Search

Deep learning methods using neural networks for solving partial differential equations (PDEs) have emerged as a new paradigm. However, many of these methods approximate solutions by optimizing loss functions, often encountering convergence issues and accuracy limitations. In this paper, we propose a novel deep learning approach that leverages the expressive power of neural networks to generate basis functions. These basis functions are then used to create trial solutions, which are optimized using the least-squares method to solve for coefficients in a system of linear equations. This method integrates the strengths of streaming PINNs and the traditional least-squares method, offering both flexibility and a high accuracy. We conducted numerical experiments to compare our method with the results of high-order finite difference schemes and several commonly used neural network methods (PINNs, lbPINNs, ELMs, and PIELMs). Thanks to the mesh-less feature of the neural network, it is particularly effective for complex geometries. The numerical results demonstrate that our method significantly enhances the accuracy of deep learning in solving PDEs, achieving error levels comparable to high-accuracy finite difference methods. [ABSTRACT FROM AUTHOR] more...

The physical characteristics of the tumor microenvironment (TME) include solid stress, interstitial fluid pressure, tissue stiffness and microarchitecture. Among them, abnormal changes in tissue stiffness hinder drug delivery, inhibit infiltration of immune killer cells to the tumor site, and contribute to tumor resistance to immunotherapy. Therefore, targeting tissue stiffness to increase the infiltration of drugs and immune cells can offer a powerful support and opportunities to improve the immunotherapy efficacy in solid tumors. In this review, we discuss the mechanical properties of tumors, the impact of a stiff TME on tumor cells and immune cells, and the strategies to modulate tumor mechanics. [ABSTRACT FROM AUTHOR] more...

Two novel highly efficient polymer composite adsorbents based on 3-chloropropyltriethoxysilane-grafted waste para-aramid (PPTA-CP-AT and PPTA-CP-L, PPTA=poly-p-phenylene terephthamide; CP = 3-chloropropyltriethoxysilane; AT=amino trimethylene phosphonic acid; L=L-proline) have been successfully prepared and characterized. The new adsorbents were synthesized by functionalizing 3-chloropropyltriethoxysilane-grafted waste para-aramid with amino trimethylene phosphonic acid and L-proline, respectively. They have been employed to adsorb gold ions from aqueous solution, and the relevant adsorption behaviors have been investigated in detail. The adsorption isotherms of PPTA-CP-AT and PPTA-CP-L were consistent with the Langmuir isotherm model, and the corresponding kinetics could be best described by the pseudo-second-order kinetic model. In particular, the adsorption capacity of PPTA-CP-L was much higher than the values reported in the literature. In addition, the effect of pH on the gold ions adsorption and the thermodynamic parameters of the adsorption procedure were assessed. The research results indicated that PPTA-CP-AT and PPTA-CP-L are two novel adsorbents with high efficiency in wastewater treatment and recovery of precious gold. In particular PPTA-CP-L, which was obtained through facile esterification synthesis at low temperature, showed an excellent adsorption performance and could be used as potentially excellent adsorbent for gold uptake. [ABSTRACT FROM AUTHOR] more...

Real-time and accurate temperature monitoring during microwave hyperthermia (MH) remains a critical challenge for ensuring treatment efficacy and patient safety. This study presents a novel approach to simulate real MH and precisely determine the temperature of the target region within biological tissues using a temporal-informed neural network. We conducted MH experiments on 30 sets of phantoms and 10 sets of ex vivo pork tissues. We proposed a novel perspective: the evolving tissue responses to continuous electromagnetic radiation stimulation are a joint evolution in temporal and spatial dimensions. Our model leverages TimesNet to extract periodic features and Cloblock to capture global information relevance in two-dimensional periodic vectors from ultrasound images. By assimilating more ultrasound temporal data, our model improves temperature-estimation accuracy. In the temperature range 25–65 °C, our neural network achieved temperature-estimation root mean squared errors of approximately 0.886 °C and 0.419 °C for fresh ex vivo pork tissue and phantoms, respectively. The proposed temporal-informed neural network has a modest parameter count, rendering it suitable for deployment on ultrasound mobile devices. Furthermore, it achieves temperature accuracy close to that prescribed by clinical standards, making it effective for non-destructive temperature monitoring during MH of biological tissues. [ABSTRACT FROM AUTHOR] more...