System of polarization autofluorescence diagnostics of biological layers with fuzzy logic of decision support
The article considers a new approach to solving the problem of increasing the reliability of diagnostics of biological tissues based on a combination of azimuthally invariant polarization and fluorescence methods for diagnosing the structure of optically anisotropic tissue samples. The improved diag...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Zhytomyr Polytechnic State University
2025-07-01
|
| Series: | Технічна інженерія |
| Subjects: | |
| Online Access: | https://ten.ztu.edu.ua/article/view/334749 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The article considers a new approach to solving the problem of increasing the reliability of diagnostics of biological tissues based on a combination of azimuthally invariant polarization and fluorescence methods for diagnosing the structure of optically anisotropic tissue samples. The improved diagnostic method involves measuring the intensity distributions of autofluorescence polarimetry and azimuthally independent Muller matrix images of optically thin tissue samples at wavelengths of 450 nm, 550 nm, 650 nm, which correspond to the maxima of the emission spectra of the intrinsic fluorophores of biological layers after excitation by a polarized beam. Further statistical processing of the measured distributions, which is carried out in an improved system of laser polarization autofluorescence diagnostics, allows you to form a vector of informative features from estimates of their averages, dispersion, asymmetry and kurtosis, formed at each of the three specified wavelengths. Based on the vector of informative features and the developed fuzzy logic decision support models obtained at three wavelengths, a recommended diagnostic solution is formed. An experimental study of the improved diagnostic method was conducted on a sample of 160 samples of biological myocardial tissues, formed by three groups: (control group – 20 samples; ischemia – 70 samples; acute coronary insufficiency – 70 samples). It was shown that a high (90–92 %) and excellent (95–95,7 % reliability) qualitative level of diagnostic assessment was achieved. An increase in the reliability of myocardial diagnosis from 2,5 to 3,7 % was obtained using the improved method in comparison with analogues. |
|---|---|
| ISSN: | 2706-5847 2707-9619 |