發(fā)布時間：2018-03-24 01:12

  本文選題：肺結(jié)節(jié)檢測　切入點(diǎn)：卷積神經(jīng)網(wǎng)絡(luò)　出處：《江南大學(xué)》2017年碩士論文

【摘要】：隨著時代的發(fā)展,空氣污染的加重,肺癌已經(jīng)成為威脅人類生命惡性程度最高的腫瘤之一。及早發(fā)現(xiàn)和治療可以大大地提高病人的存活率。肺癌的早期癥狀在醫(yī)學(xué)影像上大多表現(xiàn)為孤立的肺結(jié)節(jié),在胸片上通常表現(xiàn)為圓形或近似圓形的低對比度光斑,沒有特殊的處理,肉眼是很難將肺結(jié)節(jié)與肺部其它的軟組織區(qū)分出來。深度學(xué)習(xí)是機(jī)器學(xué)習(xí)的一個新興領(lǐng)域,在近年來得到了高速的發(fā)展。深度學(xué)習(xí)其實(shí)就是通過組建多個隱層神經(jīng)網(wǎng)絡(luò)和使用大量的數(shù)據(jù)進(jìn)行訓(xùn)練,從而提取出這些數(shù)據(jù)中更為有用的特征來提高模型的預(yù)測或分類的準(zhǔn)確性。它在圖像處理、語音和自然語言處理等多個領(lǐng)域都取得了不錯的成果。本文主要研究針對X光胸片的肺部結(jié)節(jié)自動檢測方法,并初步探索了應(yīng)用深度學(xué)習(xí)方法在CT圖像上進(jìn)行肺結(jié)節(jié)檢測。主要內(nèi)容如下:(1)通過研究傳統(tǒng)胸片肺結(jié)節(jié)檢測方案,提出一種基于卷積神經(jīng)網(wǎng)絡(luò)的胸片肺結(jié)節(jié)檢測方案。該方案首先對胸片進(jìn)行預(yù)處理,用USM銳化的方法對圖像中的結(jié)節(jié)信號進(jìn)行增強(qiáng)。然后在胸片上用滑動窗口的方法切取小塊,下采樣后輸入進(jìn)預(yù)先訓(xùn)練好的卷積神經(jīng)網(wǎng)絡(luò)進(jìn)行分類,得到整張胸片的候選結(jié)節(jié)區(qū)域。最后根據(jù)面積閾值排除掉大量的假陽性。在JSRT數(shù)據(jù)庫上的實(shí)驗(yàn)結(jié)果表明,該方法在相同的假陽性水平下比相關(guān)文獻(xiàn)中方法可以檢測出更多的肺結(jié)節(jié)。(2)通過研究肺結(jié)節(jié)圖像小塊下采樣后的形態(tài)表現(xiàn),提出一種集成卷積神經(jīng)網(wǎng)絡(luò)用于胸片上的肺結(jié)節(jié)檢測。該方法也是先對胸片進(jìn)行預(yù)處理,用USM銳化方法對圖像中的結(jié)節(jié)信號進(jìn)行增強(qiáng)。然后用滑動窗口的方法從胸片上切取229×229的小塊,接著分別下采樣到12×12,32×32和60×60三個不同的尺度,分別輸入進(jìn)三個預(yù)先訓(xùn)練好的不同的卷積神經(jīng)網(wǎng)絡(luò),最終的分類結(jié)果由這三個神經(jīng)網(wǎng)絡(luò)的輸出結(jié)果投票決定。由此可以得到整個胸片的候選區(qū)域,最后根據(jù)面積閾值排除大量的假陽性。在JSRT數(shù)據(jù)庫上的實(shí)驗(yàn)結(jié)果表明,該集成方法可以排除掉大量的假陽性,使其在相同的假陽性水平下比相關(guān)文獻(xiàn)及上一章的方法檢測出更多的肺結(jié)節(jié)。(3)初步探索了在CT圖像上進(jìn)行疑似肺結(jié)節(jié)的檢測。從肺結(jié)節(jié)的立體特性出發(fā),提出一種多輸入的卷積神經(jīng)網(wǎng)絡(luò)模型用于CT圖像上的疑似肺結(jié)節(jié)檢測。該方法首先對CT切片進(jìn)行預(yù)處理,用USM銳化增強(qiáng)結(jié)節(jié)的信號。然后在相鄰的切片的相同位置切取相同大小的小塊,輸入進(jìn)預(yù)先訓(xùn)練好的多輸入卷積神經(jīng)網(wǎng)絡(luò),得到整個CT序列中的候選區(qū)域。用面積閾值可以做初步的假陽性篩選工作。在從LIDC-IDRI中選取的子集數(shù)據(jù)庫上的實(shí)驗(yàn)結(jié)果來看,結(jié)節(jié)的檢出率滿足要求,可以用于對其做更加深層次的研究。
[Abstract]:With the development of the times, the air pollution is getting worse. Lung cancer has become one of the most malignant tumors threatening human life. Early detection and treatment can greatly improve the survival rate of patients. On chest radiographs, they usually appear as round or nearly circular low-contrast spots, without special treatment, and it is difficult for the naked eye to distinguish pulmonary nodules from other soft tissues of the lungs. Deep learning is a new field of machine learning. In recent years, rapid development has been achieved. In fact, deep learning is training by building multiple hidden layer neural networks and using a large amount of data. To extract more useful features from these data to improve the accuracy of the prediction or classification of the model, which is used in image processing, Many fields, such as speech processing and natural language processing, have achieved good results. This paper mainly studies the automatic detection method of pulmonary nodules based on X-ray chest radiographs. The paper also preliminarily explored the application of deep learning method to the detection of pulmonary nodules on CT images. The main contents are as follows: 1) by studying the traditional chest radiographic lung nodule detection scheme, A new method for detecting pulmonary nodules in chest radiographs based on convolutional neural network is proposed. Firstly, the chest radiographs are preprocessed, and the nodule signals in the images are enhanced by USM sharpening, and then the small pieces are cut out by sliding window on the chest radiographs. After sampling, we input the pre-trained convolution neural network to classify the candidate nodule area of the whole chest film. Finally, a large number of false positives are excluded according to the area threshold. The experimental results on JSRT database show that, This method can detect more pulmonary nodules at the same false positive level than in related literature. An integrated convolution neural network is proposed to detect pulmonary nodules on chest radiographs. USM sharpening method was used to enhance the nodule signal in the image, and then the small pieces of 229 脳 229 were cut from chest radiographs by sliding window method, and then sampled to three different scales of 12 脳 12, 32 脳 32 and 60 脳 60, respectively. The final classification results are determined by the output results of the three neural networks, and the candidate regions of the whole chest radiography can be obtained by the input of three pre-trained different convolutional neural networks, and the final classification results are determined by the output results of the three neural networks. Finally, a large number of false positives are excluded according to the area threshold. The experimental results on the JSRT database show that the integration method can eliminate a large number of false positives. At the same false positive level, more pulmonary nodules were detected under the same false positive level than those in the previous chapter. (3) A preliminary exploration was made for the detection of suspected pulmonary nodules on CT images. A multi-input convolution neural network model is proposed for detecting suspected pulmonary nodules on CT images. USM sharpening is used to enhance the signal of nodules. Then the same size small pieces are cut at the same position of adjacent slices and input into the pre-trained multi-input convolution neural network. The candidate regions in the whole CT sequence are obtained. The initial false positive screening can be done by using the area threshold. The experimental results from the subset database selected from LIDC-IDRI show that the detection rate of nodules meets the requirements. It can be used for deeper research.
【學(xué)位授予單位】：江南大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：R734.2;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前4條

1 陳寶;陳勝;何菁;張茗屋;仲思凱;;基于虛擬雙能量減影軟組織胸片生成技術(shù)計(jì)算機(jī)輔助檢測肺結(jié)節(jié)[J];中國醫(yī)學(xué)影像技術(shù);2015年08期

2 孫志軍;薛磊;許陽明;王正;;深度學(xué)習(xí)研究綜述[J];計(jì)算機(jī)應(yīng)用研究;2012年08期

3 陳勝;李莉;;一種全新的基于胸片計(jì)算機(jī)輔助檢測肺結(jié)節(jié)方案[J];電子學(xué)報(bào);2010年05期

4 周志華,陳世福;神經(jīng)網(wǎng)絡(luò)集成[J];計(jì)算機(jī)學(xué)報(bào);2002年01期

，

本文編號：1656032