Search

Current research on image classification has combined convolutional neural networks (CNNs) and transformers to introduce inductive biases to the model, enhancing its ability to handle long-range dependencies. However, these integrated models have limitations. Standard CNNs have a static nature, restricting their convolution from dynamically adjusting to input images, thus limiting feature expression capabilities. In addition, the static nature of CNNs impedes the seamless integration between features dynamically generated by self-attention mechanisms and static features generated by convolution when combined with transformers. Furthermore, during image processing, each model stage contains abundant information that cannot be fully utilized by single-scale convolution, ultimately impacting the network’s classification performance. To tackle these challenges, we propose WoodGLNet, a real-time multi-scale pyramid network that aggregates global and local information in an input-dependent manner and facilitates feature interaction through three scales of convolution. WoodGLNet utilizes efficient multi-scale global spatial decay attention modules and input-dependent multi-scale dynamic convolutions at different stages, enhancing the network’s inductive biases and expanding the effective receptive field. In CIFAR100 and CIFAR10 image classification tasks, WoodGLNet-T achieves Top-1 accuracies of 76.34% and 92.35%, respectively, outperforming EfficientNet-B3 by 1.03 and 0.86 percentage points. WoodGLNet-S and WoodGLNet-B attain Top-1 accuracies of 77.56%, 93.66%, and 80.12%, 94.27%, respectively. The experimental subjects of this study were sourced from the Shandong Province Construction Structural Material Specimen Museum, tasked with wood testing and requiring high real-time performance. To assess WoodGLNet’s real-time detection capabilities, 20 types of precious wood from the museum were identified in real time using the WoodGLNet network. The results indicated that WoodGLNet achieved a classification accuracy of up to 99.60%, with a recognition time of 0.013 s per single image. These findings demonstrate the network’s exceptional real-time classification and generalization abilities. [ABSTRACT FROM AUTHOR]

Background: To evaluate the effects of correction in lumbar lordosis (LL) that have on full-body realignments in patients with degenerative lumbar scoliosis (DLS) who had undergone long sacroiliac fusion surgery. Methods: A multi-center retrospective study including 88 DLS patients underwent the surgical procedure of long sacroiliac fusion with instrumentations was performed. Comparisons of radiographic and quality-of-life (QoL) data among that at the pre-operation, the 3rd month and the final follow-up were performed. The correlations between the LL correction and the changes in other spinopelvic parameters were explored using Pearson-correlation linear analysis and linear regression analysis. The correlation coefficient (r) and the adjusted r2 were calculated subsequently. Results: All radiographic and QoL data improved significantly (P < 0.001) after the surgical treatments. The LL correction correlated (P < 0.001) with the changes in the sacral slope (SS, r = 0.698), pelvic tilt (PT, r = -0.635), sagittal vertical axis (SVA, r = −0.591), T1 pelvic angle (TPA, r = −0.782), and the mismatch of pelvic incidence minus lumbar lordosis (PI–LL, r = −0.936), respectively. Moreover, LL increased by 1° for each of the following spinopelvic parameter changes (P < 0.001): 2.62° for SS (r2 = 0.488), −4.01° for PT (r2 = 0.404), −4.86° for TPA (r2 = 0.612), −2.08° for the PI–LL (r2 = 0.876) and -15.74 mm for SVA (r2 = 0.349). Changes in the thoracic kyphosis (r = 0.259) and pelvic femur angle (r = 0.12) were independent of the LL correction, respectively. Conclusions: LL correction correlated significantly to the changes in spinopelvic parameters; however, those independent variables including the thoracic spine and hip variables probably be remodeled themselves to maintain the full-body balance in DLS patients underwent the correction surgery. [ABSTRACT FROM AUTHOR]

This letter to the editor discusses a study on the impact of the surgical day of the week on the hospital course and outcomes for patients undergoing adult spinal deformity surgery. The study included 256 patients and found no difference in the length of stay between surgeries performed early in the week and later in the week. However, there were some issues with the study, such as not considering the impact of the mode of anesthesia on patient prognosis and not analyzing respiratory diseases before performing postoperative risk assessment. The authors hope that their views will be useful for further research. [Extracted from the article]

This document is a letter to the editor in response to an article titled "Geriatric distal femoral fractures: post-operative complications and nine-year mortality—a retrospective analysis of two tertiary trauma centres." The authors of the letter express their gratitude to the original authors for their research but also raise some concerns and issues that need further exploration. They question the impact of postoperative nursing care and convalescent sites on patient mortality, the accuracy of statistical analysis regarding gender as a predictor of mortality, and the lack of a clear postoperative weight-bearing protocol. The authors hope that their interpretations and observations will contribute to the readers' understanding of the topic. [Extracted from the article]

This letter to the editor responds to a study on the role of environmental and seasonal factors in surgical site infection after spinal surgery. The authors express gratitude for the study but also raise some points for further exploration. They note that the study did not provide diagnostic criteria for surgical site infection and suggest using the standards proposed by the Centers for Disease Control and Prevention. The authors also highlight the need to consider surgical complications and the gap between recommended and observed wound care practices. Overall, the letter aims to contribute to a better understanding of the study. [Extracted from the article]

Breast cancer (BC) is common worldwide. c-Myc and AXL are both overexpressed in BC, promoting its progression. The present study aimed to investigate the role of AXL in c-Myc expression in BC. Overexpression of AXL increased c-Myc expression while knockdown of AXL decreased c-Myc expression as determined by western blot analysis. Pharmaceutical inhibition of AXL also suppressed c-Myc expression. AKT and ERK inhibitor LY294002 and U0126 suppressed c-Myc expression, respectively. AXL overexpression which activates AKT and ERK signaling, upregulates c-Myc expression, while kinase-dead AXL which cannot activate AKT and ERK signaling, does not upregulate c-Myc expression, emphasizing the important role of these two signaling pathways in c-Myc upregulation. Finally, expression data of BC tissues from The Cancer Proteome Atlas displayed an association between AXL and c-Myc. Taken together, the present study revealed that AXL upregulates c-Myc expression through AKT and ERK signaling pathways in BC. [ABSTRACT FROM AUTHOR]