中铁西北科学研究院有限公司

Objective Medical image fusion integrates lesion features and complementary information from different modalities,offering a comprehensive and accurate description of medical images for clinical diagnosis.Traditional methods often result in reduced contrast and spectral degradation due to differences between multimodal images.Frequency-domain techniques mitigate these issues but rely on manually designed feature extraction and fusion rules,lacking robustness and adaptability.While deep learning-based fusion methods,such as convolutional neural networks and Transformer,have shown promising results in feature extraction and reconstruction,they often overlook complementary characteristics between modalities,leading to insufficient global information capture.Although frequency-domain methods preserve high-frequency information,they fail to adequately correlate global and local features,neglecting unique aspects of each modality and resulting in excessive smoothing and blurring.This study proposes an adaptive medical image fusion method based on cross-modality perception and spatial-frequency interaction. Methods An adaptive medical image fusion network combining cross-modality perception with spatial-frequency interaction was developed.First,a cross-modality perceptual module utilizing channel and coordinate attention mechanisms extracts multiscale deep features and local abnormality information,reducing information loss between modalities.Second,a spatial-frequency cross-fusion module based on frequency information exchange and spatial domain adaptive cross-fusion was proposed.This module alleviates information imbalance between modalities by exchanging phase information in the frequency domain and dynamically learning global interaction features in the spatial domain.This process highlights prominent targets while preserving critical pathological information and texture details.Finally,a loss function comprising content,structure,and spectral terms was designed to further improve the quality of the fused image. Results and Discussions Fusion experiment for mild Alzheimer's disease demonstrates that the proposed method better preserves positron emission tomography functional information and edge details of magnetic resonance imaging(MRI)soft tissue,improving image contrast and detail presentation compared to other methods.The fusion experiment for metastatic bronchogenic carcinoma shows that other methods suffer from low resolution,blurred textures,and noise interference,hindering the observation and diagnosis of the lesion area.In contrast,the proposed method effectively retains single-photon emission computed tomography metabolic information and MRI soft tissue edge details,enabling doctors to comprehensively evaluate lesion status.The sarcoma fusion experiment further validates the algorithm's effectiveness in preserving tissue edges,grayscale information,and density structure integrity.From tables 1-3,the AG(average gradient),MI(mutual information),SF(spatial frequency),QAB/F(fusion quality),CC(correlation coefficient),and VIF(visual information fidelity)indicators demonstrate strong performance.Specifically,the high MI value indicates that the fusion image contains rich features and edge information.The high SF value shows that the fusion image retains additional global information from the source images,with clear details and texture features.The high VIF value reflects consistency with the human eye's visual characteristics,while the high QAB/F value indicates that the fusion image maintains spatial details consistent with the source images.Compared with other algorithms,the proposed method emphasizes the perception and interaction of structural image texture contours and functional image metabolic brightness during feature extraction and fusion,addressing issues such as structural edge loss and lesion detail blurring in existing fusion methods. Conclusions To enhance the quality of multimodal medical image fusion,this study proposes a method combining cross-modality perception with spatial-frequency interaction.During feature extraction,a multiscale cross-modality perception network facilitates the interaction of structural and functional information,fully extracting source image data and enhancing local lesion features.In the fusion stage,functional and anatomical key information is preserved through frequency-domain exchange,followed by cross-attention for adaptive fusion,ensuring that detailed texture and overall edge profile information are fully fused.Additionally,content,structural,and spectral losses were designed to retain complementary and chromatic information.Experimental results demonstrate that the proposed method improves AG,MI,SF,QAB/F,CC,and VIF by 4.4％,13.2％,2.7％,3.4％,11％,and 3％,respectively,showing that the method effectively retains unique information from each modality,resulting in fusion images with clear edges,rich lesion details,and high visual fidelity.In the task of fusing multimodal medical images of the abdomen with green fluorescent protein and phase contrast images,the proposed method demonstrates strong generalization,supporting its potential for application in other biomedical diagnostic tasks and enhancing clinicians' diagnostic efficiency.

The recommended calculation method for the anti-overturning stability of gravity retaining walls in the current technical specifications of various engineering industries is problematic. In order to clarify this issue, the resultant moment theorem is a dopted to derive the correct formula for anti-overturning stability calculation. Then, the derived formula and the formula recommended by the specifications are used as examples for calculation, and the calculation results are presented in graphs and tables for comparison. The results show that according to the methods of current technical specifications for calculating the anti-overturning stability of forward inclined, vertical, and small angle backward inclined retaining walls, when the wall height is small, the result tended to be conservative, which could cause waste, and when the wall height is large, the project would fall into a dangerous situation; When calculating large angle backward inclined retaining walls, the project might be in a dangerous situation. Finally, based on this, suggestions for revising the formula of current technical specifications are proposed.

Objective Medical image registration is a spatial transformation process that aligns and matches the specific spatial structures contained in two medical images. It has been applied in disease detection, surgical diagnosis and treatment, and other fields. Traditional medical image registration methods are slow and computationally expensive. In recent years, researchers have made significant breakthroughs in medical image registration research using deep learning methods. Deep learning methods have increased the registration speed by hundreds of times, with a registration accuracy comparable to those of traditional methods. However, most patients have complex pathological conditions and lesions grow quickly, resulting in significant differences in the images collected at different stages. Existing deep learning-based registration methods have low registration accuracy and poor generalization performance when used for medical images of large deformations. Therefore, a multi-scale constraint network (MC-Net) for large-deformation 3D medical image registration Based on multi-scale constraints is proposed. Methods We propose a multi-scale constraint network (MC-Net) for large-deformation 3D medical image registration based on multi-scale constraints. Three multi-kernel (MK) modules are designed as parallel multi-channel and multi-convolution kernels for the encoder to accelerate the training speed. A convolutional block attention module (CBAM) is added to skip connections and enhance the ability to extract complex semantic information and fine-grained feature information from large-deformation images. In order to improve the registration accuracy, MC-Net combines multi-scale constrained loss functions to implement a layer-by-layer optimization strategy from low resolution to high resolution. Results and Discussions In an experiment, three publicly available 3D datasets (OASIS, LPBA40, and Abdomen CT-CT, with two modalities) were used for registration research. The effectiveness of MC-Net was demonstrated through original experiments, traditional comparison methods, deep learning comparison methods , ablation experiments, and multi-core fusion experiments. Based on the registration results shown in Figs. 5 and 6, MC-Net performed well in the registration of the OASIS and LPBA40 brain datasets, as well as for the Abdomen CT-CT abdominal dataset. In the brain image comparison experiment, the LPBA40 brain dataset was compared with a traditional registration method (ANTs) and three deep learning registration methods (VoxelMorph, CycleMorph, and TransMorph) in the same experimental environment. It was found that MC-Net outperformed the other methods in terms of detail registration in brain regions and overall brain contour deformation. The abdominal image comparison experiment compared two traditional methods (ANTs and Elastix) and two deep learning methods (VoxelMorph and TransMorph). It was found that MC-Net had some shortcomings in organ generation and contour deformation, but had better registration performance than the other methods in terms of blank area size and individual organ deformation. The ablation experiment was conducted using the LPBA40 dataset. It demonstrated the different roles of the MK and CBAM modules in processing medical images in MC-Net, which helped to improve the registration accuracy. In addition, this article also discusses the computational complexity of MC-Net. For For large target images such as medical images, this article discusses how a multi-kernel (MK) fusion module can be designed to effectively reduce the computational complexity. Conclusions In response to the low accuracy and poor generalization performance of current large-deformation image registration methods, this paper proposes a medical image registration network (MC-Net) based on multi-scale constraints, with LPBA40, OASIS, and Abdomen CT-CT medical image datasets used as research objects. Information loss can be avoided by designing CBAM modules in skip connections to enhance the ability to extract differential information from large-deformation images. In addition, considering the slow registration speed caused by the large number of parameters when processing large-deformation images, the MK module was designed with a parallel path large kernel convolution structure to improve the registration speed without affecting registration accuracy. When combined with the multi-scale constraint loss function proposed in this article, it iteratively optimizes the deformation fields at three scales from low resolution to high resolution to improve the registration accuracy. The experimental results show that compared with other methods, this method has improved registration accuracy, speed, and computational complexity. The good registration performances in three datasets with MRI and CT modalities demonstrate the generalization ability of our method. Subsequent research will focus on designing an adaptive adjustment module for multi-scale constrained loss function hyperparameters, in order to solve the problem of the time-consuming hyperparameter tuning needed for loss functions in experiments and improve the experimental efficiency. In summary, MC-Net has practical value in the registration of large-deformation images.

In borehole monitoring for deep displacement, the abrupt characteristics of inclinometer curves are the key basis for identifying the sliding surface. Previous studies have summarized several types of inclinometer curve patterns that exhibit significant sliding surface signals, including "B," "D," and "r" types. For "D" type inclinometer curves, the convex point of the curve is typically used as the position of the sliding surface. However, this method is susceptible to the influence of observation points spacing and coordinate observation scales, which can result in an unclear definition of the sliding surface position and uncertain numerical values. To overcome these drawbacks and improve the accuracy of sliding surface identification in inclinometer curves, a generalized model of landslides composed of “sliding body”, “sliding interval,” and “immovable body” was developed based on the variation characteristics of the "D" type inclinometer curve. A mechanical strut model subjected to external loads was established based on the different flexural rigidity of the three members, and the deformation characteristics of soil at different depths during landslide movement were analyzed in depth. The study found that the sliding surface of "D" curve does not entirely penetrate, leading to continuous soil deformation along the depth direction without abrupt change. The demarcation point of the positive and negative bending moments in the mechanical model is a location where the horizontal displacement of deformation curve is the largest, which can reflect the real deformation characteristics of the landslide and the position of the sliding surface. By converted the accumulated soil displacement into relative displacement, the "D" type inclinometer curve is transformed into "S" type relative displacement-depth curve, and the inflection point of the "S" type curve is close to the position of the sliding surface. By extracting the average relative displacement of soil at different depths during the monitoring period and calculating the depth value of the inflection point in the "S" type segment by using the cubic spline interpolation method, the position of the sliding surface can be determined more accurately, which can greatly improve the reliability and accuracy of deep displacement monitoring and has significant practical value.

In this paper,five dangerous rockfall collapses at K1515 of the Shanghai-Chengdu expressway are taken as the research object.Through investigation,statistics,and analysis,the engineering geological conditions and developmental deformation characteristics of the dangerous rockfall collapse area are clarified.The research results show that:(1)the failure modes of dangerous rock masses W1 and W2 are misbreaking and cracking,the destruction mode of W3-1 dangerous rock mass is dumping,the destruction mode of W3-2 dangerous rock mass is sliding,and the destruction mode of W4 and W5 is bulging;(2)the stability coefficient of W1 and W2 is 1.12 and 1.61 respectively,which are in basically stable～stable state;the stability coefficient of dumping failure of W3-1 is 0.41 and in unstable state;the stability coefficient of sliding failure of W3-2 in W 3-2 is greater than 1.35 and in stable state;under rainstorm condition;the stability coefficient of bulging deformation of W4 and W5 is 1.25 and 1.15 respectively,which are in basically stable state;(3)The authors summarize the governance strategy of"reduce risk,minimize disturbance,ensure safe stability and feasible technology",and adopt comprehensive remidiation measures of"embedding concrete retaining wall at the toe of slope+local active SNS network protection+prestressed anchor protection",and the treatment effect was good.It can provide reliable reference basis for the treatment measures of dangerous rock collapse.