Cancer Diagnosis Using N2 Laser Excited AutofluorescenceudSpectroscopy of Formalin-Fixed Human Tissue

摘要

We report results of an in- vitro autofluorescence spectroscopic study on formalin- fixed human breast tissue samples. Theudstudy involved tissue samples from 20 patients with breast cancer who underwent radical mastectomy at ChoithramudHospital and Research Centre, Indore. A diagnostic algorithm making use of principal component analysis (PCA) as theudfeature extractor and artificial neural network (ANN) as the classifier was used to classify the samples as normal orudcancerous. The algorithm based on combined PCA-ANN provided sensitivity and specificity values of 100% towardsudcancer for the training set data based on leave -one- out cross validation and a sensitivity of 97% and a specificity of 100%udtowards cancer for the independent validation set data. These results suggest that autofluorescence spectroscopy canudprovide a valuable alternate, in- vitro diagnostic modality in clinical pathology setting for discriminating cancerous tissueudsites from normal sites.