Explore the vast range of titles available.

To address the challenges of unbalanced class labels with varying maturity levels of tomato fruits and low recognition accuracy for both fruits and stems in intelligent harvesting, we propose the YOLOX-SE-GIoU model for identifying tomato fruit maturity and stems. The SE focus module was incorporated into YOLOX to improve the identification accuracy, addressing the imbalance in the number of tomato fruits and stems. Additionally, we optimized the loss function to GIoU loss to minimize discrepancies across different scales of fruits and stems. The mean average precision (mAP) of the improved YOLOX-SE-GIoU model reaches 92.17%. Compared to YOLOv4, YOLOv5, YOLOv7, and YOLOX models, the improved model shows an improvement of 1.17–22.21%. The average precision (AP) for unbalanced semi-ripe tomatoes increased by 1.68–26.66%, while the AP for stems increased by 3.78–45.03%. Experimental results demonstrate that the YOLOX-SE-GIoU model exhibits superior overall recognition performance for unbalanced and scale-variant samples compared to the original model and other models in the same series. It effectively reduces false and missed detections during tomato harvesting, improving the identification accuracy of tomato fruits and stems. The findings of this work provide a technical foundation for developing advanced fruit harvesting techniques.

Magnetic fluids are the suspensions composed of magnetic nanoparticles, surfactants, and non-magnetic carrier liquids. Magnetic fluids are widely used in various fields, especially in sealing, because of their excellent features, including rapid magnetic response, flexible flow ability, tunable magneto-viscous effect, and reliable self-repairing capability. Here, we provide an in-depth, comprehensive insight into the theoretical analyses and diverse applications of magnetic fluids in sealing from three categories: static sealing, rotary sealing, and reciprocating sealing. We summarize the magnetic fluid sealing mechanisms and the development of magnetic fluid seals from 1960s to the present, particularly focusing on the recent progress of magnetic fluid seals. Although magnetic fluid sealing technology has been commercialized and industrialized, many difficulties still exist in its applications. At the end of the review, the present challenges and future prospects in the progress of magnetic fluid seals are also outlined.

Multi-sequence magnetic resonance imaging is crucial in accurately identifying knee abnormalities but requires substantial expertise from radiologists to interpret. Here, we introduce a deep learning model incorporating co-plane attention across image sequences to classify knee abnormalities. To assess the effectiveness of our model, we collected the largest multi-sequence knee magnetic resonance imaging dataset involving the most comprehensive range of abnormalities, comprising 1748 subjects and 12 types of abnormalities. Our model achieved an overall area under the receiver operating characteristic curve score of 0.812. It achieved an average accuracy of 0.78, outperforming junior radiologists (accuracy 0.65) and remains competitive with senior radiologists (accuracy 0.80). Notably, with the assistance of model output, the diagnosis accuracy of all radiologists was improved significantly ( p  < 0.001), elevating from 0.73 to 0.79 on average. The interpretability analysis demonstrated that the model decision-making process is consistent with the clinical knowledge, enhancing its credibility and reliability in clinical practice. The authors present a deep learning model that incorporates co-plane attention across image sequences with a performance comparable to senior radiologists in classifying 12 knee abnormalities from MRI. The model significantly improves diagnostic performance and aligns with clinical observations.

Background β-thalassemia is a common monogenic genetic disorder, characterized by reduced or absent synthesis of β-globin chains. High fetal hemoglobin (HbF) levels can alleviate the severity of anemia in β-thalassemia, and miRNAs can regulate the expression of globins. MiR-329-3p is a miRNA that is differentially expressed in β-thalassemia. Aim this study mainly investigated the expression of miR-329-3p in the peripheral blood of children with β-thalassemia, analyzed its clinical diagnostic value in β-thalassemia, and further studied the regulatory effects of miR-329-3p on its target genes TNRC6B and γ-globin. Methods the expression levels of miR-329-3p, TNRC6B, and γ-globin were verified by reverse transcription quantitative real-time polymerase chain reaction (RT-qPCR). The interaction relationship between miR-329-3 and TNRC6B was confirmed through dual-luciferase assay. Cell viability was detected by the CCK8 method, cell migration rate was verified by Transwell assay, and cell apoptosis rate was determined by cell flow cytometry. Results in children with β-thalassemia, miR-329-3p is upregulated and positively correlates with γ-globin, while TNRC6B is downregulated. MiR-329-3p demonstrates potential diagnostic and prognostic value for β-thalassemia. MiR-329-3p interacts with TNRC6B, and their expression levels show a negative correlation. Knocking down miR-329-3p suppresses the activity and migration of red blood cells, promotes apoptosis, and reduces γ-globin. Conversely, miR-329-3p overexpression enhances red blood cell function, inhibits apoptosis, and increases γ-globin. Conclusions MiR-329-3p has clinical significance in the diagnosis of β-thalassemia. It can inhibit the expression of TNRC6B by upregulation and promote the expression of γ-globin.

Background The impact of screen exposure on children’s language development has been widely debated. However, some characteristics of screen use, particularly the influence of the pandemic over the past three years have yet to be sufficiently investigated. Objectives To examine the association between screen exposure, particularly during the pandemic, and language development delays in children aged 18–72 months. Methods A total of 2100 children who attended the children’s language development clinic at Guangzhou Women and Children’s Medical Center and Yuncheng Street Community Health Service Center in Guangzhou, China, were recruited into the study between January 2020 and September 2023. Children’s demographic and developmental characteristics were obtained through a structured questionnaire, and their language development delays were evaluated through the Sign-Significate Relations (S-S) assessment, which was subsequently validated by the China Developmental Scale for Children method based on the voluntary principle. Multivariate logistic regression models were employed to analyze the association between screen exposure and language development delay. In order to gain further insight, the data was stratified according to whether or not the children had experienced a period of social isolation due to the COVID-19 pandemic, the parenting environment and the quality of screen usage. Results More than half of the children (53.29%) were exposed to screens for over 1 h daily. After adjusting for potential confounders, a dose-response relationship was observed between children’s daily screen exposure exceeding 1 h and the risk of delayed language development. The stratified analyses confirmed the main findings, revealing stronger associations in children who had experienced at least one period of quarantine, whose primary language spoken at home was Cantonese, whose caregivers had an intermediate personality, whose daily outdoor activities were less than 2 h, who did not have interaction with caregivers during screen time, and who watched educational videos. Conclusion This study suggested that excessive screen exposure in children was associated with a heightened likelihood of language development delays, especially among children who experienced COVID-19 quarantine with prolonged screen time.

Several hematologic traits have been suggested to potentially contribute to the formation and rupture of intracranial aneurysms (IA). The purpose of this study is to explore the causal association between hematologic traits and the risk of IA. To explore the causal association between hematologic traits and the risk of IA, we employed two-sample Mendelian randomization (MR) analysis. Two independent summary-level GWAS data were used for preliminary and replicated MR analyses. The inverse variance weighted (IVW) method was employed as the primary method in the MR analyses. The stabilities of the results were further confirmed by a meta-analysis. In the preliminary MR analysis, hematocrit, hemoglobin concentration ( p  = 0.0047), basophil count ( p  = 0.0219) had a suggestive inverse causal relationship with the risk of aneurysm-associated subarachnoid hemorrhage (aSAH). The monocyte percentage of white cells ( p  = 0.00956) was suggestively positively causally correlated with the risk of aSAH. In the replicated MR analysis, only the monocyte percentage of white cells ( p  = 0.00297) remained consistent with the MR results in the preliminary analysis. The hematocrit, hemoglobin concentration, and basophil count no longer showed significant causal relationship ( p  > 0.05). Meta-analysis results further confirmed that only the MR result of monocyte percentage of white cells reached significance in the random effect model and fixed effect model. None of the 25 hematologic traits was causally associated with the risk of unruptured intracranial aneurysms (uIA). This study revealed a suggestive positive association between the monocyte percentage of white cells and the risk of aSAH. This finding contributes to a better understanding that monocytes/macrophages could participate in the risk of aSAH.

Apple leaf diseases significantly impair the photosynthetic efficiency and growth quality of apple trees, leading to reduced fruit yields. Existing methods for disease detection and severity classification struggle to quickly and accurately segment and quantify diseased areas on leaves, particularly in complex backgrounds. To address this issue, we propose a method for assessing the severity of apple leaf diseases based on a combination of improved HRNet and DRL-watershed algorithms. First, we selected HRNet_w32 as the backbone feature extraction network and incorporated a Normalization Attention Mechanism (NAM). Then, we combined the Dice Loss and Focal Loss functions to construct an enhanced HRNet based semantic segmentation model for pixel-level segmentation of both apple leaf and diseased regions. Furthermore, the segmented leaf and disease regions were further optimized using the DRL-watershed algorithm to distinguish overlapping leaf regions. Experimental results demonstrate that the modified HRNet model achieved a mean intersection over union (mIoU) of 88.91% and a mean pixel accuracy (mPA) of 94.13%, representing improvements of 8.77 and 7.25% points, respectively, over the original HRNet. The disease severity assessment accuracy reached 97.65%. This study not only accurately segments apple leaves and diseased areas, but also effectively addresses the impact of complex backgrounds and leaf overlap on disease severity assessment, providing a solid scientific basis for disease management strategies.

The accurate segmentation of apple leaf disease spots is the key to identifying the classification of apple leaf diseases and disease severity. Therefore, a DeepLabV3+ semantic segmentation network model with an actors spatial pyramid pool module (ASPP) was proposed to achieve effective extraction of apple leaf lesion features and to improve the apple leaf disease recognition and disease severity diagnosis compared with the classical semantic segmentation network models PSPNet and GCNet. In addition, the effects of the learning rate, optimizer, and backbone network on the performance of the DeepLabV3+ network model with the best performance were analyzed. The experimental results show that the mean pixel accuracy (MPA) and mean intersection over union (MIoU) of the model reached 97.26% and 83.85%, respectively. After being deployed into the smartphone platform, the detection time of the detection system was 9s per image for the portable and intelligent diagnostics of apple leaf diseases. The transfer learning method provided the possibility of quickly acquiring a high-performance model under the condition of small datasets. The research results can provide a precise guide for the prevention and precise control of apple diseases in fields.

Sinonasal malignant tumors are a group of uncommon malignancies that account for less than 1% of all tumors. These tumors often involve the maxillary sinus and nasal cavity, with less cumulative incidence in the ethmoidal sinus, sphenoidal sinus, and frontal sinus. The lack of consensus on the management of sinonasal malignancies is due to their rarity, diagnostic challenges, and the heterogeneity of treatments. In this paper, we present a case of endoscopic-assisted medial canthus incision combined with radiotherapy in the treatment of sinonasal malignant tumors, with the aim of providing valuable insights to clinicians on the management of these tumors.

Ferrofluids are a type of nanometer-scale functional material with fluidity and superparamagnetism. They are composed of ferromagnetic particles, surfactants, and base liquids. The main characteristics of ferrofluids include magnetization, the magnetoviscous effect, and levitation characteristics. There are many mature commercial ferrofluid damping applications based on these characteristics that are widely used in numerous fields. Furthermore, some ferrofluid damping studies such as those related to vibration energy harvesters and biomedical devices are still in the laboratory stage. This review paper summarizes typical ferrofluid dampers and energy harvesting systems from the 1960s to the present, including ferrofluid viscous dampers, ferrofluid inertia dampers, tuned magnetic fluid dampers (TMFDs), and vibration energy harvesters. In particular, it focuses on TMFDs and vibration energy harvesters because they have been the hottest research topics in the ferrofluid damping field in recent years. This review also proposes a novel magnetic fluid damper that achieves energy conversion and improves the efficiency of vibration attenuation. Finally, we discuss the potential challenges and development of ferrofluid damping in future research.