parameter, fixed and mobile the size of the image to use image size information; the translation parameters, first through statistical methods to calculate the image centroid, through the centroid of the two image information to achieve Consistent. Experimental results show that this method can replace the traditional.2. registration framework for dealing with large deformation under an efficient similarity measure algorithm. Principal component analysis (Principle Component, Analysis, PCA) is used to extract the feature points and the main fixed mobile image registration, to avoid the error caused by the extra noise. The combination of new similarity measure PCA with traditional similarity measures such as Spearman and Pearson correlation coefficient. The experimental results show that the algorithm can guarantee the accuracy of registration and further improve the convergence speed of the algorithm.

【學(xué)位授予單位】：北京工業(yè)大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類(lèi)號(hào)】：R730.56;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前9條

1 王遠(yuǎn)軍;聶生東;尹偉;;一種實(shí)用的多模醫(yī)學(xué)圖像配準(zhǔn)方法[J];生物醫(yī)學(xué)工程學(xué)雜志;2013年05期

2 顧順德,陳瑛,聶生東,章魯;數(shù)理統(tǒng)計(jì)在醫(yī)學(xué)圖像配準(zhǔn)評(píng)價(jià)中的應(yīng)用[J];上海第二醫(yī)科大學(xué)學(xué)報(bào);2000年S1期

3 徐建;秦安;孟曉林;陳武凡;馮前進(jìn);;基于CUDA的2D、3D剛性配準(zhǔn)方法[J];中國(guó)醫(yī)學(xué)物理學(xué)雜志;2010年02期

4 宮晶晶;孫毅勇;常兆華;;三維心腔標(biāo)測(cè)圖與CT分割圖像配準(zhǔn)方法的研究[J];生物醫(yī)學(xué)工程學(xué)雜志;2011年03期

5 謝新鵬,王淑珍,陳武凡;眼底圖像配準(zhǔn)方法的進(jìn)展[J];中國(guó)醫(yī)學(xué)物理學(xué)雜志;1998年01期

6 趙增軍;李寶生;孫洪福;王中堂;尹勇;劉同海;付政;方守信;;應(yīng)用運(yùn)動(dòng)體模對(duì)SPECT/CT圖像不同配準(zhǔn)方法的研究[J];中華腫瘤防治雜志;2009年23期

7 劉凡,高上凱;EEG電極與MRI頭模型的配準(zhǔn)方法[J];國(guó)外醫(yī)學(xué).生物醫(yī)學(xué)工程分冊(cè);2000年03期

8 馬廣棟;李承軍;付敬國(guó);吳冰;;不同解剖區(qū)域配準(zhǔn)方法對(duì)鼻咽癌體位誤差的影響[J];醫(yī)療衛(wèi)生裝備;2011年07期

9 ;[J];;年期

相關(guān)會(huì)議論文 前1條

1 韋海軍;梁甸農(nóng);朱炬波;;一種適合長(zhǎng)基線(xiàn)、復(fù)雜地形的InSAR精配準(zhǔn)方法[A];第十四屆全國(guó)信號(hào)處理學(xué)術(shù)年會(huì)(CCSP-2009)論文集[C];2009年

相關(guān)博士學(xué)位論文 前9條

1 趙麗亞;腫瘤手術(shù)導(dǎo)航中圖像分割與配準(zhǔn)方法研究[D];北京工業(yè)大學(xué);2016年

2 孫少燕;基于像素灰度的醫(yī)學(xué)圖像剛性配準(zhǔn)方法研究[D];大連理工大學(xué);2007年

3 李琦;多模態(tài)醫(yī)學(xué)影像魯棒配準(zhǔn)方法研究[D];西安電子科技大學(xué);2013年

4 徐玉華;二維光學(xué)和距離圖像配準(zhǔn)方法及其應(yīng)用研究[D];合肥工業(yè)大學(xué);2011年

5 張建國(guó);骨科導(dǎo)航手術(shù)中數(shù)字幾何處理相關(guān)技術(shù)的研究及其應(yīng)用[D];上海交通大學(xué);2009年

6 王曉華;基于集成互補(bǔ)不變特征的多源遙感影像配準(zhǔn)方法研究[D];中國(guó)礦業(yè)大學(xué);2013年

7 徐麗燕;基于特征點(diǎn)的遙感圖像配準(zhǔn)方法及應(yīng)用研究[D];南京理工大學(xué);2012年

8 王海南;基于互信息的多模醫(yī)學(xué)圖像配準(zhǔn)方法研究[D];西北工業(yè)大學(xué);2006年

9 欒紅霞;基于定量定性互信息的醫(yī)學(xué)圖像配準(zhǔn)[D];上海交通大學(xué);2007年

相關(guān)碩士學(xué)位論文 前10條

1 范霞妃;基于正交學(xué)習(xí)差分進(jìn)化算法的遙感圖像配準(zhǔn)方法研究[D];西安電子科技大學(xué);2014年

2 陳凱;基于特征的遙感圖像配準(zhǔn)方法研究[D];西安電子科技大學(xué);2014年

3 王詩(shī)琴;鼻咽癌進(jìn)行圖像引導(dǎo)放療時(shí)不同配準(zhǔn)方法對(duì)體位校正的影響[D];廣州醫(yī)學(xué)院;2010年

4 何夢(mèng)s，

本文編號(hào)：1559007