Curative Effect of Interventional Therapy and Neurological Changes in Ischemic Stroke of Posterior Circulation Evaluated by Magnetic Resonance Imaging under Genetic Algorithm

Objective. This study aimed to evaluate the improvement and neurological function changes of patients with ischemic stroke in the posterior circulation before and after interventional therapy using magnetic resonance imaging (MRI) under genetic algorithm and compressed sensing algorithm. Methods. Thirty-six patients with posterior circulation ischemia who visited the interventional cerebrovascular disease area were included in this study. The treatment effect was observed through abnormal signal changes in the lesion area on each sequence of MRI images before and after treatment. The National Institutes of Health Stroke Scale (NIHSS) was used for the evaluation of the changes in neurological function. Results. The real data experiment results suggested that the peak signal-to-noise ratio (PSNR) = 39.33 and structure similarity (SSIM) = 0.96 in the algorithm reconstructed image, which showed no significant difference with the simulation experiment results of PSNR = 35.19 and SSIM = 0.96 ( P < 0.05 ). In addition, the stenosis rate after interventional treatment (13.89%) was substantially lower than that before treatment (91.67%) ( P < 0.05 ). Cerebral blood flow (CBF) of the bilateral occipital lobes and cerebellum after six months of treatment was higher than that before treatment ( P < 0.05 ), and the incidence of postoperative restenosis was 11.11% (4/36). Conclusion. The combination of genetic algorithm and compressed sensing algorithm had a good effect on MRI image processing. The posterior circulation ischemia interventional stent implantation can effectively improve the stenosis of the vertebral artery and vertebral basilar artery as well as the cerebral tissue perfusion in the ischemic area, which improved the clinical symptoms substantially and reduced the probability of restenosis.

Group-Based Sparse Representation for Compressed Sensing Image Reconstruction with Joint Regularization

Achieving high-quality reconstructions of images is the focus of research in image compressed sensing. Group sparse representation improves the quality of reconstructed images by exploiting the non-local similarity of images; however, block-matching and dictionary learning in the image group construction process leads to a long reconstruction time and artifacts in the reconstructed images. To solve the above problems, a joint regularized image reconstruction model based on group sparse representation (GSR-JR) is proposed. A group sparse coefficients regularization term ensures the sparsity of the group coefficients and reduces the complexity of the model. The group sparse residual regularization term introduces the prior information of the image to improve the quality of the reconstructed image. The alternating direction multiplier method and iterative thresholding algorithm are applied to solve the optimization problem. Simulation experiments confirm that the optimized GSR-JR model is superior to other advanced image reconstruction models in reconstructed image quality and visual effects. When the sensing rate is 0.1, compared to the group sparse residual constraint with a nonlocal prior (GSRC-NLR) model, the gain of the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) is up to 4.86 dB and 0.1189, respectively.

Embracing enzyme promiscuity with activity-based compressed biosensing

Genome-scale activity-based profiling of proteases requires identifying substrates that are specific to each individual protease. However, this process becomes increasingly difficult as the number of target proteases increases because most substrates are promiscuously cleaved by multiple proteases. We introduce a method - Substrate Libraries for Compressed sensing of Enzymes (SLICE) - for selecting complementary sets of promiscuous substrates to compile libraries that classify complex protease samples (1) without requiring deconvolution of the compressed signals and (2) without the use of highly specific substrates. SLICE ranks substrate libraries according to two features: substrate orthogonality and protease coverage. To quantify these features, we design a compression score that was predictive of classification accuracy across 140 in silico libraries (Pearson r = 0.71) and 55 in vitro libraries (Pearson r = 0.55) of protease substrates. We demonstrate that a library comprising only two protease substrates selected with SLICE can accurately classify twenty complex mixtures of 11 enzymes with perfect accuracy. We envision that SLICE will enable the selection of peptide libraries that capture information from hundreds of enzymes while using fewer substrates for applications such as the design of activity-based sensors for imaging and diagnostics.