ABSTRACT
Background: Statistics show that each year more than 100,000 patients pass away from brain tumors. Due to the diverse morphology, hazy boundaries, or unbalanced categories of medical data lesions, segmentation prediction of brain tumors has significant challenges. Purpose: In this thesis, we highlight EAV-UNet, a system designed to accurately detect lesion regions. Optimizing feature extraction, utilizing automatic segmentation techniques to detect anomalous regions, and strengthening the structure. We prioritize the segmentation problem of lesion regions, especially in cases where the margins of the tumor are more hazy. Methods: The VGG-19 network structure is incorporated into the coding stage of the U-Net, resulting in a deeper network structure, and an attention mechanism module is introduced to augment the feature information. Additionally, an edge detection module is added to the encoder to extract edge information in the image, which is then passed to the decoder to aid in reconstructing the original image. Our method uses the VGG-19 in place of the U-Net encoder. To strengthen feature details, we integrate a CBAM (Channel and Spatial Attention Mechanism) module into the decoder to enhance it. To extract vital edge details from the data, we incorporate an edge recognition section into the encoder. Results: All evaluation metrics show major improvements with our recommended EAV-UNet technique, which is based on a thorough analysis of experimental data. Specifically, for low contrast and blurry lesion edge images, the EAV-Unet method consistently produces forecasts that are very similar to the initial images. This technique reduced the Hausdorff distance to 1.82, achieved an F1 score of 96.1%, and attained a precision of 93.2% on Dataset 1. It obtained an F1 score of 76.8%, a Precision of 85.3%, and a Hausdorff distance reduction to 1.31 on Dataset 2. Dataset 3 displayed a Hausdorff distance cut in 2.30, an F1 score of 86.9%, and Precision of 95.3%. Conclusions: We conducted extensive segmentation experiments using various datasets related to brain tumors. We refined the network architecture by employing smaller convolutional kernels in our strategy. To further improve segmentation accuracy, we integrated attention modules and an edge enhancement module to reinforce edge information and boost attention scores.
ABSTRACT
The reaction of enantiomeric bis-bidentate bridging ligands (+)/(-)-2,5-bis(4,5-pinene-2-pyridyl)pyrazine (L(S)/L(R)) with [Re(CO)5Cl] yielded a pair of dinuclear Re(I) enantiomers formulated as [Re2(L(S)/L(R))(CO)6Cl2]·4CH2Cl2 (R-1 and S-1, the isomers containing the respective L(R) and L(S) ligands). They were characterized by elemental analyses, IR spectra and X-ray crystallography. Circular dichroism spectra verified their chiroptical activities and enantiomeric nature. The measurements of second harmonic generation (SHG) and ferroelectric properties showed that R-1 displays a nonlinear optical (NLO) activity and ferroelectricity with a remnant polarization (P(r)) of 1.6 µC cm(-2) under an applied field of 7.3 kV cm(-1) at room temperature. R-1 and S-1 represent the first example of polynuclear Re(i) complexes with ferroelectric properties. Notably, the P(r) value is much larger than that of the reported mononuclear chiral Re(I) analogue. In particular, unlike mononuclear Re(i) complexes of the type [Re(CO)3(N^N)(X)] (N^N = diimine and X = halide), which usually exhibit an intense emission in the visible range, R-1 and S-1 do not show any detectable emission at any temperature range and the reason for the nonluminescence of R-1 and S-1 was further elucidated in this work. Moreover, our research results also elucidated that Re nuclearity has a great influence on not only the emitting properties but also on ferroelectric behavior.
ABSTRACT
Two second-order nonlinear optically (NLO)-active dinuclear and square Cu(II) enantiomeric pairs were obtained via the self-assemblies of enantiopure linear bis-bidentate ligands with different copper(II) salts under the identical reaction conditions. Their magnetic properties are switched from antiferromagnetic to ferromagnetic coupling.
