發(fā)布時(shí)間：2018-01-24 05:27

  本文關(guān)鍵詞： 腦部腫瘤 磁共振圖像 分割 高斯混合模型特征 決策樹　出處：《控制工程》2017年08期 　論文類型：期刊論文

【摘要】：磁共振(MR)圖像提供了大量用于醫(yī)療檢查的信息。精確魯棒的腦部MR圖像分割、特征提取和分類對于臨床診斷腫瘤是非常重要的。提出一種新的基于腦部MR圖像的腫瘤診斷方法。首先,通過多閾值分割形態(tài)學(xué)操作檢測圖像的畸形區(qū)域,然后,提取用于分類的高斯混合模型(GMM)特征,最后,利用決策樹分類器對腫瘤圖像類型進(jìn)行分類。整個(gè)分類過程分為訓(xùn)練和測試2個(gè)階段,訓(xùn)練階段提取腫瘤圖像和非腫瘤圖像不同的特征,在測試階段基于知識庫進(jìn)行腫瘤和非腫瘤分類。使用準(zhǔn)確度、誤報(bào)率和漏檢率3個(gè)性能指標(biāo)對算法進(jìn)行評估,實(shí)驗(yàn)結(jié)果表明,分類準(zhǔn)確度可達(dá)91.18%-94.11%,誤報(bào)率和漏檢率在2.94%-4.41%范圍內(nèi),可以有助于更好的腦部腫瘤診斷。
[Abstract]:Magnetic resonance (MR) images provide a lot of information for medical examination. Brain MR image accurate and robust segmentation, feature extraction and classification is very important for the clinical diagnosis of the tumor. Propose a new tumor diagnosis method based on MR image of the brain. First of all, the deformed regions, threshold segmentation morphology detection image then, to extract the Gauss mixture model classification (GMM) characteristics, finally, the classification of tumor image types by using decision tree classifier. The classification process is divided into 2 stages of training and testing, the extraction of tumor images and non tumor images with different characteristics of the training stage, tumor and non tumor classification in the testing stage based on the use of the knowledge base. The accuracy, false positive rate and false negative rate of 3 indicators to evaluate the performance of the algorithm, the experimental results show that the classification accuracy of 91.18%-94.11%, false alarm rate and false negative rate in 2.94% Within the range of -4.41%, it can help better diagnosis of brain tumors.

【作者單位】： 包頭醫(yī)學(xué)院計(jì)算機(jī)科學(xué)與技術(shù)系;西南科技大學(xué)國防科技學(xué)院;
【基金】：內(nèi)蒙古自治區(qū)高等學(xué)�？茖W(xué)研究項(xiàng)目(NJZY13252) 包頭醫(yī)學(xué)院科學(xué)研究基金項(xiàng)目(BYJJ-QM201657)
【分類號】：R730.44;TP391.41
【正文快照】： 1引言 磁共振(MRI)在醫(yī)療領(lǐng)域起著至關(guān)重要作用,波場不均勻性引起的強(qiáng)度變化。不均勻性,特別是 為醫(yī)療診斷提供定性、定量和準(zhǔn)確信息。其在許多應(yīng)用領(lǐng)域比其他模態(tài)醫(yī)療成像技術(shù)更具優(yōu)勢,如在心血管、神經(jīng)、肌肉疾病診斷,特別是腦成像領(lǐng)域。然而,多數(shù)MR圖像處理的問題起因于B，

本文編號：1459280