本文選題：注意缺陷多動(dòng)障礙 + 磁共振圖像��； 參考：《生物醫(yī)學(xué)工程學(xué)雜志》2017年01期

【摘要】：注意缺陷多動(dòng)障礙(ADHD)是一種高發(fā)于學(xué)齡兒童的行為障礙綜合癥。目前,ADHD的診斷主要依賴主觀方法,導(dǎo)致漏診率和誤診率較高�；诖�,本文提出一種基于卷積神經(jīng)網(wǎng)絡(luò)的ADHD客觀分類算法。首先,對(duì)腦部磁共振圖像(MRI)進(jìn)行頭骨剝離、高斯核平滑等預(yù)處理;其次,對(duì)大腦的右側(cè)尾狀核、左側(cè)楔前葉和左側(cè)額上回部位的MRI進(jìn)行粗分割;最后,利用3層卷積神經(jīng)網(wǎng)絡(luò)進(jìn)行分類。實(shí)驗(yàn)結(jié)果表明:1本文的算法能有效地對(duì)ADHD和正常人群進(jìn)行分類;2右側(cè)尾狀核和左側(cè)楔前葉的ADHD分類準(zhǔn)確率要高于ADHD-200全球競(jìng)賽中所有方法達(dá)到的ADHD最高分類準(zhǔn)確率(62.52%);3利用上述3個(gè)腦區(qū)對(duì)ADHD患者和正常人群進(jìn)行分類,其中右側(cè)尾狀核的分類準(zhǔn)確率最高。綜上所述,本文提出了一種利用粗分割和深度學(xué)習(xí)對(duì)ADHD患者和正常人群進(jìn)行分類的方法。本文方法分類準(zhǔn)確率高,計(jì)算量小,能較好地提取不明顯的圖像特征,改善了傳統(tǒng)MRI腦區(qū)精確分割耗時(shí)長(zhǎng)及復(fù)雜度高的缺點(diǎn),為ADHD的診斷提供了一種可參照的客觀方法。
[Abstract]:Attention deficit hyperactivity disorder (ADHD) is a behavioral disorder with high incidence in school age children.At present, the diagnosis of ADHD mainly depends on subjective method, which leads to high rate of missed diagnosis and misdiagnosis.Based on this, a ADHD objective classification algorithm based on convolution neural network is proposed.First, cranial dissection and smooth nucleus Gao Si were performed on MRI images of brain; secondly, MRI in the right caudate nucleus, left precuneiform lobe and left superior frontal gyrus were roughly segmented; finally, the brain was divided into two parts: the right caudate nucleus, the left anterior cuneate lobe and the left superior frontal gyrus.Three-layer convolution neural network is used to classify.The experimental results show that the ADHD classification accuracy of the right caudate nucleus and the left cuneate lobe in the ADHD and normal population can be effectively classified by the algorithm proposed in this paper, which is higher than the highest ADHD classification accuracy achieved by all the methods in the ADHD-200 Global Competition.The three brain regions mentioned above were used to classify the patients with ADHD and the normal population.The classification accuracy of the right caudate nucleus was the highest.To sum up, this paper proposes a method of classifying ADHD patients and normal population by rough segmentation and deep learning.This method has the advantages of high classification accuracy and less computation. It can extract image features that are not obvious, and improve the disadvantages of traditional MRI brain segmentation, such as long time consuming and high complexity. It provides a referential objective method for the diagnosis of ADHD.
【作者單位】： 南昌大學(xué)信息工程學(xué)院;
【基金】：國(guó)家自然科學(xué)基金(61463035) 中國(guó)博士后科學(xué)基金(2016M592117) 江西省科技廳科學(xué)基金(20161BAB202045,20151BAB213034) 江西省博士后科研擇優(yōu)項(xiàng)目(2016KY01) 江西省研究生創(chuàng)新專項(xiàng)基金(YC2016-S067)
【分類號(hào)】：TP183;R749.94

【參考文獻(xiàn)】

相關(guān)期刊論文 前5條

1 田換;覃曉;元昌安;劉致錦;;基于腦部MRI分割方法新進(jìn)展[J];廣西師范學(xué)院學(xué)報(bào)(自然科學(xué)版);2016年01期

2 李宇;黃明欣;于情;趙冰;;兒童青少年注意缺陷多動(dòng)障礙合并品行障礙的調(diào)查研究[J];國(guó)際精神病學(xué)雜志;2015年05期

3 吳靜;戴培山;趙亞麗;李玲;盛韓偉;李新春;;成人注意缺陷多動(dòng)障礙靜息態(tài)功能連接分析[J];中國(guó)醫(yī)學(xué)物理學(xué)雜志;2015年04期

4 鄒凌;張海琴;陸潔茹;;注意缺陷多動(dòng)障礙兒童的腦功能磁共振成像研究[J];國(guó)際生物醫(yī)學(xué)工程雜志;2012年05期

5 宋紅，林家瑞;用于醫(yī)學(xué)輔助診斷的神經(jīng)網(wǎng)絡(luò)方法的應(yīng)用研究[J];生物醫(yī)學(xué)工程學(xué)雜志;1996年02期

【共引文獻(xiàn)】

相關(guān)期刊論文 前10條

1 袁媛;史慧靜;夏志娟;張U，

本文編號(hào)：1734861