Anastasia I. Knyazkova

Gliomas, one of the most severe malignant tumors of the central nervous system, have a high mortality rate and an increased risk of recurrence. Therefore, early glioma diagnosis and the control of treatment have great significance. The blood plasma samples of glioma patients, patients with skull craniectomy defects, and healthy donors were studied using terahertz time-domain spectroscopy (THz-TDS). An analysis of experimental THz data was performed by machine learning (ML). The ML pipeline included (i) THz spectra smoothing using the Savitzky–Golay filter, (ii) dimension reduction with principal component analysis and t-distribution stochastic neighborhood embedding methods; (iii) data separability analyzed using Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The ML models’ performance was evaluated by a k-fold cross validation technique using ROC-AUC, sensitivity, and specificity metrics. It was shown that tree-based ensemble methods work more accurately than SVM. RF and XGBoost provided a better differentiation of the group of patients with glioma from healthy donors and patients with skull craniectomy defects. THz-TDS combined with ML was shown to make it possible to separate the blood plasma of patients before and after tumor removal surgery (AUC = 0.92). Thus, the applicability of THz-TDS and ML for the diagnosis of glioma and treatment monitoring has been shown.

In this research, an experimental U87 glioblastoma small animal model was studied. The association between glioblastoma stages and the spectral patterns of mouse blood serum measured in the terahertz range was analyzed by terahertz time-domain spectroscopy (THz-TDS) and machine learning. The THz spectra preprocessing included (i) smoothing using the Savitsky–Golay filter, (ii) outlier removing using isolation forest (IF), and (iii) Z-score normalization. The sequential informative feature-selection approach was developed using a combination of principal component analysis (PCA) and a support vector machine (SVM) model. The predictive data model was created using SVM with a linear kernel. This model was tested using k-fold cross-validation. Achieved prediction accuracy, sensitivity, specificity were over 90%. Also, a relation was established between tumor size and the THz spectral profile of blood serum samples. Thereby, the possibility of detecting glioma stages using blood serum spectral patterns in the terahertz range was demonstrated.

The effect of low-dose photodynamic therapy on in vivo wound healing with topical application of 5-aminolevulinic acid and methylene blue was investigated using an animal model for two laser radiation doses (1 and 4 J/cm²). A second-harmonic-generation-to-auto-fluorescence aging index of the dermis (SAAID) was analyzed by two-photon microscopy. SAAID measured at 60–80 μm depths was shown to be a suitable quantitative parameter to monitor wound healing. A comparison of SAAID in healthy and wound tissues during phototherapy showed that both light doses were effective for wound healing; however, healing was better at a dose of 4 J/cm².

The quasi-static compression optical coherence elastography (OCE) is used to find Young’s modulus of human skin^1,2 . The data on the layers of human skin deformation in vivo were obtained and analyzed. In the OCE compression method, a calibration layer with a known Young's modulus was used, which made it possible to identify the value of the volunteers' skin elastic modulus.

The results of the comparative analysis of exhaled air samples from patients with diabetes mellitus second type (target group) and healthy volunteers (control group) with using laser optical-acoustic IR spectroscopy are presented. The measured absorption spectra of exhaled air samples visualization were performed using the principal component analysis. The good spatial separation of the target and control groups in the space of the main components was achieved, which indicates a significant change in the composition and concentration of metabolites in the exhaled air of patients with diabetes. The volatile metabolites that may be characteristic of diabetes are also discussed.

The results of a comparative study of an emanation from the skin of patients with diabetes mellitus and healthy volunteers using THz spectroscopy. A technique for collecting and analyzing emanation samples from the skin has been developed, and its applicability in THz spectroscopy has been demonstrated. Good separation of THz spectra of the skin emanations has been shown for the target and control groups by the principal component analysis. It shows that THz spectroscopy of skin emanations is useful for the diagnosis of diabetes mellitus.

The of multiphoton microscopy (MPM) based on two-photon fluorescence and second-harmonic generation is promising for diagnosing neoplastic transformation of tissues. The results of MPM studies of tissues with prostate adenocarcinoma embedded in paraffin blocks are presented. The tissue fluorescence was also analyzed using the fluorescence lifetime (Fluorescence-lifetime imaging microscopy - FLIM) option. The relationships between the fluorescence peculiarities and the second harmonic generation of the prostate gland tissues were obtained for different morphological images.