北京生物醫(yī)學(xué)工程

基于紋理分析的阿爾茨海默癥及輕度認(rèn)知功能障礙的分類研究

Classification of Alzheimer disease and mild cognitive impairment from normal controls based on texture analysis

作者：劉衛(wèi)芳夏翃王旭周震

單位：                      首都醫(yī)科大學(xué)生物醫(yī)學(xué)工程學(xué)院（北京100069）        

關(guān)鍵詞：阿爾茨海默癥；輕度認(rèn)知功能障礙；三維紋理分析；胼胝體；分類識別

分類號：

出版年·卷·期（頁碼）：2014·33·6（609-613）

摘要：

目的利用腦MR圖像中胼胝體的三維紋理特征對阿爾茨海默癥患者（Alzheimer disease, AD）及輕度認(rèn)知功能障礙（mild cognitive impairment, MCI）患者進(jìn)行分類識別，以探索AD 早期診斷新途徑。方法選取AD患者、MCI患者及健康對照者各18例，采用灰度共生矩陣和游程長矩陣提取每位受試者胼胝體部位的三維紋理特征。通過篩選得到的紋理特征參量，利用BP神經(jīng)網(wǎng)絡(luò)建立識別模型，對AD患者、MCI患者和健康對照者進(jìn)行分類識別，并對采用主成分分析、線性判別分析和非線性判別分析3種方法得到的識別結(jié)果進(jìn)行比較。結(jié)果使用神經(jīng)網(wǎng)絡(luò)模型的非線性判別分析的分類識別正確率最高。結(jié)論利用三維紋理特征的神經(jīng)網(wǎng)絡(luò)模型可分類識別早期AD患者及MCI患者。

Objective This study investigated three-dimensional (3D) texture as a possible diagnostic marker of Alzheimer disease. Methods T1-weighted MR images were obtained from 18 AD patients, 18 MCI patients and 18 age and gender-matched normal controls. 3D texture features of the corpus callosum were extracted from the gray level co-occurrence matrix and run length matrix. The texture features that existed significant differences among the three groups were used as features in a classification procedure. Results The classification accuracy of nonlinear discriminant analysis was the highest with neural network model. Conclusions Three-dimensional texture can recognize the pathological changes of corpus callosum in patients with AD and MCI, and might be a useful aid in AD diagnosis.

參考文獻(xiàn)：

服務(wù)與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請登錄！點此登錄

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