本文選題：胎盤成熟度評(píng)估 + 特征融合�。� 參考：《深圳大學(xué)》2017年碩士論文

【摘要】：胎盤成熟度分級(jí)的準(zhǔn)確性對(duì)小于胎齡兒、死胎及死產(chǎn)的臨床診斷有重要的作用。但是由于成像過(guò)程復(fù)雜、妊娠期長(zhǎng)、圖像質(zhì)量差異以及醫(yī)生主觀判斷差異,導(dǎo)致胎盤成熟度分級(jí)成為耗時(shí)又冗長(zhǎng)的工作。盡管有近年來(lái)醫(yī)學(xué)成像手段和技術(shù)都有了很大的進(jìn)步,胎盤成熟度準(zhǔn)確分級(jí)仍然有很大的挑戰(zhàn)性。為了解決這一問(wèn)題,本文提出一種基于特征融合和判別式學(xué)習(xí)的胎盤成熟度自動(dòng)分級(jí)算法。首先,從B型灰階超聲圖像中提取灰度信息,同時(shí)從彩色多普勒能量(color Doppler energy imaging,CDE)超聲圖像中提取血管信息,通過(guò)高斯差分的方法提取關(guān)鍵點(diǎn),并對(duì)關(guān)鍵點(diǎn)提取尺度不變特征變換(scale-invariant feature transform,SIFT)特征以及灰度特征,對(duì)兩種特征進(jìn)行連接融合,利用Fisher向量編碼的方法,形成碼書,經(jīng)過(guò)歸一化,最后用支持向量機(jī)(support vector machine,SVM)進(jìn)行分類,最終得到了 92.7%的準(zhǔn)確率。對(duì)比不同關(guān)鍵點(diǎn)檢測(cè)方法、不同特征提取方法以及不同的特征編碼方法所得的實(shí)驗(yàn)結(jié)果表明,本文所提出的方法在胎盤成熟度自動(dòng)分級(jí)問(wèn)題中能取得很好的結(jié)果,對(duì)臨床的判斷有一定的指導(dǎo)意義。深度學(xué)習(xí)的發(fā)展為我們進(jìn)一步提升結(jié)果的準(zhǔn)確率提供了可能。有限的特征描述不能完整表述圖像信息,所以本文通過(guò)將現(xiàn)有主流卷積神經(jīng)網(wǎng)絡(luò)(convolutional neural network,CNN)方法用于解決胎盤成熟度自動(dòng)分級(jí)問(wèn)題,用卷積層提取特征,并以池化層加速計(jì)算,以端到端的方式得到分類結(jié)果,減少人為對(duì)特征的選擇和干預(yù),得到更好的結(jié)果。本文以先前所取得的數(shù)據(jù)做訓(xùn)練,再以此后采集的數(shù)據(jù)為測(cè)試數(shù)據(jù),利用AlexNet、VGG-F、VGG-S、VGG-M以及VGG-VD-16和VGG-VD-19進(jìn)行實(shí)驗(yàn),得到了相較于傳統(tǒng)機(jī)器學(xué)習(xí)方法更好的結(jié)果,為進(jìn)一步設(shè)計(jì)適用于該問(wèn)題的網(wǎng)絡(luò)結(jié)構(gòu)提供了基礎(chǔ)。本文在以傳統(tǒng)的機(jī)器學(xué)習(xí)方法解決胎盤成熟度自動(dòng)分級(jí)問(wèn)題中,首次引入特征融合的思想,并在特征編碼中采用多層Fisher向量編碼,增強(qiáng)局部特征,從而提升分類的準(zhǔn)確率。后續(xù)研究中對(duì)流行的深度學(xué)習(xí)方法的嘗試,并取得了不錯(cuò)的結(jié)果,也為胎盤成熟度自動(dòng)分級(jí)算法的臨床應(yīng)用提供了新的思路。
[Abstract]:The accuracy of placental maturity classification plays an important role in the clinical diagnosis of small gestational age, stillbirth and stillbirth. However, due to the complexity of imaging process, the long gestation period, the difference of image quality and the difference of doctors' subjective judgment, placental maturity grading becomes a time-consuming and lengthy task. Although great progress has been made in medical imaging techniques and techniques in recent years, accurate classification of placental maturity remains a challenge. To solve this problem, an automatic placental maturity classification algorithm based on feature fusion and discriminant learning is proposed. Firstly, grayscale information is extracted from B-type gray scale ultrasound image, and vascular information is extracted from color Doppler energy image. The key points are extracted by Gao Si difference method. The scale-invariant feature transform sift feature and gray scale feature are extracted from the key points. The two features are joined and fused. The codebook is formed by using the Fisher vector coding method. After normalization, the support vector machine is used to classify the two features. Finally, the accuracy rate of 92.7% was obtained. Compared with different key point detection methods, different feature extraction methods and different feature coding methods, the experimental results show that the proposed method can achieve good results in the placental maturity automatic grading problem. It has certain guiding significance to clinical judgment. The development of deep learning makes it possible for us to further improve the accuracy of the results. The finite feature description can not represent the image information completely, so we use the existing convolutional neural network to solve the problem of automatic grading of placenta maturity, extract the feature with convolution layer, and calculate it with pool layer. The classification results are obtained by end-to-end approach, and better results are obtained by reducing the artificial selection and intervention of features. In this paper, we use the data obtained before for training, and then take the data collected since then as the test data. We use AlexNet VGG-FGG-FG VGG-SGG-M, VGG-VD-16 and VGG-VD-19 to carry out experiments. The results are better than those of traditional machine learning methods. It provides the foundation for further designing the network structure suitable for this problem. In this paper, the idea of feature fusion is introduced for the first time in the traditional machine learning method to solve the placental maturity automatic grading problem, and the multi-layer Fisher vector coding is used in the feature coding to enhance the local features, thus improving the accuracy of classification. In the following research, the popular deep learning method has been tried, and good results have been obtained. It also provides a new idea for clinical application of placental maturity automatic grading algorithm.
【學(xué)位授予單位】：深圳大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：R714.5;R445.1

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王元?jiǎng)?劉芳;;探討高原環(huán)境對(duì)胎盤成熟度的影響[J];西藏醫(yī)藥雜志;2007年04期

2 羅曉俊;謝其燕;王莉;郭迎新;劉艷國(guó);;超聲胎盤成熟度檢查中應(yīng)用胎盤大切面的探討[J];臨床醫(yī)學(xué)工程;2012年09期

3 ;準(zhǔn)媽媽最關(guān)心的N個(gè)問(wèn)題[J];母嬰世界;2005年06期

4 韓茹;;胎盤成熟度超聲分級(jí)與圍生兒結(jié)局的關(guān)系[J];實(shí)用醫(yī)技雜志;2006年22期

5 譚小勇;張利平;;胎盤成熟度與圍產(chǎn)兒結(jié)局的臨床探討[J];西部醫(yī)學(xué);2009年09期

6 曾正經(jīng),劉登淮,張賢良,王朝華;超聲顯象監(jiān)測(cè)胎盤成熟度的改變與病理學(xué)所見的對(duì)照研究[J];中國(guó)超聲醫(yī)學(xué)雜志;1991年01期

7 張?zhí)m珍,譚麗君,李大慈;胎盤成熟度分級(jí)與胎肺成熟的相關(guān)性探討[J];中山醫(yī)科大學(xué)學(xué)報(bào);1999年02期

8 張?zhí)m珍,譚麗君,李大慈;胎盤成熟度分級(jí)與胎盤功能的相關(guān)性探討[J];中山醫(yī)科大學(xué)學(xué)報(bào);2001年05期

9 劉智,常才 ,周先榮;常規(guī)胎盤超聲分級(jí)法與自動(dòng)分級(jí)法評(píng)價(jià)胎盤成熟度的比較[J];中國(guó)醫(yī)學(xué)影像技術(shù);2001年12期

10 孫麗霞;孟源;;臍血流與胎盤成熟度測(cè)定對(duì)圍生兒預(yù)后狀況評(píng)價(jià)[J];濟(jì)寧醫(yī)學(xué)院學(xué)報(bào);2007年02期

相關(guān)會(huì)議論文 前1條

1 何寧;邵亞勤;孟君;胡衛(wèi)梅;楊高怡;;聲脈沖輻射力成像技術(shù)評(píng)價(jià)不同時(shí)期胎盤成熟度[A];2012年浙江省超聲醫(yī)學(xué)學(xué)術(shù)年會(huì)論文集[C];2012年

相關(guān)碩士學(xué)位論文 前1條

1 李婉君;胎盤成熟度自動(dòng)分級(jí)探索[D];深圳大學(xué);2017年

，

本文編號(hào)：2034574