Search

Microfluidic mixers, a pivotal application of microfluidic technology, are primarily utilized for the rapid amalgamation of diverse samples within microscale devices. Given the intricacy of their design processes and the substantial expertise required from designers, the intelligent automation of microfluidic mixer design has garnered significant attention. This paper discusses an approach that integrates artificial neural networks (ANNs) with reinforcement learning techniques to automate the dimensional parameter design of microfluidic mixers. In this study, we selected two typical microfluidic mixer structures for testing and trained two neural network models, both highly precise and cost-efficient, as alternatives to traditional, time-consuming finite-element simulations using up to 10,000 sets of COMSOL simulation data. By defining effective state evaluation functions for the reinforcement learning agents, we utilized the trained agents to successfully validate the automated design of dimensional parameters for these mixer structures. The tests demonstrated that the first mixer model could be automatically optimized in just 0.129 s, and the second in 0.169 s, significantly reducing the time compared to manual design. The simulation results validated the potential of reinforcement learning techniques in the automated design of microfluidic mixers, offering a new solution in this field. [ABSTRACT FROM AUTHOR]

The intelligent design of microfluidic mixers encompasses both the automation of predicting fluid performance and the structural design of mixers. This article delves into the technical trajectory of computer-aided design for micromixers, leveraging artificial intelligence algorithms. We propose an automated micromixer design methodology rooted in cost-effective artificial neural network (ANN) models paired with inverse design algorithms. Initially, we introduce two inverse design methods for micromixers: one that combines ANN with multi-objective genetic algorithms, and another that fuses ANN with particle swarm optimization algorithms. Subsequently, using two benchmark micromixers as case studies, we demonstrate the automatic derivation of micromixer structural parameters. Finally, we automatically design and optimize 50 sets of micromixer structures using the proposed algorithms. The design accuracy is further enhanced by analyzing the inverse design algorithm from a statistical standpoint. [ABSTRACT FROM AUTHOR]

Background: The prostate‐specific membrane antigen (PSMA) targeted positron‐emitting tomography (PET) tracers are increasingly used in clinical practice, with novel tracers constantly being developed. Recently, 18F‐PSMA‐11 has been gaining growing interest for several merits; however, direct in vivo visualization of its kinetic features in humans remains lacking. Purpose: To visualize the kinetic features of 18F‐PSMA‐11 in healthy subjects and patients with prostate cancer derived from the total‐body dynamic PET scans. Methods: A total of 8 healthy volunteers (7 males; 1 female) and 3 patients with prostate cancer underwent total‐body PET/CT imaging at 1 and 2 h post injection (p.i.) of 18F‐PSMA‐11, of which 7 healthy subjects and 3 patients underwent total‐body dynamic PET scans lasting 30 min. Reversible two‐tissue compartments (2TC) and Patlak models were fitted based on the voxel‐based time activity curves (TACs), with the parametric images generated subsequently. Additionally, semi‐automated segmentation of multiple organs was performed in the dynamic images to measure the SUVmean at different time points and in the parametric images to estimate the mean value of the kinetic parameters of these organs. Results: 18F‐PSMA‐11 showed quick accumulation within prostate cancer, as early as 45 s after tracer injection. It was rapidly cleared from blood circulation and predominantly excreted through the urinary system. High and rapid radiotracer accumulation was observed in the liver, spleen, lacrimal glands, and salivary glands, whereas gradual accumulation was observed in the skeleton. Prostate cancer tissue is visualized in all parametric images, and best seen in DV and Patlak Ki images. Patlak Ki showed a good correlation with 2TC Ki values (r = 0.858, p < 0.05) but less noise than 2TC images. A scanning time point of 30–35 min p.i. was then suggested for satisfactory tumor to background ratio. Conclusion: Prostate cancer tissue is visible in most parametric images, and is better shown by Patlak Ki and 2TC DV images. Patlak Ki is consistent with, and thus is preferred over, 2TC Ki images for substantially quicker calculation. Based on the dynamic imaging analysis, a shorter uptake time (30–35 min) might be preferred for a better balance of tumor to background ratio. [ABSTRACT FROM AUTHOR]

Background: Erectile dysfunction and atherosclerosis are common cardiovascular complications in diseases. Clinical associations between erectile dysfunction and atherosclerosis have been noticed, but the specific mechanisms are not illustrated adequately. Objectives: The aim of the study was to further mine associated pathological mechanisms and genetic alterations of atherosclerosis in diabetes mellitus‐related erectile dysfunction. Materials and methods: Significant atherosclerosis‐related genes were identified from transcriptome data of diabetes mellitus‐related erectile dysfunction and atherosclerosis‐related gene sets from DisGeNET and GeneCard databases. Functional enrichment and immune infiltration analyses were performed to clarify the biological roles and pathways as well as immune responses of significant atherosclerosis‐related gene sets. A protein–protein interaction network was constructed, and gene clusters were performed. Then, data of diabetic plaques and high‐glucose cavernosum endothelial cells were analyzed for validation. And hub atherosclerosis‐related gene sets were identified. Finally, expressed pattern of hub atherosclerosis‐related gene sets were explored by single‐cell profiling and immune analysis. Results: In total, 202 significant atherosclerosis‐related gene sets including 100 upregulated and 102 downregulated genes were identified. These genes were related to endothelial cell migration, inflammatory response, regulation of oxidative stress, and immune response. In immune infiltration, immature dendritic cells and monocytes showed differential expression between the diabetes mellitus‐related erectile dysfunction and control groups, A protein–protein interaction network containing 135 nodes was constructed. A hub atherosclerosis‐related gene set signature consisting of HBEGF, LOX, NQO1, and VLDLR was obtained by multi‐omics validation. In addition, Functional enrichment analysis revealed that hub atherosclerosis‐related gene sets were involved in oxidoreductase activity and extracellular matrix organization. Discussion and conclusion: We explored atherosclerosis‐related genetic changes and signaling pathways in diabetes mellitus‐related erectile dysfunction. HBEGF, LOX, NQO1, and VLDLR were identified as hub atherosclerosis‐related gene sets. These may serve as potential biomarkers for the clinical management of atherosclerosis and preventing further cardiovascular risks in diabetes mellitus‐related erectile dysfunction. [ABSTRACT FROM AUTHOR]