本文選題：腰椎　切入點(diǎn)：卷積神經(jīng)網(wǎng)絡(luò)　出處：《南京理工大學(xué)》2017年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：隨著數(shù)字圖像技術(shù)與計(jì)算機(jī)視覺(jué)技術(shù)的不斷發(fā)展,使用計(jì)算機(jī)技術(shù)手段對(duì)醫(yī)學(xué)圖像數(shù)據(jù)進(jìn)行處理和分析來(lái)輔助醫(yī)生診斷疾病已逐漸得到普及。本文針對(duì)腰椎不穩(wěn)癥這一普遍而嚴(yán)重的健康問(wèn)題,提出了一種腰椎不穩(wěn)癥輔助診斷方法:基于學(xué)習(xí)的腰椎檢測(cè)和跟蹤方法。該方法使用腰椎的數(shù)字視頻影像(DVF)進(jìn)行處理與分析,主要研究工作如下:(1)針對(duì)目前腰椎跟蹤方法中初始狀態(tài)的腰椎目標(biāo)均需通過(guò)人工標(biāo)注的問(wèn)題,提出了一種基于卷積神經(jīng)網(wǎng)絡(luò)的腰椎檢測(cè)方法。首先對(duì)原始DVF圖像進(jìn)行對(duì)比度拉伸和去噪預(yù)處理,增加DVF圖像的清晰度;在離線訓(xùn)練階段,使用大量腰椎樣本圖像來(lái)訓(xùn)練卷積神經(jīng)網(wǎng)絡(luò)分類(lèi)器;檢測(cè)時(shí),利用霍夫變換在二值化的DVF圖像中尋找到腰椎的邊角點(diǎn)以得到腰椎的角度參數(shù),再使用腰椎解剖統(tǒng)計(jì)數(shù)據(jù)獲得初始候選檢測(cè)區(qū)域的邊界框;之后按邊界框從經(jīng)預(yù)處理的DVF圖像中提取初始候選檢測(cè)區(qū)域送入卷積神經(jīng)網(wǎng)絡(luò)分類(lèi)器當(dāng)中獲得檢測(cè)結(jié)果。該方法在實(shí)驗(yàn)中表現(xiàn)出了十分高的腰椎檢測(cè)準(zhǔn)確率,能夠?qū)崿F(xiàn)對(duì)精度較嚴(yán)格的場(chǎng)景下的應(yīng)用。(2)針對(duì)當(dāng)前許多跟蹤算法在對(duì)腰椎進(jìn)行跟蹤時(shí)的魯棒性較差的問(wèn)題,提出了一種可在線更新的基于棧式自動(dòng)編碼機(jī)的腰椎跟蹤方法。在離線訓(xùn)練時(shí),獲得能夠表述通用物體的深層特征;在線跟蹤時(shí),以粒子濾波為框架,使用自動(dòng)編碼機(jī)獲得當(dāng)前幀的跟蹤結(jié)果;最后再對(duì)神經(jīng)網(wǎng)絡(luò)權(quán)值參數(shù)進(jìn)行在線更新。該方法有效提高了算法的魯棒性并減少了跟蹤漂移的可能,在實(shí)驗(yàn)中展現(xiàn)出了很強(qiáng)的腰椎識(shí)別能力。以上技術(shù)能夠在DVF影像對(duì)比度較低且較為模糊的情況下將部分腰椎檢測(cè)出來(lái),并展現(xiàn)出了很強(qiáng)的識(shí)別能力,在跟蹤過(guò)程中可準(zhǔn)確發(fā)現(xiàn)腰椎不穩(wěn)癥狀,可作為腰椎不穩(wěn)癥臨床診斷中非常有效的輔助手段。
[Abstract]:With the development of digital image technology and computer vision technology, The use of computer technology to process and analyze medical image data to assist doctors in diagnosing diseases has become increasingly popular. In this paper, an auxiliary diagnosis method of lumbar vertebrae instability is proposed, which is based on learning and tracking of lumbar vertebrae, which is processed and analyzed by digital video image of lumbar vertebrae (DVF). The main research work is as follows: (1) aiming at the problem that the initial status of lumbar vertebrae in the current lumbar tracking method needs manual labeling, A novel lumbar spine detection method based on convolution neural network is proposed. Firstly, the contrast stretching and denoising preprocessing of the original DVF image is carried out to increase the clarity of the DVF image. The convolutional neural network classifier is trained with a large number of lumbar vertebrae samples, and the angle parameters of the lumbar vertebrae are obtained by using Hoff transform in the binary DVF image to find the side corner of the lumbar vertebrae. The boundary frame of the initial candidate detection area was obtained by using lumbar anatomical statistical data. Then, according to the boundary frame, the initial candidate detection area is extracted from the pre-processed DVF image and sent to the convolutional neural network classifier to obtain the detection results. To solve the problem that many current tracking algorithms have poor robustness in tracking the lumbar vertebrae. In this paper, an on-line updating method of lumbar spine tracking based on stack automatic coding machine is proposed. When training offline, the deep features of common objects can be expressed, and the particle filter is used as the framework for on-line tracking. The tracking result of the current frame is obtained by using the automatic coding machine. Finally, the weights of the neural network are updated online. This method can effectively improve the robustness of the algorithm and reduce the possibility of tracking drift. These techniques can detect parts of lumbar vertebrae in the case of low contrast and blur of DVF image, and show strong recognition ability. The unstable symptoms of lumbar vertebrae can be found accurately in the process of tracking, and can be used as a very effective auxiliary method in the clinical diagnosis of lumbar instability.
【學(xué)位授予單位】：南京理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.41;R445;R681.5

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 Wang Guohong;Tan Shuncheng;Guan Chengbin;Wang Na;Liu Zhaolei;;Multiple model particle flter track-before-detect for range ambiguous radar[J];Chinese Journal of Aeronautics;2013年06期

，

本文編號(hào)：1587389