本文關(guān)鍵詞： 深度學(xué)習(xí) 乳腺癌 動態(tài)增強核磁共振成像 三維卷積神經(jīng)網(wǎng)絡(luò) 遷移學(xué)習(xí)　出處：《杭州電子科技大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：在世界范圍內(nèi),乳腺癌以其高發(fā)病率、高死亡率嚴(yán)重威脅女性身體健康,且近年來乳腺癌新增病例數(shù)持續(xù)上升。因其發(fā)病機理不確定和病情隱匿,使得早期乳腺癌很難被發(fā)現(xiàn)。乳腺動態(tài)增強核磁共振影像(Dynamic Contrast-enhanced magnetic resonance imaging,DCE-MRI)具有較高的軟組織分辨能力,近年來成為廣泛應(yīng)用于乳腺癌早期檢查的重要方式。模仿生物視覺原理的深度學(xué)習(xí)能夠自動學(xué)習(xí)數(shù)據(jù)層次化的特征,使其在圖像、語音、自然語言處理等方面取得巨大成就。人們不斷探索將深度學(xué)習(xí)應(yīng)用在生物醫(yī)學(xué)領(lǐng)域,并取得了一定成果。本論文的研究工作主要是基于深度學(xué)習(xí)方法在早期乳腺癌診斷上的應(yīng)用,探索研究基于不同深度學(xué)習(xí)方法,并利用不同模態(tài)的影像數(shù)據(jù)對乳腺癌早期診斷。本文的主要研究內(nèi)容如下:(1)基于非監(jiān)督學(xué)習(xí)堆疊自編碼特征提取方法與分類利用非監(jiān)督堆疊自編碼(Stacked Autoencoder,SAE)進(jìn)行乳腺癌特征提取與分類。首先對實驗數(shù)據(jù)預(yù)處理,提取ROI及PCA白化,其次利用非監(jiān)督逐層訓(xùn)練的方式提取不同層級的特征,最后利用Softmax進(jìn)行早期乳腺癌良惡性判別。(2)基于三維卷積神經(jīng)網(wǎng)絡(luò)乳腺癌早期診斷提出構(gòu)建三維卷積神經(jīng)網(wǎng)絡(luò),通過平移、旋轉(zhuǎn)、鏡像等方式將樣本數(shù)據(jù)擴充。然后利用二維和三維卷積網(wǎng)絡(luò)來對疾病分類預(yù)測。利用三維增強影像序列和增強率影像實現(xiàn)早期乳腺癌的識別分類。(3)遷移學(xué)習(xí)判別乳腺癌良惡性研究研究遷移學(xué)習(xí)模型在早期乳腺癌良惡性分類上的應(yīng)用,將在大數(shù)據(jù)集(如ImageNet)上預(yù)訓(xùn)練得到的網(wǎng)絡(luò)模型作為底層和中層的特征提取器,遷移到MRI影像數(shù)據(jù)集,微調(diào)模型參數(shù)進(jìn)行分類。從研究結(jié)果來看,本文所提出的研究方法能夠較好的對早期乳腺癌識別分類。降噪堆疊自編碼對乳腺癌早期診斷實驗結(jié)果AUC達(dá)到0.85�；�3DCNN早期乳腺癌分類實驗結(jié)果AUC值0.80,靈敏度和特異性分別達(dá)到0.82和0.74。在遷移網(wǎng)絡(luò)模型分類實驗中,AUC,靈敏度和特異性分別達(dá)到0.86,0.85和0.81。未來若將深度學(xué)習(xí)方法自動學(xué)習(xí)到的不同層級的特征融合到MRI輔助診斷系統(tǒng)中,將有助提升系統(tǒng)的性能,具有較好應(yīng)用前景。
[Abstract]:In the world, breast cancer is a serious threat to the health of women because of its high incidence and high mortality, and in recent years, the number of new cases of breast cancer has been increasing, because of its pathogenesis of uncertainty and hidden disease. This makes early breast cancer difficult to detect. Dynamic enhanced Magnetic Resonance Imaging (. Dynamic Contrast-enhanced magnetic resonance imaging. DCE-MRI) has high soft tissue resolution. In recent years, it has become an important way to be widely used in early detection of breast cancer. Deep learning imitating biological vision principles can automatically learn the hierarchical features of data and make it in images and speech. Great achievements have been made in natural language processing and so on. People are constantly exploring the application of in-depth learning in biomedical fields. The research work in this paper is mainly based on the application of depth learning method in the diagnosis of early breast cancer, and the research is based on different depth learning methods. The main contents of this paper are as follows: (1) based on unsupervised learning stack self-coding feature extraction method and classification using unsupervised stack self-coding (. Stacked Autoencoder. First, ROI and PCA whitening were extracted from the experimental data, and then the features of different levels were extracted by unsupervised training. Finally, Softmax is used to distinguish benign and malignant breast cancer. (2) based on three-dimensional convolution neural network for early diagnosis of breast cancer, a three-dimensional convolutional neural network is proposed to construct a three-dimensional convolutional neural network, which can be translated and rotated. Image image is used to expand the sample data, and then two dimensional and three dimensional convolution networks are used to predict disease classification. Three-dimensional enhanced image sequences and enhancement rate images are used to realize the recognition and classification of early breast cancer. Study on differentiation of benign and malignant Breast Cancer by Migration Learning; Application of Migration Learning Model in Classification of benign and malignant Breast Cancer in early stage. The network model pre-trained on the big data set (such as Image net) is used as a feature extractor at the bottom and middle levels to migrate to the MRI image data set. Fine tuning the model parameters to classify. From the results of the study. The research method proposed in this paper can identify and classify early breast cancer better. The experimental results of early breast cancer diagnosis based on noise reduction stacking self-coding can reach 0.85. The classification of early breast cancer based on 3DCNs is true. The AUC value was 0.80. The sensitivity and specificity were 0.82 and 0.74.The sensitivity and specificity of AUC were 0.86 respectively. 0.85 and 0.81. In the future, if the features of different levels of the automatic learning method are fused into the MRI aided diagnosis system, it will help to improve the performance of the system and have a good prospect of application.
【學(xué)位授予單位】：杭州電子科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41;R737.9

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 羅蔓;黃靖;楊豐;;基于多模態(tài)3D-CNNs特征提取的MRI腦腫瘤分割方法[J];科學(xué)技術(shù)與工程;2014年31期

2 莊福振;羅平;何清;史忠植;;遷移學(xué)習(xí)研究進(jìn)展[J];軟件學(xué)報;2015年01期

3 李學(xué)璐;趙作偉;朱丹丹;;乳腺攝片的計算機輔助診斷技術(shù)在乳腺癌診斷中的新進(jìn)展[J];醫(yī)學(xué)與哲學(xué)(B);2013年03期

4 程智輝;陳將宏;;基于概率神經(jīng)網(wǎng)絡(luò)的乳腺癌計算機輔助診斷[J];計算機仿真;2012年09期

5 余立君;;乳腺癌早期診斷設(shè)備及其技術(shù)進(jìn)展——超聲、磁共振、核醫(yī)學(xué)乳腺成像技術(shù)進(jìn)展(二)[J];中國醫(yī)療設(shè)備;2010年08期

6 王榮福;;乳腺癌影像診斷技術(shù)應(yīng)用進(jìn)展[J];中國醫(yī)學(xué)影像技術(shù);2009年05期

7 婁路馨;彰俊杰;時高峰;;MR動態(tài)增強及減影成像對乳腺良惡性疾病的診斷價值[J];臨床放射學(xué)雜志;2007年02期

8 孫強;;乳腺癌的早期診斷[J];實用醫(yī)學(xué)雜志;2007年01期

9 方志沂,邱曉光;乳腺癌的分布規(guī)律及其危險因素[J];中國全科醫(yī)學(xué);2002年06期

10 夏順仁,呂維雪;乳腺X線圖像的計算機輔助診斷技術(shù)研究進(jìn)展[J];國外醫(yī)學(xué).生物醫(yī)學(xué)工程分冊;2000年01期

相關(guān)博士學(xué)位論文 前2條

1 周悅;基于乳腺X線圖像的計算機輔助診斷方法研究[D];蘇州大學(xué);2014年

2 徐偉棟;乳腺X線圖像的計算機輔助診斷技術(shù)研究[D];浙江大學(xué);2006年

相關(guān)碩士學(xué)位論文 前3條

1 劉洋;基于深度學(xué)習(xí)的圖像檢索技術(shù)研究[D];華中科技大學(xué);2015年

2 李衛(wèi);深度學(xué)習(xí)在圖像識別中的研究及應(yīng)用[D];武漢理工大學(xué);2014年

3 楊騫;基于DCE-MRI影像的乳腺癌早期診斷研究[D];杭州電子科技大學(xué);2014年

，

本文編號：1469127