中华肿瘤杂志
中華腫瘤雜誌
중화종류잡지
CHINESE JOURNAL OF ONCOLOGY
2014年
8期
582-586
,共5页
张海鹏%付彤%张志茹%范志民%郑超%韩冰
張海鵬%付彤%張誌茹%範誌民%鄭超%韓冰
장해붕%부동%장지여%범지민%정초%한빙
乳腺肿瘤%光谱分析,拉曼%支持向量机-递归特征消去法%诊断,鉴别
乳腺腫瘤%光譜分析,拉曼%支持嚮量機-遞歸特徵消去法%診斷,鑒彆
유선종류%광보분석,랍만%지지향량궤-체귀특정소거법%진단,감별
Breast neoplasms%Spectrum analysis,raman%Support vector machine-recursive feature elimination%Diagnosis,differential
目的 探讨支持向量机-递归特征消去法(SVM-RFE)分析拉曼光谱在乳腺良恶性疾病鉴别诊断中的价值.方法 收集168例手术患者的新鲜乳腺组织标本,其中正常组织51例,良性病变组织66例,恶性病变组织51例,均进行拉曼光谱检测,SVM-RFE方法处理数据,构建模型,马氏距离法判断数据处理方法的优劣.结果 共得到1 800个拉曼光谱,良性和恶性乳腺组织的特征峰出现在1 281、1 341、1 381、1 417、1 465、1 530和1 637 cm-1处,而正常乳腺组织的特征峰出现在1 078、1 267、1 301、1 437、1 653和1 743 cm-1处.良性和恶性乳腺组织的主要不同集中在1 340和1 480cm-1处.SVM-RFE判断正常和恶性乳腺组织的正确率分别为100.0％和95.0％,判断良性乳腺组织的正确率为93.0％.结论 正常、良性与恶性病变组织的拉曼光谱存在显著差异,SVM-RFE可以用来构建鉴别乳腺病变性质的模型.
目的 探討支持嚮量機-遞歸特徵消去法(SVM-RFE)分析拉曼光譜在乳腺良噁性疾病鑒彆診斷中的價值.方法 收集168例手術患者的新鮮乳腺組織標本,其中正常組織51例,良性病變組織66例,噁性病變組織51例,均進行拉曼光譜檢測,SVM-RFE方法處理數據,構建模型,馬氏距離法判斷數據處理方法的優劣.結果 共得到1 800箇拉曼光譜,良性和噁性乳腺組織的特徵峰齣現在1 281、1 341、1 381、1 417、1 465、1 530和1 637 cm-1處,而正常乳腺組織的特徵峰齣現在1 078、1 267、1 301、1 437、1 653和1 743 cm-1處.良性和噁性乳腺組織的主要不同集中在1 340和1 480cm-1處.SVM-RFE判斷正常和噁性乳腺組織的正確率分彆為100.0％和95.0％,判斷良性乳腺組織的正確率為93.0％.結論 正常、良性與噁性病變組織的拉曼光譜存在顯著差異,SVM-RFE可以用來構建鑒彆乳腺病變性質的模型.
목적 탐토지지향량궤-체귀특정소거법(SVM-RFE)분석랍만광보재유선량악성질병감별진단중적개치.방법 수집168례수술환자적신선유선조직표본,기중정상조직51례,량성병변조직66례,악성병변조직51례,균진행랍만광보검측,SVM-RFE방법처리수거,구건모형,마씨거리법판단수거처리방법적우렬.결과 공득도1 800개랍만광보,량성화악성유선조직적특정봉출현재1 281、1 341、1 381、1 417、1 465、1 530화1 637 cm-1처,이정상유선조직적특정봉출현재1 078、1 267、1 301、1 437、1 653화1 743 cm-1처.량성화악성유선조직적주요불동집중재1 340화1 480cm-1처.SVM-RFE판단정상화악성유선조직적정학솔분별위100.0％화95.0％,판단량성유선조직적정학솔위93.0％.결론 정상、량성여악성병변조직적랍만광보존재현저차이,SVM-RFE가이용래구건감별유선병변성질적모형.
Objective To explore the value of application of support vector machine-recursive feature elimination (SVM-RFE) method in Raman spectroscopy for differential diagnosis of benign and malignant breast diseases.Methods Fresh breast tissue samples of 168 patients (all female; ages 22-75) were obtained by routine surgical resection from May 2011 to May 2012 at the Department of Breast Surgery,the First Hospital of Jilin University.Among them,there were 51 normal tissues,66 benign and 51 malignant breast lesions.All the specimens were assessed by Raman spectroscopy,and the SVM-RFE algorithm was used to process the data and build the mathematical model.Mahalanobis distance and spectral residuals were used as discriminating criteria to evaluate this data-processing method.Results 1 800 Raman spectra were acquired from the fresh samples of human breast tissues.Based on spectral profiles,the presence of 1 078,1 267,1 301,1 437,1 653,and 1 743 cm-1 peaks were identified in the normal tissues; and 1 281,1 341,1 381,1 417,1 465,1 530,and 1 637 cm-1 peaks were found in the benign and malignant tissues.The main characteristic peaks differentiating benign and malignant lesions were 1 340 and 1 480 cm-1.The accuracy of SVM-RFE in discriminating normal and malignant lesions was 100.0％,while that in the assessment of benign lesions was 93.0％.Conclusions There are distinct differences among the Raman spectra of normal,benign and malignant breast tissues,and SVM-RFE method can be used to build differentiation model of breast lesions.
