DocumentCode :
2478480
Title :
Least squares SVM combined with near infrared spectroscopy for diagnosing endometrial carcinoma
Author :
Tian, Jing ; Xiang, Yuhong ; Zhang, Zhuoyong ; de B Harrington, Peter ; Dai, Yinmei
Author_Institution :
Dept. of Chem., Capital Normal Univ., Beijing, China
fYear :
2011
fDate :
24-26 June 2011
Firstpage :
7656
Lastpage :
7659
Abstract :
The feasibility of early diagnosis of endometrial carcinoma was studied by least squares support vector machines (LS-SVM) that classified near infrared (NIR) spectra of tissues. MR spectra of 77 specimens of endometrium were collected. The spectra were pretreated by the 1st derivative Savitzky-Golay and direct orthogonal signal correction (DOSC) methods to improve the signal-to-noise ratio and remove the influences of background and baseline. The effects of modeling parameters were investigated using grid searching technique and bootstrapped Latin-partition methods. The model was optimized with the destination function of the average RMSE of bootstrapped Latin partition cross validation. The optimal model of the LS-SVM successfully classified all the samples of the test set into three groups. The proposed procedure was proven to be rapid and convenient, which is suitable to be developed as a non-invasive diagnosis method for cancer tissue.
Keywords :
biomedical optical imaging; cancer; gynaecology; infrared imaging; infrared spectra; least squares approximations; medical image processing; support vector machines; 1st derivative Savitzky-Golay method; RMSE; bootstrapped Latin-partition methods; cancer tissue; direct orthogonal signal correction method; early diagnosis; endometrial carcinoma; endometrium; grid searching technique; least squares SVM; modeling parameters; near infrared spectroscopy; non-invasive diagnosis method; signal-to-noise ratio; support vector machines; Algorithm design and analysis; Calibration; Cancer; Mathematical model; Spectroscopy; Support vector machines; Training; Cancer diagnosis; Endometrial carcinoma; Least squares support vector machines; Near infrared spectroscopy;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Remote Sensing, Environment and Transportation Engineering (RSETE), 2011 International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4244-9172-8
Type :
conf
DOI :
10.1109/RSETE.2011.5966148
Filename :
5966148
Link To Document :
بازگشت