本文關鍵詞： 食管癌 圖像分型 數據挖掘技術 計算機輔助診斷 分類模型評估　出處：《新疆醫(yī)科大學》2017年碩士論文　論文類型：學位論文

【摘要】：目的:本研究針對食管X線圖像,研究數據挖掘技術在新疆哈薩克族食管癌X線圖像分型中的應用,旨在為放射科醫(yī)生的診斷決策提供具有實際參考價值的輔助信息,提高新疆哈薩克族食管癌診斷的準確率和效率。方法:利用MATLAB圖像處理軟件,手動選取食管X射線圖像的感興趣區(qū)域,對其進行中值濾波去噪和直方圖均衡化的預處理以改善圖像質量;提取基于灰度直方圖、灰度共生矩陣、灰度梯度共生矩陣和Tamura紋理特征;采用PCA特征選擇法和AUC面積約束特征篩選法對所提取到的特征進行優(yōu)化選擇,剔除冗余特征量;使用KNN、RF、SVM和Logistic回歸分類器,通過10折交叉驗證,對正常食管和早期食管癌,潰瘍型、縮窄型、蕈傘型中晚期食管癌食管X線圖像進行分類研究;利用參數評估、ROC和Calibration曲線對各分類模型性能進行評價。結果:正常食管和早期食管癌分型:a)PCA特征選擇:提取到8個主成分,在PCA特征集下KNN(K=1)、RF、SVM和Logistic回歸分類器對正常食管分類準確率為91.43%、80.38%、89.26%和95.29%,對早期食管癌分類準確率為94.29%、84.67%、92.65%和97.14%。b)AUC面積約束特征篩選:篩選到18個AUC值大于0.75的特征量,在AUC特征集下KNN(K=3)、RF、SVM和Logistic回歸分類器對正常食管分類準確率88.60%、78.57%、92.96%和86.37%,對早期食管癌分類準確率為86.50%、82.65%、94.29%和85.86%。潰瘍型、縮窄型、蕈傘型食管癌分型:a)PCA特征選擇:提取到7個主成分,在PCA特征集下KNN(K=1)、RF、SVM和Logistic回歸分類器對潰瘍型食管癌分類準確率為88.13%、87.32%、93.67%和94.56%,對縮窄型食管癌分類準確率為87.90%、88.64%、92.67%和94.30%,對蕈傘型食管癌分類準確率為86.88%、85.12%、91.54%和93.36%。b)AUC面積約束特征篩選:篩選到14個AUC值大于0.75的特征量,在AUC特征集下KNN(K=3)、RF、SVM和Logistic回歸分類器對潰瘍型食管癌分類準確率為83.45%、87.34%、94.45%和95.68%,對縮窄型食管癌分類準確率為84.75%、83.36%、91.33%和94.05%,對蕈傘型食管癌分類準確率為83.55%、79.42%、90.58%和91.36%。結論:正常食管和早期食管癌分型:PCA特征選擇法優(yōu)于AUC面積約束特征篩選法;早期食管癌分類效果優(yōu)于正常食管;SVM分類器分類效果最佳。潰瘍型、縮窄型、蕈傘型食管癌分型:PCA特征選擇法和AUC面積約束特征篩選法均適用于中晚期食管癌;潰瘍型食管癌分類效果最好;Logistic回歸和SVM分類器更適合于中晚期食管癌的分型;綜合早期和中晚期食管癌分型結果,PCA特征選擇和SVM分類器最適用于食管癌分型。本研究結果能為放射科醫(yī)生對食管癌的診斷提供有價值的參考意見,尤其是對早期食管癌的診斷,為開發(fā)面向臨床的新疆哈薩克族食管癌計算機輔助診斷系統(tǒng)奠定了基礎。
[Abstract]:Objective: to study the application of data mining technology in the classification of esophageal carcinoma in Xinjiang Kazak nationality. The purpose of this study was to provide assistant information with practical reference value for radiologists to make diagnosis decision, and to improve the accuracy and efficiency of diagnosis of esophageal cancer in Kazak nationality in Xinjiang. Methods: MATLAB image processing software was used. In order to improve the image quality, the region of interest of esophageal X-ray image is manually selected, and the median filter denoising and histogram equalization are used to improve the image quality. Extraction based on gray histogram, gray co-occurrence matrix, gray-level gradient co-occurrence matrix and Tamura texture features; The PCA feature selection method and the AUC area-constrained feature selection method are used to optimize the selection of the extracted features, and the redundant feature quantities are eliminated. By using Logistic regression classifier and Logistic regression classifier, normal esophagus, early esophageal carcinoma, ulcerative type and constriction type were examined by 10 fold cross validation. The esophageal X-ray images of middle and late stage esophageal carcinoma of mushroom type were studied. Using parameter evaluation. ROC and Calibration curves were used to evaluate the performance of each classification model. Results: eight principal components were extracted from normal esophagus and early esophageal carcinoma. Under the PCA feature set, the accuracy of PCA and Logistic regression classifier for normal esophagus classification was 91.43% and 80.38% respectively. The accuracy of classification of early esophageal carcinoma in 89.26% and 95.29 was 94. 29% and 84. 67%. 92.65% and 97.14. The area constraint characteristics of AUC were screened: 18 characteristic quantities with AUC value greater than 0.75 were screened, and the RF was obtained under the AUC feature set. The accuracy of SVM and Logistic regression classifier for normal esophageal classification was 88.60% and 92.96% and 86.37% respectively. The accuracy of classification for early esophageal carcinoma was 86.50%, 82.65% and 85.86%, respectively. The selection of PCA features for the classification of mushroom esophageal carcinoma: seven principal components were extracted, and the RF of KNNN was extracted under the PCA feature set. The accuracy of SVM and Logistic regression classifier in the classification of ulcerative esophageal carcinoma was 88.13 ~ 87.32 ~ 93.67% and 94.56% respectively. The accuracy of classification of constricted esophageal carcinoma was 87.90% and 94.30%, 86.8888% and 85.12% respectively. 91.54% and 93.36. area restriction feature screening of AUC: 14 characteristic quantities with AUC value greater than 0.75 were screened, and the RF of KNNs was found to be higher than 0.75 under the AUC feature set. The accuracy of SVM and Logistic regression classifier in the classification of ulcerative esophageal carcinoma was 83.45% and 95.68% respectively. The accuracy of classification of constricted esophageal carcinoma was 91.33% and 94.05%, and that of mushroom carcinoma was 83.55% and 79.42%, respectively. Conclusion: the classification of normal esophagus and early esophageal carcinoma is superior to that of AUC. The classification effect of early esophageal carcinoma was better than that of normal esophagus. The results of SVM classifier were the best. The ulcerative type, constriction type, mushroom type esophageal carcinoma typing: PCA: 1. The AUC area constraint feature selection method were all suitable for the middle and late stage esophageal carcinoma. The classification effect of ulcerative esophageal carcinoma was the best. Logistic regression and SVM classifier were more suitable for classification of advanced esophageal carcinoma. Combined with the early and late esophageal cancer classification results, the SVM classifier and PCA feature selection are the most suitable for the classification of esophageal cancer. The results of this study can provide valuable reference for radiologists in the diagnosis of esophageal cancer. Especially, the diagnosis of early esophageal cancer lays a foundation for the development of the computer aided diagnosis system for Xinjiang Kazak esophageal carcinoma.
【學位授予單位】：新疆醫(yī)科大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：R735.1

【相似文獻】

相關期刊論文 前10條

1 周旭東,陳紅梅;新疆哈薩克族食管癌136例臨床分析[J];中國內鏡雜志;2000年03期

2 伊力亞爾·夏合丁;李卉;霍奇;陳艷;余亮;龐作良;王洪江;周新;趙學信;李惠武;;基質金屬蛋白酶-7在哈薩克族食管癌中的表達及其意義[J];地方病通報;2008年04期

3 張力為;伊力亞爾·夏合丁;吳明拜;王艷萍;張鑄;;MTHFR基因1298 A→C多態(tài)與新疆哈薩克族食管癌風險關系的研究[J];中華腫瘤防治雜志;2008年17期

4 張慧霞;陳艷;尹東;鄧彥超;馬彥清;居來提;;新疆哈薩克族食管癌危險因素的探討[J];現(xiàn)代預防醫(yī)學;2009年10期

5 劉真群;陳艷;;伊犁地區(qū)哈薩克族食管癌高低發(fā)區(qū)人體內外環(huán)境化學元素含量分析[J];新疆醫(yī)科大學學報;2012年11期

6 李婧;秦江;;新疆哈薩克族食管癌風險的預測[J];世界華人消化雜志;2014年10期

7 盧慧;楊磊;李鋒;秦江梅;王秀梅;李冬妹;譚曉華;何玲;;細胞色素P4501A1基因多態(tài)性與哈薩克族食管癌的易感性研究[J];農墾醫(yī)學;2006年02期

8 王秀梅;杰恩斯;馬彥清;陳波;郭小進;阿力木太;哈那提;李鋒;楊磊;秦江梅;;新疆哈薩克族食管癌危險因素病例對照研究[J];中國公共衛(wèi)生;2007年06期

9 王秀梅;張衛(wèi)群;陳波;何玲;阿力木太;哈那提;李鋒;楊磊;秦江梅;;MTHFR基因多態(tài)性與哈薩克族食管癌易感性[J];中國公共衛(wèi)生;2007年08期

10 陳志剛;楊軍;周婷;周迪;李宏;陳波;秦江梅;;抗核抗體在漢族、哈薩克族食管癌患者體內的表達[J];山東醫(yī)藥;2008年41期

相關會議論文 前3條

1 王靜雄;張月明;陳堅;;維生素A、E營養(yǎng)及免疫機能與哈薩克族食管癌[A];中國營養(yǎng)學會營養(yǎng)與腫瘤學術會議論文摘要匯編[C];1990年

2 張力為;伊力亞爾·夏合丁;王艷萍;吳明拜;張鑄;;亞甲基四氫葉酸還原酶基因1298 A→C多態(tài)與新疆哈薩克族食管癌風險關聯(lián)[A];全國腫瘤流行病學和腫瘤病因學學術會議論文集[C];2007年

3 李秀梅;王洪江;陳艷;李卉;龐作良;張麗萍;李惠武;;新疆哈薩克族食管癌中Survivin表達上調對細胞凋亡相關基因的影響研究[A];“細胞活動 生命活力”——中國細胞生物學學會全體會員代表大會暨第十二次學術大會論文摘要集[C];2011年

相關博士學位論文 前5條

1 張力為;哈薩克族食管癌與易感基因多態(tài)關系及免疫相關因素研究[D];新疆醫(yī)科大學;2006年

2 劉玲;新疆哈薩克族食管癌早期相關基因甲基化分析及功能研究[D];新疆醫(yī)科大學;2012年

3 張昌明;新疆漢族、維吾爾族及哈薩克族食管癌血清蛋白質指紋圖譜研究[D];新疆醫(yī)科大學;2010年

4 盧曉梅;哈薩克族食管癌發(fā)病學分子機制和食管癌細胞干預的探討[D];新疆醫(yī)科大學;2005年

5 陳曉;哈薩克族食管癌發(fā)病的分子生物學機制研究[D];新疆醫(yī)科大學;2002年

相關碩士學位論文 前10條

1 楊芳;新疆哈薩克族食管癌X射線圖像計算機輔助診斷技術的研究[D];新疆醫(yī)科大學;2016年

2 尹鈺;葉酸及相關指標與哈薩克族食管癌關系的病例—對照研究[D];新疆醫(yī)科大學;2016年

3 甄玉潔;葉酸代謝等相關基因甲基化與哈薩克族食管癌及預后關系的研究[D];新疆醫(yī)科大學;2017年

4 李卉;消化道腫瘤相關基因在哈薩克族食管癌中表達改變的研究[D];新疆醫(yī)科大學;2007年

5 王艷萍;葉酸和亞甲基四氫葉酸還原酶多態(tài)與哈薩克族食管癌關系的實驗研究[D];新疆醫(yī)科大學;2007年

6 崔麗;新疆哈薩克族食管癌患者血清差異蛋白質篩選及蛋白質譜檢測[D];新疆醫(yī)科大學;2013年

7 劉真群;新疆伊犁地區(qū)哈薩克族食管癌環(huán)境相關因素的探析[D];新疆醫(yī)科大學;2013年

8 馬師琦;二十年前后新疆哈薩克族食管癌發(fā)病狀況對比[D];新疆醫(yī)科大學;2013年

9 周峰;新疆哈薩克族食管癌患者放化療前后血清蛋白質組學特征差異分析[D];新疆醫(yī)科大學;2011年

10 李婧;新疆哈薩克族食管癌風險預測研究[D];石河子大學;2014年

，

本文編號：1480318