Classification for breast cancer diagnosis with Raman spectroscopy

In order to promote the development of the portable, low-cost and in vivo cancer diagnosisinstrument, a miniature laser Raman spectrometer was employed to acquire the conventional Ramanspectra for breast cancer detection in this paper. But it is difficult to achieve highdiscrimination accuracy. Then a novel method of adaptive weight k-local hyperplane (AWKH) isproposed to increase the classification accuracy. AWKH is an extension and improvement ofK-local hyperplane distance nearest-neighbor (HKNN). It considers the features weights of thetraining data in the nearest neighbor selection and local hyperplane construction stage, whichresolve the basic shortcoming of HKNN works well only for small values of the nearest-neighbor.Experimental results on Raman spectra of breast tissues in vitro show the proposed method canrealize high classification accuracy.OCIS codes: (170.5660) Raman spectroscopy, (300.6450) Spectroscopy, Raman, (170.6510) Spectroscopy, tissue diagnostics