Fluorescence spectral analysis and logistic regression modeling for diagnosing basal cell carcinoma on head and neck.

The optical fluorescence method is distinguished by key features such as non-invasiveness, high sensitivity, and resolution, which are superior to traditional diagnostic approaches. Unlike histopathological examinations and biochemical analyses, optical diagnostic methods obviate the need for tissue sampling, enabling the analysis of virtually unlimited material. The research aims to examine the effectiveness of emission spectra analysis in the diagnosis of basal cell carcinoma (BCC) of the scalp and neck. The analysis was based on data provided by Specialized Hospital No. 2 in Bytom comprising a study sample of 10 patients. For each patient, fluorescence emission spectra were recorded from each of 512 points along a 5 mm line. The results obtained from the histopathological examination, the analysis and morphological evaluation of the tissue, and the diagnosis through microscopic observation were used to define a dichotomous variable (presence or absence of a cancerous lesion), adopted in the study as the modeled variable. The next step of the presented study involved constructing a logistic regression model for identifying cancerous lesions depending on the biochemical indicator's relative fluorescence value (RFV) and emission wavelength (ELW) within the 620 nm to 730 nm range. This wavelength range is often used in fluorescence diagnostics to detect various pathologies, including cancerous lesions. The resulting binary logistic regression model, logit(p)=-33.17+0.04ELW+0.01RFV, indicates a statistically significant relationship between wavelength and relative fluorescence values with the probability of detecting cancer. The estimated model exhibits a good fit and high predictive accuracy. The overall model accuracy is 84.8 %, with the correct classification rates at approximately 96 % for healthy individuals and 74 % for individuals with cancer. These findings underscore the potential of photodynamic diagnostics in cancer detection and monitoring.