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

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