Investigating the Role of Image Fusion in Brain Tumor Classification Models Based on Machine Learning Algorithm for Personalized Medicine.

Image fusion can be performed on images either in spatial domain or frequency domain methods. Frequency domain methods will be most preferred because these methods can improve the quality of edges in an image. In image fusion, the resultant fused images will be more informative than individual input images, thus more suitable for classification problems. Artificial intelligence (AI) algorithms play a significant role in improving patient's treatment in the health care industry and thus improving personalized medicine. This research work analyses the role of image fusion in an improved brain tumour classification model, and this novel fusion-based cancer classification model can be used for personalized medicine more effectively. Image fusion can improve the quality of resultant images and thus improve the result of classifiers. Instead of using individual input images, the high-quality fused images will provide better classification results. Initially, the contrast limited adaptive histogram equalization technique preprocess input images such as MRI and SPECT images. Benign and malignant class brain tumor images are applied with discrete cosine transform-based fusion method to obtain fused images. AI algorithms such as support vector machine classifier, KNN classifier, and decision tree classifiers are tested with features obtained from fused images and compared with the result obtained from individual input images. Performances of classifiers are measured using the parameters accuracy, precision, recall, specificity, and F1 score. SVM classifier provided the maximum accuracy of 96.8%, precision of 95%, recall of 94%, specificity of 93%, F1 score of 91%, and performed better than KNN and decision tree classifiers when extracted features from fused images are used. The proposed method results are compared with existing methods and provide satisfactory results.

Anharmonic vibrational analysis of 3,4-diaminopyridine and 3-aminopyridine by density functional theory calculations.

In this work, we will report a combined experimental and theoretical study on molecular structure and vibrational analysis of 3,4-diaminopyridine (3,4-DAP) and 3-aminopyridine (3-AP). The Fourier transform infrared and Fourier transform Raman spectra of 3,4-DAP were recorded in the solid phase. The molecular geometry, harmonic vibrational wavenumbers of 3-AP and 3,4-DAP in the ground-state have been calculated by using MP2 and density functional methods (B3LYP) using 6-311++G(d,p) as basis set. Predicted electronic absorption spectra 3,4-DAP from TD-DFT calculation have been analyzed comparing with the experimental UV-vis spectrum. The calculated HOMO and LUMO energies show that charge transfer occur in the molecule. A detailed interpretation of the infrared spectra of 3-AP and 3,4-DAP is reported. The theoretical spectrograms for FTIR and FT-Raman spectra of the title molecules have also been constructed. Comparison of the experimental spectra with anharmonic vibrational wavenumbers indicates that B3LYP results are more accurate.

The spectroscopic (FTIR, FT-IR gas phase and FT-Raman), first order hyperpolarizabilities, NMR analysis of 2,4-dichloroaniline by ab initio HF and density functional methods.

In this work, the experimental and theoretical study on molecular structure and vibrational spectra of 2,4-dichloroaniline (2,4-DCA) were studied. The Fourier transform infrared (gas phase) and Fourier transform Raman spectra of 2,4-DCA were recorded. The molecular geometry and vibrational frequencies of 2,4-DCA in the ground state were calculated by using the Hartree-Fock (HF) and density functional (DF) methods (BLYP, B3LYP and SVWN) with 6-31G(d,p) as basis set. Comparison of the observed fundamental vibrational frequencies of 2,4-DCA with calculated results by HF and density functional methods indicates that BLYP is superior to other methods for molecular vibrational problems. The difference between the observed and scaled wave number values of most of the fundamentals is very small. The electric dipole moment (micro) and the first hyperpolarizability (beta) values of the investigated molecule were computed using ab initio quantum mechanical calculations. The calculated results also show that the 2,4-DCA molecule might have microscopic nonlinear optical (NLO) behavior with non-zero values. Natural atomic charges of 2,4-DCA and 4-chloroaniline was calculated and compared. The isotropic chemical shift computed by (13)C NMR analyses also shows good agreement with experimental observations. The theoretically predicted FTIR and FT-Raman spectra of the title molecule have been constructed.