【摘要】：中醫(yī)望診是一種傳統(tǒng)的疾病診斷方式,其中舌像診斷是很重要的一個(gè)組成部分。舌像診斷主要分為舌面診斷和舌下靜脈診斷等,對(duì)于舌面診斷已經(jīng)有了許多針對(duì)性的研究,而且經(jīng)過(guò)多年的發(fā)展已經(jīng)產(chǎn)生了許多成果,但是關(guān)于舌下靜脈的研究還比較的少,有待進(jìn)一步的探討。本課題主要是在舌下靜脈的影像信息中,尋找對(duì)于疾病分析有潛在價(jià)值、有指導(dǎo)意義的特征,并根據(jù)這些特征來(lái)進(jìn)行健康與疾病的分析。具體研究?jī)?nèi)容包括:圖像的采集與預(yù)處理、舌下靜脈血管的分割、特征選擇與優(yōu)化以及基于舌下靜脈血管特征的聚類分析。通過(guò)與醫(yī)院合作,采集到舌下靜脈圖像的樣本,同時(shí)得到對(duì)應(yīng)樣本的各類生化指標(biāo)以及醫(yī)生所做出的健康狀況判定結(jié)果,并把這些信息作為該樣本的疾病標(biāo)簽。截止目前已采集含標(biāo)簽樣本兩千多例。本課題選取其中采集樣本較多的類別,如肺癌、高血壓、乳腺癌、腎病、失眠、糖尿病、胃炎、腫瘤以及健康樣本等作為數(shù)據(jù)集。對(duì)于采集到的原始圖像采用一種基于多項(xiàng)式的校正算法進(jìn)行顏色校正,并提出了一種基于HSI與LUV顏色空間像素生長(zhǎng)法的交互式分割算法進(jìn)行舌下靜脈圖像的分割�；�1000幅分割后的舌下靜脈圖像構(gòu)建了舌下靜脈的顏色空間,并通過(guò)k-means聚類方法獲得了舌下靜脈基于該顏色空間的顏色特征;同時(shí),根據(jù)分割的舌下靜脈提取了基于RGB和HSV顏色空間下的顏色特征,以及舌下靜脈長(zhǎng)度、寬度以及長(zhǎng)寬比等幾何特征,并通過(guò)不同的特征組合進(jìn)行了特征向量的優(yōu)化。利用舌下靜脈特征向量對(duì)采集的圖像樣本進(jìn)行了聚類分析,主要進(jìn)行了健康與幾種疾病的二分類,通過(guò)不同的二分類算法的比較選擇了SVM分類器算法進(jìn)行二分類,最后分類結(jié)果的平均正確度為80.88%,而對(duì)于幾種典型的疾病如2型糖尿病與健康的分類精度可以達(dá)到89.34%,這說(shuō)明舌下靜脈這一特征對(duì)于疾病分析確實(shí)有意義。實(shí)現(xiàn)了SVM決策樹的多分類器,對(duì)于健康、失眠和乳腺癌三類的分類準(zhǔn)確度可以達(dá)到70.19%,說(shuō)明SVM決策樹算法對(duì)于多分類問(wèn)題可以有比較好的效果,并且證明舌下靜脈對(duì)于疾病的診斷分析是有意義的。
[Abstract]:Traditional Chinese medicine diagnosis is a traditional way of disease diagnosis, among which tongue image diagnosis is an important part. Tongue image diagnosis is mainly divided into tongue surface diagnosis and sublingual vein diagnosis. There have been many targeted studies on tongue surface diagnosis, and after years of development, many achievements have been produced, but the research on sublingual vein is still relatively few. Further discussion is needed. In this paper, we mainly look for the potential and instructive features of disease analysis in the image information of sublingual vein, and analyze the health and disease according to these characteristics. The specific research contents include: image acquisition and preprocessing, sublingual vein segmentation, feature selection and optimization, and clustering analysis based on sublingual vein features. By cooperating with the hospital, the samples of the sublingual vein images were collected, and the biochemical indexes of the corresponding samples and the results of the doctor's health assessment were obtained, and the information was used as the disease label of the sample. Up to now, more than 2,000 samples containing labels have been collected. In this study, we selected a large number of samples, such as lung cancer, hypertension, breast cancer, nephropathy, insomnia, diabetes, gastritis, tumor and health samples as data sets. A polynomial correction algorithm is used to correct the original image and an interactive segmentation algorithm based on HSI and LUV color space pixel growth method is proposed to segment the sublingual vein image. The color space of the sublingual vein is constructed based on 1000 segmented images of the sublingual vein, and the color feature of the sublingual vein based on the color space is obtained by k-means clustering. Based on the segmented sublingual veins, the color features based on RGB and HSV color spaces, as well as the geometric features such as the length, width and aspect ratio of the sublingual veins are extracted, and the feature vectors are optimized by different feature combinations. The sublingual vein feature vector is used to cluster the collected image samples. The two classification methods of health and several diseases are mainly carried out. The SVM classifier algorithm is selected to do the two classification by comparing different two classification algorithms. The average accuracy of the classification results is 80.88, while the classification accuracy of several typical diseases such as type 2 diabetes and health can reach 89.34, which indicates that the sublingual vein is of great significance for disease analysis. The classification accuracy of SVM decision tree can reach 70.19 for health, insomnia and breast cancer. It shows that the SVM decision tree algorithm has good effect on multi-classification problem. It also proves that the sublingual vein is of significance in the diagnosis and analysis of the disease.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：R241;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 于淼;閆子飛;王寬全;李乃民;;一種近紅外舌下靜脈提取方法[J];智能系統(tǒng)學(xué)報(bào);2008年04期

2 趙進(jìn);杜克莘;孫曉明;劉新領(lǐng);趙峰;;機(jī)能實(shí)驗(yàn)教學(xué)中舌下靜脈血管注射方法的改進(jìn)[J];西北醫(yī)學(xué)教育;2010年04期

3 王榕平;陳利銘;林寶桑;林民生;童國(guó)tT;;1463例正常人舌下靜脈觀察分析[J];福建中醫(yī)藥;1986年05期

4 張平,劉秀麗,杜希哲,劉偉,張?zhí)K麗,王銳;西安地區(qū)60歲以上老年人舌體粘膜和舌下靜脈的觀察[J];西安醫(yī)科大學(xué)學(xué)報(bào);1997年01期

5 張學(xué)森;秦鈺萍;姜大春;李德生;;舌下靜脈分度對(duì)冠心病的預(yù)測(cè)價(jià)值[J];西南國(guó)防醫(yī)藥;2014年08期

6 傅家武,羅小寧;望診舌下靜脈變化對(duì)冠心病治療的觀察[J];廣州醫(yī)藥;2000年04期

7 楊江存,王欽和;肺氣腫 肺心病舌下靜脈臨床觀察[J];福建中醫(yī)藥;2004年01期

8 姜波濤;;探討一種新的大鼠取血方法——舌下靜脈采血[J];臨床和實(shí)驗(yàn)醫(yī)學(xué)雜志;2011年05期

9 蘇干伸;;觀察舌下靜脈瘤狀突起辯治慢阻肺急性加重期46例[J];海南醫(yī)學(xué)院學(xué)報(bào);2011年07期

10 丁喜艷;劉順益;;原發(fā)性高血壓病中醫(yī)證型與舌下靜脈關(guān)系的臨床觀察[J];遼寧中醫(yī)雜志;2008年06期

相關(guān)會(huì)議論文 前3條

1 閆子飛;李乃民;張大鵬;王寬全;賈丹兵;于淼;;近紅外舌下圖像中舌下靜脈提取方法研究[A];第二次全國(guó)中西醫(yī)結(jié)合診斷學(xué)術(shù)研討會(huì)論文集[C];2008年

2 劉興忠;史學(xué)茂;譚京海;高明英;張兆航;史達(dá);;糖尿病患者舌下靜脈與血瘀證相關(guān)意義的研究[A];內(nèi)分泌代謝病中西醫(yī)結(jié)合研究——臨床與基礎(chǔ)[C];2010年

3 秦吉華;姜玉成;李蘭;王莉;王萍;;2100例正常人舌下靜脈及舌面PH值調(diào)查分析(摘要)[A];第一屆全國(guó)中西醫(yī)結(jié)合診斷學(xué)術(shù)會(huì)議論文選集[C];2006年

相關(guān)重要報(bào)紙文章 前3條

1 陸基宗;暈動(dòng)癥的防治[N];華東旅游報(bào);2003年

2 上海曙光醫(yī)院 蔣健 教授;“兩種處方”益處多(七)[N];上海中醫(yī)藥報(bào);2013年

3 上海中醫(yī)藥大學(xué)附屬曙光醫(yī)院內(nèi)科 蔣健 教授;閉經(jīng)治從多基線(下)[N];上海中醫(yī)藥報(bào);2011年

相關(guān)碩士學(xué)位論文 前2條

1 李偉;舌下靜脈血管分割及其病理特征分析研究[D];哈爾濱工業(yè)大學(xué);2016年

2 劉順益;原發(fā)性高血壓病中醫(yī)證型與舌下靜脈相關(guān)性的臨床研究[D];福建中醫(yī)學(xué)院;2005年

，

本文編號(hào)：2264923