北京生物醫(yī)學(xué)工程

MRI大腦圖像灰質(zhì)與白質(zhì)的分割

Segmentation for brain grey matter and white matter of a MRI brain image

作者：陳亮亮

單位：陳亮亮。E-mail:[email protected]

關(guān)鍵詞： MRI大腦圖像；小波變換；大腦灰質(zhì)；大腦白質(zhì)；閾值分割；多尺度

分類號(hào)：

出版年·卷·期（頁(yè)碼）：2013·32·5（519-523）

摘要：

目的利用小波變換對(duì)MRI大腦圖像進(jìn)行多尺度下的自動(dòng)閾值處理，實(shí)現(xiàn)大腦灰質(zhì)與白質(zhì)的分割。方法首先將MRI大腦圖像去噪，接著進(jìn)行預(yù)分割以去除非腦組織，余下的腦實(shí)質(zhì)部分選擇sym4小波函數(shù)對(duì)其一維直方圖信號(hào)進(jìn)行不同層次的小波系數(shù)的分解，實(shí)現(xiàn)多尺度下的自動(dòng)閾值分割，從而提取腦實(shí)質(zhì)中的灰質(zhì)和白質(zhì)。經(jīng)過(guò)圖像的后處理，以錯(cuò)誤分割的百分比作為分割結(jié)果的評(píng)判標(biāo)準(zhǔn)。結(jié)果該方法能正確分離白質(zhì)和灰質(zhì)，對(duì)多幅MRI大腦圖像重復(fù)實(shí)驗(yàn)，計(jì)算得到的像素差異百分比不超過(guò)3.7%，錯(cuò)誤分割的百分比在允許范圍內(nèi)。結(jié)論該方法對(duì)于MRI大腦的灰白質(zhì)分割具有一定的有效性，且操作簡(jiǎn)單、快速，分割效果理想。但由于小波閾值分割法的單一性，分割過(guò)程仍有人工干涉，分割結(jié)果也存在一定的過(guò)分割現(xiàn)象，應(yīng)在此方法的基礎(chǔ)上進(jìn)一步研究和完善。

Objective To realize the segmentation of brain grey matter and white matter of a MRI brain image accurately by means of wavelet transformation which could automatically gain the threshold with multi-scale decomposition. Methods Firstly，The MRI brain image was denoised and pre-segmented to remove non-brain tissue. Then one-dimensional histogram signal of the rest brain tissue was decomposed by different levels of wavelet coefficients to realize automatically threshold segmentation under multi-scale，thus the brain grey matter and white matter were extracted. Finally，the results were evaluated by the percentage of error segmentation after the post-treatment. Results The expriment results showed that brain grey matter and white matter were correctly segmented，and the max percentage of error segmentation was 3.7%，which was within the allowable range. Conclusions The method is effective，easy and fast in segmentation for brain grey matter and white matter of a MRI image. However，due to the simplicity of the threshold segmentation with wavelet transformation，the whole process does not work without human intervention and there is some over-segmentation in the results. Further study and improvement should be made based on this method.

參考文獻(xiàn)：

［1］余學(xué)飛.基于模糊理論的醫(yī)學(xué)圖像分割算法研究［D］.廣州：南方醫(yī)科大學(xué)，2009.
Yu Xuefei.Research about algorithm based on fuzzy theory for medical image segmentation［D］. Guangzhou:Southern Medical University,2009.
［2］Lipton Richard J. DNA Solution of Hard Computational Problems［J］. Science,1995， 268 (4):542-545.
［3］Pemmaraju S，Mitra S，Shieh Y，et al. Multiresolution waveletdecomposition and neur o-fuzzy clustering for segmentation of radiographic images［J］. Proceedings of the Eighth Annual IEEE Symposium on Computer-Based Med-I cal Systems (CBMS. 95). 1995:142-149.
［4］Olivo JC．Automatic threshold selection using the Wavelet transform． CVGIP-GMIP，1994，56(3)：205-218.
［5］邢凡，樊瑜瑾.基于小波變換多閾值彩色鐵譜圖像的分割方法［J］.潤(rùn)滑與密封，2008,33(7):69-72.
Xing Fan，F(xiàn)an Yujin. Multi-threshould segmentation method based on wavelet transformation for color ferrography image［J］. Lubrication and Sealing，2008,33(7):69-72.
［6］何軍寶.腦部核磁共振圖像的模糊均值抗噪分割算法［D］.武漢：華中科技大學(xué)，2006.
He Junbao. Fuzzy c-means with entinoise segmentation algorithm for MRI brain image［D］. Wuhan:Huazhong University of Science and Technology,2006.
［7］Rajaqakse JC. Statistical approach to segmentation of single-channel cerebral M R images［J］. IEEE Trans Med Imaging，1997，16 (2):176-186.
［8］王建中.核磁共振腦圖像分割方法的研究［D］.長(zhǎng)春：東北師范大學(xué),2007.
Wang Jianzhong. Research on methods for segmentation of MRI brain images［D］. Changchun:Northeast Normal University,2007.
［9］聶生東,章魯,顧順德,等. 磁共振圖像的分割［J］. 國(guó)外醫(yī)學(xué)生物醫(yī)學(xué)工程分冊(cè),1999,22(6):23-25.
Nie Shengdong，Zhang Lu，Gu Shunde，et al. Segmentation of brain images［J］. Foreign Medical Sciences:Biomedical Engineering，1999，22(6):23-25.
［10］劉靜. 基于小波變換的圖像分割技術(shù)研究［D］. 濟(jì)南：山東大學(xué),2005.
Liu Jing. Reaseach on teconology for images segmentation based on wavelet transformation［D］. Jinan:Shandong University,2005.
［11］Reddick WE,Glass JO，Cook EN,et al.Automated segmentation and classification of multi spectral magnetic images using artificia neural networks［J］. IEEE Trans Med Imaging,1997,16(6):911-918.
［12］Li Bai， Yihui Liu， Dorothee Auer， Paul Morgan. Automatic Segmentation of Putamen from Brain MRI［J］. Technology & Automation,2001,19(8):679-698.

服務(wù)與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請(qǐng)登錄！點(diǎn)此登錄

51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频