Wavelet-based Denoised and Feature Extraction of NMR Spectroscopy Based on Pattern Recognition

According to the shortages of application of MRS and MRI to the clinical cancer diagnosis, an effective method to analyze and process the raw data of nuclear magnetic resonance is brought forward based on wavelet transform and pattern recognition technologies. Aiming at the characteristics of FID signals and MRS, de-nosing of FID and MRS data was performed using wavelet threshold to obtain the better MRS spectra, and then the feature of certain cancer from MRS spectra were extracted based on independent component analysis (ICA) and support vector machine (SVM). Comparing with the de-nosing effect of conventional wavelet basis functions, a new designed wavelet filter set showed better performance. Experiments were carried out on a small amount of low SNR dataset. The results showed the improved effect on de-nosing and feature extraction