DCFNet:An Effective Dual-Branch Cross-Attention Fusion Network for Medical Image Segmentation

Automatic segmentation of medical images provides a reliable scientific basis for disease diagnosis and analysis.Notably,most existing methods that combine the strengths of convolutional neural networks(CNNs)and Transformers have made significant progress.However,there are some limitations in the current integration of CNN and Transformer technology in two key aspects.Firstly,most methods either overlook or fail to fully incorporate the complementary nature between local and global features.Secondly,the significance of integrating the multiscale encoder features from the dual-branch network to enhance the decoding features is often disregarded in methods that combine CNN and Transformer.To address this issue,we present a groundbreaking dual-branch cross-attention fusion network(DCFNet),which efficiently combines the power of Swin Transformer and CNN to generate complementary global and local features.We then designed the Feature Cross-Fusion(FCF)module to efficiently fuse local and global features.In the FCF,the utilization of the Channel-wise Cross-fusion Transformer(CCT)serves the purpose of aggregatingmulti-scale features,and the Feature FusionModule(FFM)is employed to effectively aggregate dual-branch prominent feature regions from the spatial perspective.Furthermore,within the decoding phase of the dual-branch network,our proposed Channel Attention Block(CAB)aims to emphasize the significance of the channel features between the up-sampled features and the features generated by the FCFmodule to enhance the details of the decoding.Experimental results demonstrate that DCFNet exhibits enhanced accuracy in segmentation performance.Compared to other state-of-the-art(SOTA)methods,our segmentation framework exhibits a superior level of competitiveness.DCFNet’s accurate segmentation of medical images can greatly assist medical professionals in making crucial diagnoses of lesion areas in advance.

U-Net Based Dual-Pooling Segmentation of Bone Metastases in Thoracic SPECT Bone Scintigrams

In order to enhance the performance of the CNN-based segmentation models for bone metastases, this study proposes a segmentation method that integrates dual-pooling, DAC, and RMP modules. The network consists of distinct feature encoding and decoding stages, with dual-pooling modules employed in encoding stages to maintain the background information needed for bone scintigrams diagnosis. Both the DAC and RMP modules are utilized in the bottleneck layer to address the multi-scale problem of metastatic lesions. Experimental evaluations on 306 clinical SPECT data have demonstrated that the proposed method showcases a substantial improvement in both DSC and Recall scores by 3.28% and 6.55% compared the baseline. Exhaustive case studies illustrate the superiority of the methodology.

Functional Pattern-Related Anomaly Detection Approach Collaborating Binary Segmentation with Finite State Machine

The process control-oriented threat,which can exploit OT(Operational Technology)vulnerabilities to forcibly insert abnormal control commands or status information,has become one of the most devastating cyber attacks in industrial automation control.To effectively detect this threat,this paper proposes one functional pattern-related anomaly detection approach,which skillfully collaborates the BinSeg(Binary Segmentation)algorithm with FSM(Finite State Machine)to identify anomalies between measuring data and control data.By detecting the change points of measuring data,the BinSeg algorithm is introduced to generate some initial sequence segments,which can be further classified and merged into different functional patterns due to their backward difference means and lengths.After analyzing the pattern association according to the Bayesian network,one functional state transition model based on FSM,which accurately describes the whole control and monitoring process,is constructed as one feasible detection engine.Finally,we use the typical SWaT(Secure Water Treatment)dataset to evaluate the proposed approach,and the experimental results show that:for one thing,compared with other change-point detection approaches,the BinSeg algorithm can be more suitable for the optimal sequence segmentation of measuring data due to its highest detection accuracy and least consuming time;for another,the proposed approach exhibits relatively excellent detection ability,because the average detection precision,recall rate and F1-score to identify 10 different attacks can reach 0.872,0.982 and 0.896,respectively.

Enhanced Feature Fusion Segmentation for Tumor Detection Using Intelligent Techniques

In thefield of diagnosis of medical images the challenge lies in tracking and identifying the defective cells and the extent of the defective region within the complex structure of a brain cavity.Locating the defective cells precisely during the diagnosis phase helps tofight the greatest exterminator of mankind.Early detec-tion of these defective cells requires an accurate computer-aided diagnostic system(CAD)that supports early treatment and promotes survival rates of patients.An ear-lier version of CAD systems relies greatly on the expertise of radiologist and it con-sumed more time to identify the defective region.The manuscript takes the efficacy of coalescing features like intensity,shape,and texture of the magnetic resonance image(MRI).In the Enhanced Feature Fusion Segmentation based classification method(EEFS)the image is enhanced and segmented to extract the prominent fea-tures.To bring out the desired effect the EEFS method uses Enhanced Local Binary Pattern(EnLBP),Partisan Gray Level Co-occurrence Matrix Histogram of Oriented Gradients(PGLCMHOG),and iGrab cut method to segment image.These prominent features along with deep features are coalesced to provide a single-dimensional fea-ture vector that is effectively used for prediction.The coalesced vector is used with the existing classifiers to compare the results of these classifiers with that of the gen-erated vector.The generated vector provides promising results with commendably less computatio nal time for pre-processing and classification of MR medical images.

Defocus Blur Segmentation Using Local Binary Patterns with Adaptive Threshold

Enormousmethods have been proposed for the detection and segmentation of blur and non-blur regions of the images.Due to the limited available information about blur type,scenario and the level of blurriness,detection and segmentation is a challenging task.Hence,the performance of the blur measure operator is an essential factor and needs improvement to attain perfection.In this paper,we propose an effective blur measure based on local binary pattern(LBP)with adaptive threshold for blur detection.The sharpness metric developed based on LBP used a fixed threshold irrespective of the type and level of blur,that may not be suitable for images with variations in imaging conditions,blur amount and type.Contrarily,the proposed measure uses an adaptive threshold for each input image based on the image and blur properties to generate improved sharpness metric.The adaptive threshold is computed based on the model learned through support vector machine(SVM).The performance of the proposed method is evaluated using two different datasets and is compared with five state-of-the-art methods.Comparative analysis reveals that the proposed method performs significantly better qualitatively and quantitatively against all of the compared methods.

Automatic image segmentation method for cotton leaves with disease under natural environment

In order to improve the image segmentation performance of cotton leaves in natural environment, an automatic segmentation model of diseased leaf with active gradient and local information is proposed. Firstly, a segmented monotone decreasing edge composite function is proposed to accelerate the evolution of the level set curve in the gradient smooth region. Secondly, canny edge detection operator gradient is introduced into the model as the global information. In the process of the evolution of the level set function, the guidance information of the energy function is used to guide the curve evolution according to the local information of the image, and the smooth contour curve is obtained. And the main direction of the evolution of the level set curve is controlled according to the global gradient information, which effectively overcomes the local minima in the process of the evolution of the level set function. Finally, the Heaviside function is introduced into the energy function to smooth the contours of the motion and to increase the penalty function Φ(x) to calibrate the deviation of the level set function so that the level set is smooth and closed. The results showed that the model of cotton leaf edge profile curve could be obtained in the model of cotton leaf covered by bare soil, straw mulching and plastic film mulching, and the ideal edge of the ROI could be realized when the light was not uniform. In the complex background, the model can segment the leaves of the cotton with uneven illumination, shadow and weed background, and it is better to realize the ideal extraction of the edge of the blade. Compared with the Geodesic Active Contour(GAC) algorithm, Chan-Vese(C-V) algorithm and Local Binary Fitting(LBF) algorithm, it is found that the model has the advantages of segmentation accuracy and running time when processing seven kinds of cotton disease leaves images, including uneven lighting, leaf disease spot blur, adhesive diseased leaf, shadow, complex background, unclear diseased leaf edges, and staggered condition. This model can not only conduct image segmentation of cotton leaves under natural conditions, but also provide technical support for the accurate identification and diagnosis of cotton diseases.

Image Segmentation: A Novel Cluster Ensemble Algorithm

Cluster ensemble has testified to be a good choice for addressing cluster analysis issues, which is composed of two processes: creating a group of clustering results from a same data set and then combining these results into a final clustering results. How to integrate these results to produce a final one is a significant issue for cluster ensemble. This combination process aims to improve the quality of individual data clustering results. A novel image segmentation algorithm using the Binary k-means and the Adaptive Affinity Propagation clustering (CEBAAP) is designed in this paper. It uses a Binary k-means method to generate a set of clustering results and develops an Adaptive Affinity Propagation clustering to combine these results. The experiments results show that CEBAAP has good image partition effect.

A variational formulation for physical noised image segmentation

Image segmentation is a hot topic in image science. In this paper we present a new variational segmentation model based on the theory of Mumford-Shah model. The aim of our model is to divide noised image, according to a certain criterion, into homogeneous and smooth regions that should correspond to structural units in the scene or objects of interest. The proposed region-based model uses total variation as a regularization term, and different fidelity term can be used for image segmentation in the cases of physical noise, such as Gaussian, Poisson and multiplicative speckle noise. Our model consists of five weighted terms, two of them are responsible for image denoising based on fidelity term and total variation term, the others assure that the three conditions of adherence to the data, smoothing, and discontinuity detection are met at once. We also develop a primal-dual hybrid gradient algorithm for our model. Numerical results on various synthetic and real images are provided to compare our method with others, these results show that our proposed model and algorithms are effective.

DFNet:高效的无解码语义分割方法

针对编解码语义分割网络计算量大、解码结构复杂的问题,提出一种高效无解码的二值语义分割模型DFNet。该模型首先去除主流分割网络中复杂的解码结构和跳跃连接,采用卷积重塑上采样方法重塑特征编码直接得到分割结果,简化网络模型结构;其次在编码器中融合轻量双重注意力机制EC&SA,提高特征编码的通道及空间信息交互,增强网络的编码能力;最后使用PolyCE损失替代常规分割损失,解决正负样本不均衡问题,提高模型的分割精度。在Deep‑Globe道路分割和CrackForest缺陷检测等二值分割数据集上的实验结果表明,本文模型的分割精度F1均值和IoU均值分别达到84.69%和73.95%,且分割速度高达94 FPS,远超主流语义分割模型,极大地提高了分割任务效率。

双通道特征融合的真实场景点云语义分割方法

真实场景点云不仅具有点云的空间几何信息,还具有三维物体的颜色信息,现有的网络无法有效利用真实场景的局部特征以及空间几何特征信息,因此提出了一种双通道特征融合的真实场景点云语义分割方法DCFNet(dual-channel feature fusion of real scene for point cloud semantic segmentation)可用于不同场景下的室内外场景语义分割。更具体地说,为了解决不能充分提取真实场景点云颜色信息的问题,该方法采用上下两个输入通道,通道均采用相同的特征提取网络结构,其中上通道的输入是完整RGB颜色和点云坐标信息,该通道主要关注于复杂物体对象场景特征,下通道仅输入点云坐标信息,该通道主要关注于点云的空间几何特征;在每个通道中为了更好地提取局部与全局信息,改善网络性能,引入了层间融合模块和Transformer通道特征扩充模块;同时,针对现有的三维点云语义分割方法缺乏关注局部特征与全局特征的联系,导致对复杂场景的分割效果不佳的问题,对上下两个通道所提取的特征通过DCFFS(dual-channel feature fusion segmentation)模块进行融合,并对真实场景进行语义分割。对室内复杂场景和大规模室内外场景点云分割基准进行了实验,实验结果表明,提出的DCFNet分割方法在S3DIS Area5室内场景数据集以及STPLS3D室外场景数据集上,平均交并比(MIOU)分别达到71.18%和48.87%,平均准确率(MACC)和整体准确率(OACC)分别达到77.01%与86.91%,实现了真实场景的高精度点云语义分割。

拉普拉斯卷积的双路径特征融合遥感图像智能解译方法

由于遥感图像存在多尺度变化和目标边缘模糊等问题,对其进行智能解译仍然是一项极具挑战性的工作。传统的语义分割方法在处理这些问题时存在局限性,难以有效捕捉全局和局部信息。针对上述问题,文中提出一种双路径特征融合分割方法 DFNet。首先,使用Swin Transformer作为主干提取全局语义特征,以处理像素之间的长距离依赖关系,从而促进对图像中不同区域相关性的理解;其次,将拉普拉斯卷积嵌入到空间分支,以捕获局部细节信息,加强目标地物边缘信息表达;最后,引入多尺度双向特征融合模块,充分利用图像中的全局和局部信息,以增强多尺度信息的获取能力。在实验中,使用了三个公开的高分辨率遥感图像数据集进行验证,并通过消融实验验证了所提模型不同模块的作用。实验结果表明,所提方法在Uavid数据集、Potsdam数据集、LoveDA数据集的mIoU达到了71.32%、85.58%、54.01%,提高了语义分割的性能,使分割结果更为精细。

基于双路径编码的遥感建筑物图像分割方法

高分辨率遥感图像建筑物分割是遥感影像研究的热点之一,而高分辨率遥感图像中建筑物尺度多样容易导致错分割、漏分割和边界模糊。针对上述问题,基于U-Net网络结构提出了一种双路径编码的遥感建筑物图像分割网络(DCU-Net)。DCU-Net在U-Net上加入一条并行编码路径,形成双路径编码结构。在编码阶段设计了密集残差编码模块(DRCM)和多尺度空洞卷积编码模块(MDCCM)以增强多尺度特征提取。在网络中加入双路融合注意力模块(DFAM),增强网络对特征的表达能力。为验证网络有效性,在WHU与Massachusetts数据集上进行实验,召回率、F1分数和交并比指标在WHU上达到91.26%、92.33%和86.15%,在Massachusetts Buildings上达到81.64%、84.33%和82.72%。结果表明,DCU-Net对于不同尺度的建筑物提取有较高的提取精度。

基于密集多尺度特征和双注意力模块的皮肤病变分割

针对皮肤病变分割任务中病变区域大小不一、形状各异、内部像素差异大、边界模糊、周围存在气泡等问题,提出了一种基于密集多尺度特征和双注意力模块的U型分割网络DDAnet。该网络中的DenseASPP模块通过密集连接多个空洞卷积层来获取丰富的多尺度信息,同时由通道注意力模块(CAM)和位置注意力模块(PAM)构成的双注意力模块通过编码全局上下文信息,在通道和位置上对特征图进行重新配准,实现对相关特征的强调和对无关特征的抑制。两个模块并行连接、共同作用以提高分割精度。在ISIC2018数据集上,DDAnet的准确率(Acc)、Jaccard相似系数(JI)、Dice系数(DC)、敏感度(Sen)和特异性(Spec)指标值分别为96.75%、85.00%、91.36%、91.82%和97.42%,分割结果优于其他的分割网络,并且对于极具挑战的病例,DDAnet仍然能够产生准确、可靠的分割结果,说明其具备在临床诊断中辅助医生进行皮肤病变分割的潜力。

基于高光谱成像的烤烟着生部位识别

【目的】采用高光谱成像技术结合机器学习方法,建立烤烟着生部位(上部、中部、下部)的识别模型。【方法】首先,通过分析烟叶在水、氮敏感波段下的强度分布特征,采用了一种结合OTSU和Sauvola图像分割算法的双阈值感兴趣区(ROI)选取方法,然后对比分析不同预处理方法对数据建模的影响规律,采用支持向量机(SVM)、极限梯度提升(XGBoost)算法进行判别模型的建立,通过参数寻优进行模型的优化。使用遗传算法(GA)和遗传算法结合连续投影算法(GA-SPA)进行特征波长的选择,建立简化模型。【结果】(1)建立的双阈值感兴趣区选取方法能准确高效地实现烤烟叶片正常叶面区域的选取(2)不同数据预处理方法对识别模型影响较为显著,基于一阶导和萨维莱茨-戈莱平滑(1Der+SG)预处理光谱数据,结合GA选取的特征波长建立的XGBoost着生部位识别模型具有最佳的分类效能,其准确率高达97.78%。【结论】研究建立的基于高光谱成像技术结合机器学习方法的部位模型可满足烤烟着生部位的高效准确识别。

基于功率控制环扰动的DC-DC变换器能量信息一体化研究

针对实现DC-DC变换器之间的信息交互较为复杂的问题,提出了一种基于功率控制环扰动实现其能量信息一体化的方法。通过在DC-DC变换器的传统功率控制环中叠加二进制频移键控(binary frequency shift keying,2FSK)信号作为扰动,将数据信息叠加到传统脉冲宽度调制(pulse-width modulation,PWM)信号中,使得该PWM信号同时包含数据信息,实现能量信息一体化。首先,给出基于2FSK的功率/数据双载波调制以及实时的滑动离散傅里叶变换(sliding discrete Fourier transform,SDFT)解调方案。然后,通过对Buck变换器的能量信息一体化模型进行小信号建模与分析可知,降低输入阻抗可提升通信的信噪比。最后搭建一个由两个Buck变换器并联的实验装置进行验证。实验结果表明在稳态和负载突变的工况下均可实现3 kb/s的稳定通信,验证了所提方法的可行性。该方法使得DC-DC变换器能同时进行功率变换和数据传输,提升数字化和智能化水平。

基于改进Swin Transformer的遥感图像语义分割方法

在高分辨率的遥感图像中提取出准确的地物信息对城市规划以及土地资源利用有重要作用。然而,遥感图像具有目标物体之间尺度差异大,背景复杂等特点,易导致提取结果不准确,特别是对小尺度地物的提取精度较低。为了解决这些问题,提出一种新型双编码结构,充分获取全局语义信息以及空间细节信息,分阶段融合不同尺度的特征信息,增强特征表示能力。构造了特征加强模块(FEM),以减少下采样中细节信息的丢失,关注更多小尺度特征。为了更好地细化特征信息,融合了通道注意力和内核注意力后进行上采样,能够将局部特征与对应的全局空间依赖关系整合,提升目标物体的分割精度。在Potsdam数据集和Vaihingen数据集上的mIoU分别为86.1%和82.4%,与流行的语义分割模型进行对比分析,结果表明,该方法能够有效解决遥感图像中小尺度物体分割不准确的问题,适合处理遥感图像语义分割任务。

一种基于对偶学习的场景分割模型

城市场景分割等复杂任务存在特征图空间信息利用率低下、分割边界不够精准以及网络参数量过大的问题。为解决这些问题,提出了一种基于对偶学习的场景分割模型DualSeg。首先,采用深度可分离卷积使模型参数量显著减少;其次,融合空洞金字塔池化与双重注意力机制模块获取准确的上下文信息;最后,利用对偶学习构建闭环反馈网络,通过对偶关系约束映射空间,同时训练“图像场景分割”和“对偶图像重建”两个任务,辅助场景分割模型的训练,帮助模型更好地感知类别边界、提高识别能力。实验结果表明,在自然场景分割数据集PASCAL VOC中,基于Xception骨架网络的DualSeg模型的mIoU和全局准确率分别达到81.3%和95.1%,在CityScapes数据集上mIoU达到77.4%,并且模型参数量减少18.45%,验证了模型的有效性。后续将探索更有效的注意力机制,进一步提高分割精度。

基于动态采样对偶可变形网络的实时视频实例分割

为了更好地利用视频帧中蕴含的时间信息,提升视频实例分割的推理速度,提出动态采样对偶可变形网络(DSDDN). DSDDN使用动态采样策略,根据前、后帧的相似性调整采样策略.对于相似性高的帧,该方法跳过当前帧的推理过程,仅使用前帧分割进行简单迁移计算.对于相似性低的帧,该方法动态聚合时间跨度更大的视频帧作为输入,对当前帧进行信息增强.在Transformer结构里,该方法额外使用2个可变形操作,避免基于注意力的方法中的指数级计算量.提供精心设计的追踪头和损失函数,优化复杂的网络.在YouTube-VIS数据集上获得了39.1%的平均推理精度与40.2帧/s的推理速度,验证了提出的方法能够在实时视频分割任务上取得精度与推理速度的良好平衡.

基于各向异性注意力的双分支血管分割模型

血管分割对于血管疾病的诊断和治疗具有重要意义,但由于血管边界模糊、病变血管的形状多变且不同样本之间的差异性较大,因此要求分割模型能够准确地挖掘血管与背景类间的差异性以及血管内部的连通性。提出一种基于中心线约束与各向异性注意力的新型三维血管分割网络CAU-Net。针对血管分割的难点,对基础网络结构ResU-Net进行改进,构建各向异性注意力模块,该模块根据管腔结构特有的空间各向异性,从3个方向提取血管空间各向异性特征,并对特征通道间的相关性进行建模,学习血管的三维空间信息。采用主-辅双分支模型,b-Net对血管进行语义分割,a-Net学习血管中心线的连续性特征,约束b-Net的血管分割结果,保证血管分割结果的完整性。在公开数据集3D-IRCADb-01上的实验结果表明,对于门静脉及肝静脉的分割,CAU-Net分别取得(74.80±8.05)%和(76.14±6.89)%的Dice系数、(54.80±8.09)%和(50.40±5.22)%的NSD系数、(72.43±8.26)%和(70.84±6.05)%的clDice系数、(46.47±12.89)%和(39.19±7.97)%的分支检测率以及(67.08±15.59)%和(61.47±9.32)%的树长检测率。在公开脑血管数据集IXI上进行组件消融实验,模型在验证集上的平均Dice、NSD、clDice、BD和TD分别为(94.11±0.39)%、(96.53±0.37)%、(95.83±0.59)%、(98.64±1.63)%和(95.44±1.22)%,相比于Baseline分别提升了0.92%、0.82%、0.92%、1.11%和1.60%。CAU-Net血管分割模型能够显著提升血管分割的精度和完整度。

结合双重注意力机制的遥感图像道路分割

为解决光学遥感图像道路分割所存在的漏判、误判等问题,提出了一种改进U型网络结构的语义分割模型,融入双重通道注意力机制和改进空间金字塔池化结构的残差特征提取U型网络(RSD-UNet)。首先,编码模块采用具有残差结构的ResNet—34,避免神经网络出现梯度消失;其次,融入串行改进的SPPCSPC池化模块,提高网络的感受野、解决道路特征多尺度问题;最后,在上采样操作后融入多频谱通道和空间的维度的双重注意力机制(DAM)。实验结果表明:在CHN6—CUG数据集上,对比基准网络UNet,指标IoU和F1分数提高了4.4%和3.07%。因此,RSD-UNet能够较好实现对于光学遥感图像道路分割。