發(fā)布時(shí)間：2018-08-14 10:02

【摘要】：深度學(xué)習(xí)(Deep Learning)目前被廣泛應(yīng)用在很多科研領(lǐng)域,并且在工業(yè)生產(chǎn)中也得到了很多的應(yīng)用,都取的了很多不錯(cuò)的效果。最近幾年,深度學(xué)習(xí)算法的研究非常熱門(mén),已經(jīng)有研究人員將深度學(xué)習(xí)應(yīng)用到醫(yī)學(xué)圖像分析領(lǐng)域,深度學(xué)習(xí)算法的出現(xiàn),使得計(jì)算機(jī)在處理大批量的圖像數(shù)據(jù)變得更加容易,處理數(shù)據(jù)的速度更快。深度學(xué)習(xí)模型也越來(lái)越多,根據(jù)實(shí)現(xiàn)功能的不同,學(xué)習(xí)模型又分為很多種。比如說(shuō),深度卷積神經(jīng)網(wǎng)絡(luò)(Convolutional Neural Networks,CNNs)應(yīng)用于圖像分類(lèi),全卷積神經(jīng)網(wǎng)絡(luò)(Fully Convolutional Networks,FCN)應(yīng)用于深度學(xué)習(xí)算法圖像分割,不同的網(wǎng)絡(luò)模型有不同的結(jié)構(gòu)參數(shù)。醫(yī)學(xué)圖像分割就是將醫(yī)學(xué)圖像中病變區(qū)域給劃分出來(lái),將這些區(qū)域進(jìn)行定量或定性的疾病分析,醫(yī)學(xué)圖像分割在醫(yī)學(xué)圖像處理過(guò)程中地位十分重要,是實(shí)現(xiàn)目標(biāo)區(qū)域提取和定量表示的基礎(chǔ),能夠?yàn)獒t(yī)療診斷提供有用信息。在本文中我們將著重研究深度學(xué)習(xí)算法在主動(dòng)脈瘤CT(電子計(jì)算機(jī)斷層掃描技術(shù))影像分割和OCT(光學(xué)相干斷層掃描技術(shù))脈絡(luò)膜分割中的應(yīng)用,提出的方法介紹如下:(1)為了解決能將CT影像中主動(dòng)脈瘤分割出來(lái),我們?cè)O(shè)計(jì)出了基于深度學(xué)習(xí)算法的TJ-1模型,利用我們已有的數(shù)據(jù)集,結(jié)合我們自己搭建的深度學(xué)習(xí)算法運(yùn)行平臺(tái)Caffe,實(shí)現(xiàn)對(duì)TJ-1分割網(wǎng)絡(luò)模型的學(xué)習(xí)過(guò)程,最后通過(guò)實(shí)驗(yàn)的方式,來(lái)證明我們所設(shè)計(jì)的網(wǎng)絡(luò)模型對(duì)主動(dòng)脈瘤分割是有效的。(2)基于TJ-1模型,我們?cè)O(shè)計(jì)了TJ-2模型,利用TJ-2模型學(xué)習(xí)得到的OCT圖像邊緣權(quán)重,再結(jié)合圖搜索算法來(lái)完成OCT脈絡(luò)膜分割實(shí)驗(yàn)。通過(guò)實(shí)驗(yàn),我們發(fā)現(xiàn)我們所提的方法,具有很好的應(yīng)用前景,值得我們繼續(xù)去深入研究。我們?cè)O(shè)計(jì)的實(shí)驗(yàn)方案,分割效果好,時(shí)間效率高。
[Abstract]:Deep learning (Deep Learning) has been widely used in many fields of scientific research, and has been applied in industrial production, and many good results have been obtained. In recent years, the research of depth learning algorithm is very popular. Some researchers have applied depth learning to the field of medical image analysis. The emergence of depth learning algorithm makes it easier for computers to process large quantities of image data. Data processing is faster. There are more and more deep learning models, which can be divided into many kinds according to the different functions. For example, the deep convolution neural network (Convolutional Neural networks) is applied to image classification, and the full convolution neural network (Fully Convolutional networks) is applied to image segmentation. Different network models have different structural parameters. Medical image segmentation is to divide the diseased areas in medical images and analyze these areas quantitatively or qualitatively. Medical image segmentation is very important in the process of medical image processing. It is the basis of target region extraction and quantitative representation, and can provide useful information for medical diagnosis. In this paper, we will focus on the application of depth learning algorithm in CT image segmentation and OCT (optical coherence tomography) choroidal segmentation of aortic aneurysms. The proposed methods are described as follows: (1) in order to solve the problem of segmenting aortic aneurysms from CT images, we design a TJ-1 model based on depth learning algorithm and use our existing data sets. The learning process of TJ-1 segmenting network model is realized by using our running platform of depth learning algorithm. Finally, the experimental method is used to prove that the network model designed by us is effective for aortic aneurysm segmentation. (2) based on TJ-1 model, the network model can be used to segment aortic aneurysm. We design the TJ-2 model and use the TJ-2 model to learn the edge weight of the OCT image and then combine the image search algorithm to complete the OCT choroid segmentation experiment. Through experiments, we find that the proposed method has a good prospect of application and is worthy of further study. The experimental scheme designed by us has good segmentation effect and high time efficiency.
【學(xué)位授予單位】：山東師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.41;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李寰宇;畢篤彥;查宇飛;楊源;;一種易于初始化的類(lèi)卷積神經(jīng)網(wǎng)絡(luò)視覺(jué)跟蹤算法[J];電子與信息學(xué)報(bào);2016年01期

2 李玉榮;;計(jì)算機(jī)圖像處理技術(shù)的應(yīng)用策略研究[J];科技創(chuàng)新與應(yīng)用;2015年23期

3 張維維;羅建光;肖恩華;;多層密網(wǎng)支架在動(dòng)脈瘤及主動(dòng)脈夾層中的研究進(jìn)展[J];臨床放射學(xué)雜志;2015年06期

4 江貴平;秦文健;周壽軍;王昌淼;;醫(yī)學(xué)圖像分割及其發(fā)展現(xiàn)狀[J];計(jì)算機(jī)學(xué)報(bào);2015年06期

5 楊海燕;蔣新華;聶作先;;基于并行卷積神經(jīng)網(wǎng)絡(luò)的人臉關(guān)鍵點(diǎn)定位方法研究[J];計(jì)算機(jī)應(yīng)用研究;2015年08期

6 陳玉平;;光學(xué)相干層析成像綜述[J];價(jià)值工程;2014年32期

7 劉建偉;劉媛;羅雄麟;;深度學(xué)習(xí)研究進(jìn)展[J];計(jì)算機(jī)應(yīng)用研究;2014年07期

8 賀鵬;趙川;;淺談人工智能的現(xiàn)狀與發(fā)展[J];電子技術(shù)與軟件工程;2013年19期

9 張國(guó)建;;CT影像在惡性腫瘤診斷中的應(yīng)用分析[J];中國(guó)衛(wèi)生產(chǎn)業(yè);2012年31期

10 張石;董建威;佘黎煌;;醫(yī)學(xué)圖像分割算法的評(píng)價(jià)方法[J];中國(guó)圖象圖形學(xué)報(bào);2009年09期

相關(guān)博士學(xué)位論文 前1條

1 張小峰;基于模糊聚類(lèi)算法的醫(yī)學(xué)圖像分割技術(shù)研究[D];山東大學(xué);2014年

相關(guān)碩士學(xué)位論文 前3條

1 劉崢強(qiáng);深度學(xué)習(xí)算法在車(chē)牌識(shí)別系統(tǒng)中的應(yīng)用[D];電子科技大學(xué);2016年

2 曹貴寶;隨機(jī)森林和卷積神經(jīng)網(wǎng)絡(luò)在神經(jīng)細(xì)胞圖像分割中的應(yīng)用研究[D];山東大學(xué);2014年

3 邵永杰;腔內(nèi)修復(fù)術(shù)治療腹主動(dòng)脈瘤臨床應(yīng)用研究[D];大連醫(yī)科大學(xué);2014年

，

本文編號(hào)：2182508