Low-amplitude structure recognition method based on non-subsampled contourlet transform

Currently, horizontal well fracturing is indispensable for shale gas development. Due to the variable reservoir formation morphology, the drilling trajectory often deviates from the high-quality reservoir,which increases the risk of fracturing. Accurately recognizing low-amplitude structures plays a crucial role in guiding horizontal wells. However, existing methods have low recognition accuracy, and are difficult to meet actual production demand. In order to improve the drilling encounter rate of high-quality reservoirs, we propose a method for fine recognition of low-amplitude structures based on the non-subsampled contourlet transform(NSCT). Firstly, the seismic structural data are analyzed at multiple scales and directions using the NSCT and decomposed into low-frequency and high-frequency structural components. Then, the signal of each component is reconstructed to eliminate the low-frequency background of the structure, highlight the structure and texture information, and recognize the low-amplitude structure from it. Finally, we combined the drilled horizontal wells to verify the low-amplitude structural recognition results. Taking a study area in the west Sichuan Basin block as an example, we demonstrate the fine identification of low-amplitude structures based on NSCT. By combining the variation characteristics of logging curves, such as organic carbon content(TOC), natural gamma value(GR), etc., the real structure type is verified and determined, and the false structures in the recognition results are checked. The proposed method can provide reliable information on low-amplitude structures for optimizing the trajectory of horizontal wells. Compared with identification methods based on traditional wavelet transform and curvelet transform, NSCT enhances the local features of low-amplitude structures and achieves finer mapping of low-amplitude structures, showing promise for application.

基于双域Transformer耦合特征学习的CT截断数据重建模型

目的为解决CT扫描视野(FOV)不足导致的截断伪影和图像结构失真问题,本文提出了一种基于投影和图像双域Transformer耦合特征学习的CT截断数据重建模型(DDTrans)。方法基于Transformer网络分别构建投影域和图像域恢复模型,利用Transformer注意力模块的远距离依赖建模能力捕捉全局结构特征来恢复投影数据信息,增强重建图像。在投影域和图像域网络之间构建可微Radon反投影算子层,使得DDTrans能够进行端到端训练。此外,引入投影一致性损失来约束图像前投影结果,进一步提升图像重建的准确性。结果Mayo仿真数据实验结果表明,在部分截断和内扫描两种截断情况下,本文方法DDTrans在去除FOV边缘的截断伪影和恢复FOV外部信息等方面效果均优于对比算法。结论DDTrans模型可以有效去除CT截断伪影,确保FOV内数据的精确重建,同时实现FOV外部数据的近似重建。

Image edge detection based on nonsubsampled contourlet transform and mathematical morphology

A novel algorithm for image edge detection is presented. This algorithm combines the nonsubsampled contourlet transform and the mathematical morphology. First, the source image is decomposed by the nonsubsampled contourlet transform into multi-scale and multi-directional subbands. Then the edges in the high-frequency and low-frequency sub-bands are respectively extracted by the dualthreshold modulus maxima method and the mathematical morphology operator. Finally, the edges from the high- frequency and low-frequency sub-bands are integrated to the edges of the source image, which are refined, and isolated points are excluded to achieve the edges of the source image. The simulation results show that the proposed algorithm can effectively suppress noise, eliminate pseudo-edges and overcome the adverse effects caused by uneven illumination to a certain extent. Compared with the traditional methods such as LoG, Sobel, and Carmy operators and the modulus maxima algorithm, the proposed method can maintain sufficient positioning accuracy and edge details, and it can also make an improvement in the completeness, smoothness and clearness of the outline.

Spectral matching algorithm based on nonsubsampled contourlet transform and scale-invariant feature transform

A new spectral matching algorithm is proposed by us- ing nonsubsampled contourlet transform and scale-invariant fea- ture transform. The nonsubsampled contourlet transform is used to decompose an image into a low frequency image and several high frequency images, and the scale-invariant feature transform is employed to extract feature points from the low frequency im- age. A proximity matrix is constructed for the feature points of two related images. By singular value decomposition of the proximity matrix, a matching matrix （or matching result） reflecting the match- ing degree among feature points is obtained. Experimental results indicate that the proposed algorithm can reduce time complexity and possess a higher accuracy.

基于Transformer的肺肿瘤三维CT图像分割

基于信息学技术自动分割病人的肺部CT图像,有助于医生对于肺癌患者的早期诊断,提取和整合图像区域间的空间关联,对于提升肺肿瘤分割性能是十分重要的。本文提出了一个新的基于Transformer的分割模型,用于肺肿瘤三维CT图像分割、学习和整合此类关联。本文分别设计了带有混合多头图像区域节点注意力的Transformer模块和类别注意力模块,学习并融合了肺部CT图像的空间层面和通道层面的信息。将新的基于Transformer的分割模型同其他较为先进的模型进行了对比实验,实验结果表明新的模型在骰子系数、交并比和豪斯多夫距离等方面优于其他模型。

Directional Filter for SAR Images Based on Nonsubsampled Contourlet Transform and Immune Clonal Selection

A directional filter algorithm for intensity synthetic aperture radar （SAR） image based on nonsubsampled contourlet transform （NSCT） and immune clonal selection （ICS） is presented. The proposed filter mainly focuses on exploiting different features of edges and noises by NSCT. Furthermore, ICS strategy is introduced to optimize threshold parameter and amplify parameter adaptively. Numerical experiments on real SAR images show that there are improvements in both visual effects and objective indexes.

MCIF-Transformer Mask RCNN:Multi-Branch Cross-Scale Interactive Feature Fusion Transformer Model for PET/CT Lung Tumor Instance Segmentation

The precise detection and segmentation of tumor lesions are very important for lung cancer computer-aided diagnosis.However,in PET/CT(Positron Emission Tomography/Computed Tomography)lung images,the lesion shapes are complex,the edges are blurred,and the sample numbers are unbalanced.To solve these problems,this paper proposes a Multi-branch Cross-scale Interactive Feature fusion Transformer model(MCIF-Transformer Mask RCNN)for PET/CT lung tumor instance segmentation,The main innovative works of this paper are as follows:Firstly,the ResNet-Transformer backbone network is used to extract global feature and local feature in lung images.The pixel dependence relationship is established in local and non-local fields to improve the model perception ability.Secondly,the Cross-scale Interactive Feature Enhancement auxiliary network is designed to provide the shallow features to the deep features,and the cross-scale interactive feature enhancement module(CIFEM)is used to enhance the attention ability of the fine-grained features.Thirdly,the Cross-scale Interactive Feature fusion FPN network(CIF-FPN)is constructed to realize bidirectional interactive fusion between deep features and shallow features,and the low-level features are enhanced in deep semantic features.Finally,4 ablation experiments,3 comparison experiments of detection,3 comparison experiments of segmentation and 6 comparison experiments with two-stage and single-stage instance segmentation networks are done on PET/CT lung medical image datasets.The results showed that APdet,APseg,ARdet and ARseg indexes are improved by 5.5%,5.15%,3.11%and 6.79%compared with Mask RCNN(resnet50).Based on the above research,the precise detection and segmentation of the lesion region are realized in this paper.This method has positive significance for the detection of lung tumors.

Feature Extraction of Fabric Defects Based on Complex Contourlet Transform and Principal Component Analysis

To extract features of fabric defects effectively and reduce dimension of feature space,a feature extraction method of fabric defects based on complex contourlet transform （CCT） and principal component analysis （PCA） is proposed.Firstly,training samples of fabric defect images are decomposed by CCT.Secondly,PCA is applied in the obtained low-frequency component and part of highfrequency components to get a lower dimensional feature space.Finally,components of testing samples obtained by CCT are projected onto the feature space where different types of fabric defects are distinguished by the minimum Euclidean distance method.A large number of experimental results show that,compared with PCA,the method combining wavdet low-frequency component with PCA （WLPCA）,the method combining contourlet transform with PCA （CPCA）,and the method combining wavelet low-frequency and highfrequency components with PCA （WPCA）,the proposed method can extract features of common fabric defect types effectively.The recognition rate is greatly improved while the dimension is reduced.

Image Fusion Based on Complex Contourlet Transform and Nonnegative Matrix Factorization

An image fusion method combining complex contourlet transform(CCT) with nonnegative matrix factorization(NMF) is proposed in this paper.After two images are decomposed by CCT,NMF is applied to their highand low-frequency components,respectively,and finally an image is synthesized.Subjective-visual-quality of the image fusion result is compared with those of the image fusion methods based on NMF and the combination of wavelet /contourlet /nonsubsampled contourlet with NMF.The experimental results are evaluated quantitatively,and the running time is also contrasted.It is shown that the proposed image fusion method can gain larger information entropy,standard deviation and mean gradient,which means that it can better integrate featured information from all source images,avoid background noise and promote space clearness in the fusion image effectively.

Segmentation of Head and Neck Tumors Using Dual PET/CT Imaging:Comparative Analysis of 2D,2.5D,and 3D Approaches Using UNet Transformer

The segmentation of head and neck(H&N)tumors in dual Positron Emission Tomography/Computed Tomogra-phy(PET/CT)imaging is a critical task in medical imaging,providing essential information for diagnosis,treatment planning,and outcome prediction.Motivated by the need for more accurate and robust segmentation methods,this study addresses key research gaps in the application of deep learning techniques to multimodal medical images.Specifically,it investigates the limitations of existing 2D and 3D models in capturing complex tumor structures and proposes an innovative 2.5D UNet Transformer model as a solution.The primary research questions guiding this study are:(1)How can the integration of convolutional neural networks(CNNs)and transformer networks enhance segmentation accuracy in dual PET/CT imaging?(2)What are the comparative advantages of 2D,2.5D,and 3D model configurations in this context?To answer these questions,we aimed to develop and evaluate advanced deep-learning models that leverage the strengths of both CNNs and transformers.Our proposed methodology involved a comprehensive preprocessing pipeline,including normalization,contrast enhancement,and resampling,followed by segmentation using 2D,2.5D,and 3D UNet Transformer models.The models were trained and tested on three diverse datasets:HeckTor2022,AutoPET2023,and SegRap2023.Performance was assessed using metrics such as Dice Similarity Coefficient,Jaccard Index,Average Surface Distance(ASD),and Relative Absolute Volume Difference(RAVD).The findings demonstrate that the 2.5D UNet Transformer model consistently outperformed the 2D and 3D models across most metrics,achieving the highest Dice and Jaccard values,indicating superior segmentation accuracy.For instance,on the HeckTor2022 dataset,the 2.5D model achieved a Dice score of 81.777 and a Jaccard index of 0.705,surpassing other model configurations.The 3D model showed strong boundary delineation performance but exhibited variability across datasets,while the 2D model,although effective,generally underperformed compared to its 2.5D and 3D counterparts.Compared to related literature,our study confirms the advantages of incorporating additional spatial context,as seen in the improved performance of the 2.5D model.This research fills a significant gap by providing a detailed comparative analysis of different model dimensions and their impact on H&N segmentation accuracy in dual PET/CT imaging.

结合NSCT变换和引导滤波的多光谱图像全色锐化算法

遥感图像融合技术能够将两幅或多幅多源遥感图像信息进行互补、增强,使图像携带的信息更加准确和全面。非下采样轮廓波变换(nonsubsampled contourlet transform,NSCT)对遥感数字图像进行多尺度多方向分解,有益于提取高分遥感图像细节,从而实现图像的锐化高空间分辨率,但传统NSCT直接生成的高频细节信息过少,且容易产生“虚影”现象。基于此,论文结合NSCT与引导滤波(guided filter,GF),提出了一种新的遥感图像全色锐化融合算法。该算法通过NSCT变换的多尺度多方向分解与重构特性,提取直方图匹配后的图像的细节分量,同时结合GF提取具有全色细节特征的多光谱细节分量,最终通过加权细节信息锐化获得高空-谱融合结果。通过多个高分遥感数据集的主客观评价验证了所提出算法有效性。

CT灌注成像结合血清EPA/AA预测脑白质疏松的急性缺血性脑卒中溶栓后出血转化及短期预后的价值

目的 探讨CT灌注成像(CTP)结合血清二十碳五烯酸(EPA)/花生四烯酸(AA)预测脑白质疏松的急性缺血性脑卒中(AIS)患者溶栓后出血转化及短期预后的价值。方法 选取2021年1月至2022年12月我院神经内科收治的合并脑白质疏松的AIS患者98例为研究对象,根据是否发生溶栓后出血转化分为出血转化组及无出血转化组。采用Fazekas量表评估患者脑白质疏松情况。对比2组患者和出血转化组不同程度脑白质疏松患者CTP参数及EPA/AA。采用受试者工作特征(ROC)曲线评估CTP参数及EPA/AA对发生出血转化的预测价值;根据患者溶栓后1个月的改良Rankin量表(mRS)评分评估预后;采用线性及线性组合评估变量间的线性关系;采用ROC曲线评估CTP参数及EPA/AA对患者短期预后的预测价值。结果 出血转化组患者的相对脑血流量(rCBF)、相对脑血容量(rCBV)及CTP整合指数、EPA/AA明显低于无出血转化组(P<0.05),而相对达峰时间(rTTP)明显长于无出血转化组(P<0.05)。随着脑白质疏松程度增加,患者出血转化发生率增加(P<0.05)。在出血转化组患者中,轻度脑白质疏松患者rCBF、rCBV、CTP整合指数及EPA/AA高于中重度脑白质疏松患者(P<0.05)。轻度脑白质疏松患者中,rCBF及EPA/AA预测出血转化的曲线下面积(AUC)分别为0.712、0.720(P<0.05);对于中重度脑白质疏松患者,rCBF、rCBV、rTTP、CTP整合指数、EPA/AA预测出血转化的AUC分别为0.738、0.714、0.717、0.739、0.742(P<0.05)。98例溶栓患者中,35例患者出现预后不良。rCBF、rCBV、CTP整合指数、EPA/AA预测短期预后的AUC分别为0.742、0.732、0.704、0.738,四者联合预测的AUC为0.968。结论 CTP参数及EPA/AA对合并脑白质疏松的AIS患者溶栓后发生出血转化具有一定的预测价值,rCBV、rCBF、CTP整合指数、EPA/AA是影响此类患者短期预后的重要因素。

复Contourlet域TS-MRF模型的医学CT影像分割

针对CT影像存在伪影、分割困难的问题,提出了复Contourlet域树结构马尔可夫随机场(tree-structured Markov random filed, TS-MRF)的医学CT图像分割算法。采用复Contourlet分析提取CT图像各尺度中的特征信息,特征信息的相关性以其对应标记的相关性表征;其次,相邻尺度间标记的相关性通过构建一阶Markov模型建立联系;尺度内通过构建TS-MRF模型,采用父节点标记对子节点标记的约束以及子节点邻域间标记的相关性描述尺度内节点标记的局部相关性;CT图像特征场通过在每一尺度内构建同标记的高斯模型表征;最后,图像分割的结果通过极大化特征场与标记场联合分布来实现。实验结果表明,相对于空域TS-MRF、小波域TS-MRF、空域马尔科夫随机场(Markov random filed, MRF)、复小波域MRF等4种算法,复域(ontourle, TS-MRF)算法反映分割区域一致性的概率Rand指数(probabilistic rand index, PRI)提高0.091 3以上;同区域分割误差指标全局一致性误差指数(global consistency error, GCE)降低了0.002 8以上;分割边缘连续性指标边界偏移误差指数(boundary displacement error, BDE)降低0.617 9以上;分割后信息丢失指标信息变化指数(variation of information, VoI)降低了0.889 6以上。因此,算法对医学CT图像分割具有较好的区域一致性、分割精度和鲁棒性。

基于非下采样Contourlets的CT/MRI图像自适应融合

结合人类视觉特性,针对CT/MRI医学图像的特点,提出了一种基于非下采样Contourlet变换的图像融合算法。先对源图像作非下采样Contourlet变换,完成图像的多尺度分析和方向分析。充分考虑各尺度分解层的系数特征,对低通子带,基于评价准则最优,采用免疫克隆选择优化策略迭代获取近似最优融合权值;对高通子带则选取绝对值最大作融合。实验结果表明:分别与基于小波、非下采样小波,以及Contourlet的融合结果相比较,文中融合算法获得的融合图像边缘的清晰度,以及整体的对比度都有所改善。

基于Contourlet阈值法的锥形束CT图像去噪研究

目的:将多尺度分析工具之一的Contourlet变换运用到锥形束CT(CBCT)图像去噪领域,并对Contourlet不同阈值去噪方法进行探讨。提出基于Contourlet变换结合半软阈值方法对锥形束CT去噪,并论证去噪效果。方法:利用Contourlet变换的多尺度多方向性以及平移不变性,对低分辨率锥形束CT图像进行拉普拉斯塔形滤波和方向滤波多层分解后得到变换系数,随后对变换系数采用不同阈值方法进行处理,最后逆序反变换得到去噪后图像。通过软阈值和硬阈值方法在Contourlet变换中的应用,提出半软阈值结合Contourlet变换方法对锥形束CT图像去噪。通过对头,胸,盆腔各10例临床锥形束CT图像的去噪,比较三种阈值去噪效果。结果:半软阈值法在胸部和盆腔部锥形束CT图像去噪中比Contourlet硬阈值去噪在PSNR上平均高出1.40 d B和3.11 d B,但在头部锥形束CT图像处理中无优势,而Contourlet软阈值去噪后的锥形束CT图像在消除噪声的同时,信号自身的能量被消弱最多。结论:本文半软阈值法在一定程度上修正了硬,软阈值函数的缺陷,结合Contourlet变换在处理图像几何结构方面的优势,为锥形束CT图像去噪提供了一个新思路。

基于非下采样Contourlet变换的医学CT图像去噪

为克服Contourlet变换的非平移不变性及频谱混叠等缺陷,提出了一种基于非下采样Contourlet变换的医学CT图像去噪方法。对含噪的CT图像进行非下采样Contourlet变换,得到不同尺度及各个方向上的变换系数,利用Context模型将每个尺度每个方向子带分级,不同分级采用相应的阈值去噪。实验表明,该方法适宜于处理含有更多高斯噪声的医学CT图像,与其他方法相比提高了PSNR值,更好地保留了图像细节,改善了医学CT图像的质量。

基于非亚采样Contourlet变换的PET/CT图像融合

提出了一种新的基于非亚采样Contourlet变换的PET/CT图像融合方法。通过非亚采样金字塔(NSP)和非亚采样方向滤波器组(NSDFB)实现对图像的多尺度多方向分解。在融合处理中,对分解图像所得的高频及低频系数,根据不同分解面的特性,采用不同的加权规则进行融合。该方法既保留了Contourlet变换方法的多分辨率特性,又具有平移不变性。实验结果表明,相对于传统的拉普拉斯金字塔变换法、小波变换法和Contourlet变换法等,取得了更佳的融合效果。

基于Contourlet变换的图像DCT去噪新方法

为了改进滤波效果,以提高图像去噪质量,提出了一种通过离散余弦变换对contourlet域中噪声能量进行估计来实现去噪的新方法。该算法不依赖于对噪声方差进行估计,而是直接利用离散余弦变换来对高频各子带进行局部特征提取,以便估计噪声能量的估计阈值。实验结果表明,与传统的小波软、硬阈值去噪方法和基于小波变换的图像离散余弦变换去噪方法比较,该方法有效地克服了采用硬阈值法引起的伪吉布斯现象和软阈值法因导致过度光滑而使信号失真等缺点。实验表明,该算法不仅可提高处理图像的信噪比,而且图像的视觉效果也明显改善,因此更具有实用价值。

基于Contourlet变换的CT和锥形束CT图像配准算法

目的提出一种基于Contourlet变换,用于放射治疗定位的CT与锥形束CT(cone beam CT,CBCT)图像配准的方法。方法利用Contourlet变换多尺度多方向的分辨特性,将待配准图像进行Contourlet变换分解,分解后的高频方向子带合成梯度图像,采用归一化互信息作为相似性测度,把梯度图像与低频方向子带以加权函数结合,进行临床医学图像的刚性配准,有效弥补了互信息配准中缺少空间信息的不足。结果通过已知空间变换参数图像的配准结果验证了算法的准确性。配准后10幅图像变换参数的误差极小,且均方根误差接近于0。结论该图像配准算法精确度高,并具有很好的鲁棒性,有助于提高图像引导放射治疗(image guided radiation therapy,IGRT)中解剖组织结构和靶区的定位精度。

基于Contourlet变换和DCT量化的零水印算法

提出一种基于Contourlet变换和DCT量化的数字图像零水印算法。对原始载体图像进行Contourlet变换,对其低频逼近子图进行分块DCT变换,并将系数值的量化结果和置乱后的水印图像进行一定运算得到构造图像,再加密成密钥图像。密钥图像被用来提取水印。实验仿真结果表明,该算法比较简单,不可觉察性很好,有较强的鲁棒性。