Explore the vast range of titles available.

The morphological analysis and volume measurement of the hippocampus are crucial to the study of many brain diseases. Therefore, an accurate hippocampal segmentation method is beneficial for the development of clinical research in brain diseases. U-Net and its variants have become prevalent in hippocampus segmentation of Magnetic Resonance Imaging (MRI) due to their effectiveness, and the architecture based on Transformer has also received some attention. However, some existing methods focus too much on the shape and volume of the hippocampus rather than its spatial information, and the extracted information is independent of each other, ignoring the correlation between local and global features. In addition, many methods cannot be effectively applied to practical medical image segmentation due to many parameters and high computational complexity. To this end, we combined the advantages of CNNs and ViTs (Vision Transformer) and proposed a simple and lightweight model: Light3DHS for the segmentation of the 3D hippocampus. In order to obtain richer local contextual features, the encoder first utilizes a multi-scale convolutional attention module (MCA) to learn the spatial information of the hippocampus. Considering the importance of local features and global semantics for 3D segmentation, we used a lightweight ViT to learn high-level features of scale invariance and further fuse local-to-global representation. To evaluate the effectiveness of encoder feature representation, we designed three decoders of different complexity to generate segmentation maps. Experiments on three common hippocampal datasets demonstrate that the network achieves more accurate hippocampus segmentation with fewer parameters. Light3DHS performs better than other state-of-the-art algorithms. •A lightweight network called Light3DHS is proposed for 3D hippocampus segmentation.•Light3DHS effectively combines the characteristics of CNN and Transformer paradigms.•Light3DHS utilizes multi-scale attention to fuse features from local to global.•Results from the decoders demonstrate the effectiveness of encoder.•Light3DHS can deeply understand and precisely segment 3D hippocampus.

Pests are a major cause of crop loss globally, and accurate pest identification is crucial for effective prevention and control strategies. This paper proposes a novel deep-learning architecture for crop pest classification, addressing the limitations of existing methods that struggle with distinguishing the fine details of pests and background interference. The proposed model is designed to balance fine-grained feature extraction with deep semantic understanding, utilizing a parallel structure composed of two main components: the Feature Fusion Module (FFM) and the Mixed Attention Module (MAM). FFM focuses on extracting key fine-grained features and fusing them across multiple scales, while MAM leverages an attention mechanism to model long-range dependencies within the channel domain, further enhancing feature representation. Additionally, a Transformer block is integrated to overcome the limitations of traditional convolutional approaches in capturing global contextual information. The proposed architecture is evaluated on three benchmark datasets—IP102, D0, and Li—demonstrating its superior performance over state-of-the-art methods. The model achieves accuracies of 75.74% on IP102, 99.82% on D0, and 98.77% on Li, highlighting its robustness and effectiveness in complex crop pest recognition tasks. These results indicate that the proposed method excels in multi-scale feature fusion and long-range dependency modeling, offering a new competitive approach to pest classification in agricultural settings.

In the radargram obtained by the high-frequency lunar penetrating radar onboard the Chang’E-3 mission, we notice a potential subsurface cavity that has a smaller permittivity compared to the surrounding materials. The two-way travel time between the top and bottom boundaries of the potential cavity is ~ 21 ns, and the entire zone is located within the continuous ejecta deposits of the Ziwei crater, which generally have similar physical properties to typical lunar regolith. We carried out numerical simulations for electromagnetic wave propagation to investigate the nature of this low-permittivity zone. Assuming different shapes for this zone, a comprehensive comparison between our model results and the observed radargram suggests that the roof of this zone is convex and slightly inclined to the south. Modeling subsurface materials with different relative permittivities suggests that the low-permittivity zone is most likely formed due to a subsurface cavity. The maximum vertical dimension of this potential cavity is ~ 3.1 m. While the continuous ejecta deposits of Ziwei crater are largely composed of pre-impact regolith, competent mare basalts were also excavated, which is evident by the abundant meter-scale boulders on the wall and rim of Ziwei crater. We infer that the subsurface cavity is supported by excavated large boulders, which were stacked during the energetic emplacement of the continuous ejecta deposits. However, the exact geometry of this cavity (e.g., the width) cannot be constrained using the single two-dimensional radar profile. This discovery indicates that large voids formed during the emplacement of impact ejecta should be abundant on the Moon, which contributes to the high bulk porosity of the lunar shallow crust, as discovered by the GRAIL mission. Our results further suggest that ground penetrating radar is capable of detecting and deciphering subsurface cavities such as lava tubes, which can be applied in future lunar and deep space explorations.

The Moon has a magmatic and thermal history that is distinct from that of the terrestrial planets 1 . Radioisotope dating of lunar samples suggests that most lunar basaltic magmatism ceased by around 2.9–2.8 billion years ago (Ga) 2 , 3 , although younger basalts between 3 Ga and 1 Ga have been suggested by crater-counting chronology, which has large uncertainties owing to the lack of returned samples for calibration 4 , 5 . Here we report a precise lead–lead age of 2,030 ± 4 million years ago for basalt clasts returned by the Chang’e-5 mission, and a 238 U/ 204 Pb ratio ( µ value) 6 of about 680 for a source that evolved through two stages of differentiation. This is the youngest crystallization age reported so far for lunar basalts by radiometric dating, extending the duration of lunar volcanism by approximately 800–900 million years. The µ value of the Chang’e-5 basalt mantle source is within the range of low-titanium and high-titanium basalts from Apollo sites ( µ value of about 300–1,000), but notably lower than those of potassium, rare-earth elements and phosphorus (KREEP) and high-aluminium basalts 7 ( µ value of about 2,600–3,700), indicating that the Chang’e-5 basalts were produced by melting of a KREEP-poor source. This age provides a pivotal calibration point for crater-counting chronology in the inner Solar System and provides insight on the volcanic and thermal history of the Moon. Basalt samples returned from the Moon by the Chang’e-5 mission are revealed to be two billion years old by radioisotopic dating, providing insight on the volcanic history of the Moon.

Complex oxide heterointerfaces and van der Waals heterostructures present two versatile but intrinsically different platforms for exploring emergent quantum phenomena and designing new functionalities. The rich opportunity offered by the synergy between these two classes of materials, however, is yet to be charted. Here, we report an unconventional nonlinear optical filtering effect resulting from the interfacial polar alignment between monolayer MoS 2 and a neighboring ferroelectric oxide thin film. The second harmonic generation response at the heterointerface is either substantially enhanced or almost entirely quenched by an underlying ferroelectric domain wall depending on its chirality, and can be further tailored by the polar domains. Unlike the extensively studied coupling mechanisms driven by charge, spin, and lattice, the interfacial tailoring effect is solely mediated by the polar symmetry, as well explained via our density functional theory calculations, pointing to a new material strategy for the functional design of nanoscale reconfigurable optical applications. The heterointerface between complex oxides and van der Waals materials presents a versatile platform for exploring new functionalities. Here, the authors report an unconventional nonlinear optical filtering effect resulting from the interfacial polar alignment between monolayer MoS 2 and a ferroelectric oxide thin film.

Pest infestation is a major cause of crop losses and a significant factor contributing to agricultural economic damage. Accurate identification of pests is therefore critical to ensuring crop safety. However, existing pest recognition methods often struggle to distinguish fine-grained visual differences between pest species and are susceptible to background interference from crops and environments. To address these challenges, we propose an improved pest identification method based on the Swin Transformer architecture, named Swin-AARNet (Attention Augmented Residual Network). Our method achieves efficient and accurate pest recognition. On the one hand, Swin-AARNet enhances local key features and establishes a feature complementation mechanism, thereby improving the extraction capability of local features. On the other hand, it integrates multi-scale information to effectively alleviate the problem of fine-grained feature ambiguity or loss. Furthermore, Swin-AARNet attained a classification accuracy of 78.77% on IP102, the largest publicly available pest dataset to date. To further validate its effectiveness and generalization ability, we conducted additional training and evaluation on the citrus benchmark dataset CPB and Li, achieving impressive accuracies of 82.17% and 99.48%, respectively. SwinAARNet demonstrates strong capability in distinguishing pests with highly similar appearances while remaining robust against complex and variable backgrounds. This makes it a promising tool for enhancing agricultural safety management, including crop environment monitoring and early invasion warning. Compared with other state-of-the-art models, our proposed method exhibits superior performance in pest image classification tasks, highlighting its potential for real-world agricultural applications.

The present work aims to reduce tunnel construction accidents to personnel. The threshold adaptive segmentation algorithm combined with the Canny operator is employed to extract and detect the cracks on the rock mass of the tunnel face from digital images of the tunnel face. Firstly, the gray change processing and histogram equalization technology of the image processing algorithm enhance the contrast of the digital image of rock mass on the tunnel face. Then, the Canny operator and OTSU method construct a threshold adaptive segmentation algorithm to segment the rock mass crevice image after increasing the contrast and to classify crevices on the tunnel face into streak cracks and irregular cracks. Secondly, the segmented image is corrupted, extended, and refined; meanwhile, boundary fitting, separation, merging, and filtering are carried out to form a relatively complete rock boundary recognition result. Finally, the streak crevices and irregular crevices are detected according to the crevice geometry and pixel distribution characteristics to determine the crack direction. The experimental results show that this method can extract complete rock cracks with less than a 2% extraction error rate. Besides, the detection rates of the algorithm for the streak crevices and irregular crevices are 97% and 94%, respectively, and the detection accuracy of the crevice direction is 98%. This indicates that the algorithm proposed here is applicable to geological sketch and provides a reference for the classification of surrounding rock on the tunnel face.

The joints are existing throughout the underground rock mass. It is of great significance to investigate the shear performance of the rock mass to maintain the stability of the underground structure. In this study, we conducted orthogonal tests to determine the proportion of rock-like materials, and used JRC curves to make specimen molds and then prepare the specimens. We conducted straight shear tests and uniaxial compression tests to determine the various mechanical parameters of the rock-like materials. Next, we carried out the compression and shear tests to investigate the shear characteristics of the specimens, and study the damage pattern and shear strength of the jointed rock mass under different confining pressures and roughness levels. The mesoscopic displacements in the shear process of joints were analyzed by using ABAQUS. The test results show that the effect of the confining pressure on the shear strength of the joint plane is relatively obvious, and a larger confining pressure indicates a larger shear strength. The effects of different joint plane roughness and shear rated on the shear characteristics of the joint plane are also significant. The mesoscopic displacement difference inside the joint plane with higher roughness is relatively large, and the stress concentration phenomenon is obvious and lasts longer, which leads to the faster destruction of the specimen with higher roughness and the higher destruction degree. Therefore, we suggest that the priority should be given to the reinforcement of jointed rock mass with high roughness during the construction to prevent sudden destabilization and failure.

Impact ejecta are important references to establish regional and global stratigraphy of planetary bodies. Canonical views advocate radial distributions of distal ejecta with respect to the source crater, and their trajectories are significantly deflected on fast-rotating bodies. The Hokusai crater on Mercury formed a peculiar ray that features a hyperbola shape, and the sharp swerve of orientation was interpreted as a sign of a faster planetary rotation in the near past. Here, we show that this ray was not caused by a hypothesized larger Coriolis force, but due to abruptly-steepened ejection angles. Heterogeneous shock impedances of pre-impact impactor and/or target, such as topographic undulations, affect local propagation paths of shock and rarefaction waves, causing sudden changes of ejection angles. Distal ejecta with non-radial distributions are an inherent product of planetary impacts, and their unobvious provenances could mislead stratigraphic interpretations and hamper age estimations based on spatial densities of impact craters. Heterogeneous shock impedances of planetary materials cause abrupt changes of ejection angles, forming non-radial ejecta. Interpretations for provenances of surface deposits and ages derived from crater counts are affected by such untrackable ejecta.

To quickly determine the blasting block degree and conduct an accurate and objective analysis of the tunnel blasting effect, this study has enhanced and improved upon the traditional genetic algorithm and Otsu algorithm. It has combined it with the marking watershed method and utilized ground digital acquisition to capture images of blasting debris. These images are then used in our custom-developed blasting analysis software to calculate the blasting block degree distribution and provide a quantitative analysis of blasting block degree. The research results show that the optimized image segmentation algorithm effectively improves the traditional threshold segmentation method on the poor effect of segmentation of the edge of the adherent block or the direct application of the watershed segmentation of the over-segmentation problem, to improve the segmentation accuracy based on the new segmentation technology is close to the traditional technology in terms of time. Through the self-developed software, the construction personnel in the project site to quickly obtain the blasting block degree histogram, block degree cumulative curve and other important indicators of the evaluation of the effect of blasting block degree, to provide data support for on-site construction, to assist in the modification of the blasting program, and to improve the efficiency of construction. This study realizes the rapid detection and block identification of blasting blocks, provides data support for the optimization of blasting parameters, and has good application and promotion value.