A multiscale double-branch residual attention network for anatomical-functional medical image fusion.

Medical image fusion technology synthesizes complementary information from multimodal medical images. This technology is playing an increasingly important role in clinical applications. In this paper, we propose a new convolutional neural network, which is called the multiscale double-branch residual attention (MSDRA) network, for fusing anatomical-functional medical images. Our network contains a feature extraction module, a feature fusion module and an image reconstruction module. In the feature extraction module, we use three identical MSDRA blocks in series to extract image features. The MSDRA block has two branches. The first branch uses a multiscale mechanism to extract features of different scales with three convolution kernels of different sizes, while the second branch uses six 3 × 3 convolutional kernels. In addition, we propose the Feature L1-Norm fusion strategy to fuse the features obtained from the input images. Compared with the reference image fusion algorithms, MSDRA consumes less fusion time and achieves better results in visual quality and the objective metrics of Spatial Frequency (SF), Average Gradient (AG), Edge Intensity (EI), Quality-Aware Clustering (QAC), Variance (VAR), and Visual Information Fidelity for Fusion (VIFF).

Computer-aid drug design, synthesis, and anticoagulant activity evaluation of novel dabigatran derivatives as thrombin inhibitors.

In this study, computer-aided drug design techniques were adopted to explore the structural and chemical features for dabigatran and design novel derivatives. The built 3D-QSAR models demonstrated significant statistical quality and excellent predictive ability by internal and external validation. Based on QSAR information, 11 novel dabigatran derivatives (12a-12k) were designed and predicted, then ADME prediction and molecular docking were performed. Furthermore, all designed compounds were synthesized and characterized by 1H NMR, 13C NMR and HR-MS. Finally, they were evaluated for anticoagulant activity in vitro. The activity results showed that the 10 obtained compounds exhibited comparable activity to the reference dabigatran (IC50 = 9.99 ±â€¯1.48 nM), except for compound 12i. Further analysis on molecular docking was performed on three compounds (12a, 12c and 12g) with better activity (IC50 = 11.19 ±â€¯1.70 nM, IC50 = 10.94 ±â€¯1.85 nM and IC50 = 11.19 ±â€¯1.70 nM). MD simulations (10 ns) were carried out, and their binding free energies were calculated, which showed strong hydrogen bond and pi-pi stacking interactions with key residues Gly219, Asp189 and Trp60D. The 10 novel dabigatran derivatives obtained can be further studied as anticoagulant candidate compounds.