本文關(guān)鍵詞： 乳腺癌 乳腺X線(xiàn)圖像 計(jì)算機(jī)輔助診斷 卷積神經(jīng)網(wǎng)絡(luò) 遷移學(xué)習(xí)　出處：《昆明理工大學(xué)》2017年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：乳腺癌是女性最常見(jiàn)的惡性腫瘤之一,女性一生中患乳腺癌的可能性約為10%,在所有女性惡性腫瘤中,乳腺癌的發(fā)病率已居于首位,同時(shí)其致死率高達(dá)40%以上。目前對(duì)乳腺癌尚無(wú)積極的預(yù)防手段,早期診斷和及時(shí)治療是提高乳腺癌術(shù)后生存率的唯一途徑。但是乳腺腫塊的研究仍存在一定的難點(diǎn),因?yàn)槿橄倌[塊大小和對(duì)比度差異性較大,而且易受偽影和周?chē)袤w組織的干擾,極大地影響診斷系統(tǒng)的精度。本文在對(duì)目前乳腺癌計(jì)算機(jī)輔助診斷系統(tǒng)研究的基礎(chǔ)上,深入研究了卷積神經(jīng)網(wǎng)絡(luò)模型在乳腺腫塊分類(lèi)中的應(yīng)用問(wèn)題,開(kāi)展的主要研究工作如下:(1)乳腺腫塊圖像去噪。為了盡可能消除噪聲對(duì)乳腺X線(xiàn)圖像的影響,同時(shí)又保證乳腺腫塊的邊緣信息,本文分析了乳腺X線(xiàn)影像中噪聲的特點(diǎn),對(duì)比多種圖像去噪算法,并在乳腺X線(xiàn)影像上進(jìn)行試驗(yàn),經(jīng)實(shí)驗(yàn)結(jié)果確定使用小波算法去除圖像噪聲。(2)腫塊區(qū)域分割與形態(tài)學(xué)處理。論文在乳腺腫塊的分割方面,應(yīng)用大津算法對(duì)乳腺X線(xiàn)影像進(jìn)行分割,提取出感興趣區(qū)域。然后運(yùn)用形態(tài)學(xué)方法對(duì)粗分割得來(lái)的感興趣區(qū)域進(jìn)行膨脹與開(kāi)閉運(yùn)算處理,用于保存腫塊圖像的邊緣信息和消除腫塊內(nèi)部的孔洞,得到最終的腫塊圖像。(3)腫塊分類(lèi)。論文選擇使用遷移學(xué)習(xí)的方法,將大規(guī)模深度卷積神經(jīng)網(wǎng)絡(luò)應(yīng)用在乳腺腫塊良惡性區(qū)分中。論文對(duì)卷積神經(jīng)網(wǎng)絡(luò)模型結(jié)構(gòu)和訓(xùn)練過(guò)程進(jìn)行分析與研究,嘗試使用遷移學(xué)習(xí)的方法,將在自然圖像集上訓(xùn)練完畢的GoogLeNet和AlexNet在乳腺腫塊圖像上進(jìn)行微調(diào),微調(diào)后的模型應(yīng)用在乳腺腫塊的分類(lèi)中,實(shí)現(xiàn)了基于卷積神經(jīng)網(wǎng)絡(luò)的乳腺腫塊良惡性的區(qū)分。文中還對(duì)比從乳腺圖像上直接訓(xùn)練的淺層卷積神經(jīng)網(wǎng)絡(luò)和人工設(shè)定特征實(shí)現(xiàn)分類(lèi)的幾種模型,實(shí)驗(yàn)結(jié)果也表明了基于遷移學(xué)習(xí)的深度卷積神經(jīng)網(wǎng)絡(luò)模型在乳腺腫塊良惡性區(qū)分中存在較大的優(yōu)勢(shì)。
[Abstract]:Breast cancer is one of the most common malignant tumors in women. At the same time, the fatality rate of breast cancer is over 40%. At present, there is no positive preventive method for breast cancer. Early diagnosis and timely treatment are the only way to improve the survival rate of breast cancer. However, there are still some difficulties in the study of breast masses. Because the size and contrast of breast masses vary greatly, and they are easily disturbed by artifacts and surrounding glands, the accuracy of the diagnostic system is greatly affected. In this paper, the application of convolution neural network model in classification of breast masses is deeply studied. The main research work is as follows: 1) De-noising of breast masses. At the same time, the edge information of breast mass is guaranteed. This paper analyzes the characteristics of noise in mammography, compares various image denoising algorithms, and carries out experiments on mammography. The experimental results confirm that the wavelet algorithm is used to remove the noise of the image and to deal with the morphology of the mass. In the aspect of the segmentation of the breast mass, the paper applies the Otsu algorithm to segment the mammary mammary X-ray image. The region of interest is extracted, and then the rough segmentation of the region of interest is processed by the morphological method, which is used to preserve the edge information of the mass image and eliminate the holes inside the mass. The final mass image is obtained. The large scale deep convolution neural network is applied to distinguish benign and malignant breast masses. This paper analyzes and studies the model structure and training process of convolution neural network, and tries to use the transfer learning method. The GoogLeNet and AlexNet trained on the natural image set are fine-tuned on the breast mass image, and the fine-tuned model is applied to the classification of the breast mass. The classification of benign and malignant breast masses based on convolution neural network is realized. The experimental results also show that the deep convolution neural network model based on migration learning has a great advantage in differentiating benign and malignant breast masses.
【學(xué)位授予單位】：昆明理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：R737.9;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前4條

1 江帆;劉輝;王彬;孫曉峰;;基于火焰圖像CNN的轉(zhuǎn)爐煉鋼吹煉終點(diǎn)判斷方法[J];計(jì)算機(jī)工程;2016年10期

2 王志明;;無(wú)參考圖像質(zhì)量評(píng)價(jià)綜述[J];自動(dòng)化學(xué)報(bào);2015年06期

3 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(bào);2015年01期

4 方志沂,劉君;乳腺癌診斷進(jìn)展[J];中國(guó)腫瘤臨床;2002年11期

相關(guān)碩士學(xué)位論文 前1條

1 張橋新;乳腺腫塊計(jì)算機(jī)輔助檢測(cè)算法研究[D];西安電子科技大學(xué);2009年

，

本文編號(hào)：1497097