Due to the inherent intermittency, variability, and randomness, photovoltaic (PV) power generation faces significant challenges in energy grid integration. To address these challenges, current research mainly focuses on developing more efficient energy management systems and prediction technologies. Through optimizing scheduling and integration in PV power generation, the stability and reliability of the power grid can be further improved. In this study, a new prediction model is introduced that combines the strengths of convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and attention mechanisms, so we call this algorithm CNN-LSTM-Attention (CLA). In addition, the Crested Porcupine Optimizer (CPO) algorithm is utilized to solve the short-term prediction problem in photovoltaic power generation. This model is abbreviated as CPO-CLA. This is the first time that the CPO algorithm has been introduced into the LSTM algorithm for parameter optimization. To effectively capture univariate and multivariate time series patterns, multiple relevant and target variables prediction patterns (MRTPPs) are employed in the CPO-CLA model. The results show that the CPO-CLA model is superior to traditional methods and recent popular models in terms of prediction accuracy and stability, especially in the 13 h timestep. The integration of attention mechanisms enables the model to adaptively focus on the most relevant historical data for future power prediction. The CPO algorithm further optimizes the LSTM network parameters, which ensures the robust generalization ability of the model. The research results are of great significance for energy generation scheduling and establishing trust in the energy market. Ultimately, it will help integrate renewable energy into the grid more reliably and efficiently.

Purpose To evaluate posture-dependent spinal curvature in adolescents using a novel rotatable cryogen-free 1.5T MRI system and to establish a fully automated analysis pipeline for quantitative Cobb angle measurement. Methods Thirty-two healthy adolescents (15 males, 17 females; mean age 15.0 ± 2.2 years) underwent whole-spine MRI in both supine (0°) and upright (90°) postures. Imaging was performed with a 3D coronal LAVA sequence. A custom pipeline integrated structural-similarity–based image stitching, deep learning–assisted segmentation and annotation, and Cobb angle computation from coronal projections. Cobb angles were compared between postures using paired t-tests with Bonferroni correction, and effect sizes were reported as Cohen’s d. Results Imaging and automated analysis were successfully completed for all participants. Upright Cobb angles were significantly larger than supine across most regions: thoracic (6.5 ± 2.3° vs. 8.4 ± 3.1°, d = 0.65, corrected p = 0.003), lumbar (6.7 ± 3.9°vs 8.7 ± 4.9°, d = 0.43, corrected p = 0.060), cervicothoracic (5.0 ± 2.2°vs 6.3 ± 2.9°, d = 0.53, corrected p = 0.030), and thoracolumbar (8.1 ± 3.6° vs. 11.3 ± 4.6°, d = 0.74, corrected p < 0.001). Maximum Cobb angle increased from 9.1 ± 3.3° to 12.4 ± 3.9° (d = 0.83, corrected p < 0.001). Using the clinical threshold of 10°, 13 of 32 (41%) subjects were classified as negative in supine but positive in upright, indicating that supine imaging may underestimate spinal curvature magnitude in posture-dependent assessments. Conclusion This study demonstrates the feasibility and clinical potential of a rotatable upright MRI system for radiation-free, posture-dependent assessment of spinal curvature. Upright imaging consistently revealed greater Cobb angles than supine imaging, particularly in the thoracolumbar region, and identified cases that would be underestimated with conventional methods. Combined with a fully automated analysis pipeline, this approach provides a reproducible and physiologically relevant framework for characterizing spinal curvature under natural loading conditions.

Compared with hyperpolarized noble gas MRI, oxygen-enhanced lung imaging is a cost-effective approach to investigate lung function. In this study, we investigated the feasibility of free-breathing phase-resolved oxygen-enhanced pulmonary MRI based on a 3D stack-of-stars ultra-short echo time (UTE) sequence. We conducted both computer simulation and in vivo experiments and calculated percent signal enhancement maps of four different respiratory phases on four healthy volunteers from the end of expiration to the end of inspiration. The phantom experiment was implemented to verify simulation results. The respiratory phase was segmented based on the extracted respiratory signal and sliding window reconstruction, providing phase-resolved pulmonary MRI. Demons registration algorithm was applied to compensate for respiratory motion. The mean percent signal enhancement of the average phase increases from anterior to posterior region, matching previous literature. More details of pulmonary tissues were observed on post-oxygen inhalation images through the phase-resolved technique. Phase-resolved UTE pulmonary MRI shows the potential as a valuable method for oxygen-enhanced MRI that enables the investigation of lung ventilation on middle states of the respiratory cycle.

This paper introduces a motion-corrected, free-breathing dynamic contrast-enhanced (DCE) MRI reconstruction method, termed low-rank plus sparse (L+S) with soft weighting. We designed a soft weighting matrix that smoothly transitions spokes between the target and other motion states to suppress motion blurring. The optimized fast iterative shrinkage-thresholding algorithm (FISTA) was employed to solve the L+S optimization problem, enabling faster convergence and better image quality. A DCE-MRI computer simulation framework, based on a modified Shepp-Logan model, was used as ground truth to quantify the motion suppression errors. Both simulation and clinical datasets demonstrate that the proposed method provides superior motion correction and higher reconstruction efficiency compared to existing motion-corrected GRASP frameworks.

According to the report from the World Health Organization (WHO), vascular diseases became the most life-threatening diseases by 2015. Time of flight angiography (TOF) is a non-contrast MRI technique to visualize blood vessel in the human vascular system. However, diagnosis of the complex vascular network structures was difficult based on traditional (2D) display method owing to the complexity and variability of vascular network structures. In this study, we investigated the feasibility of displaying three-dimensional (3D) vessel network in virtual reality (VR) environment, using 3D TOF data. Also, the potential value of its clinical application was evaluated. The experiment results, 3D VR videos, showed that the intervention of VR technology is feasible for the 3D image display of cerebrovascular network.