Distinction of cervical cancer biopsies by use of infrared microspectroscopy and probabilistic neural networks.

摘要: Fourier-transform infrared spectroscopy has shown alterations of spectral characteristics cells and tissues as a result carcinogenesis. The research reported here focuses on the diagnosis cancer in formalin-fixed biopsied tissue for which immunochemistry is not possible when PAP-smear results are to be confirmed. data from two groups patients (a control group diagnosed with cervical cancer) were analyzed. It was found that glucose/phosphate ratio decreases (by 23-49%) RNA/DNA increases 38-150%) carcinogenic compared normal tissue. microspectroscopy used examine these tissues. This type study larger populations may help set standards or classes use treated predict possibility cancer. Probabilistic neural networks statistical tests parts biopsies high degree accuracy (> 95%).