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.

DS-TransFusion:基于改进Swin Transformer的视网膜血管自动分割

视网膜血管的准确分割在辅助筛查各种疾病方面具有重大意义.然而,当前流行的模型仍存在细小血管的分割不清晰,以及眼底血管分支末端与背景的对比度较低等问题.针对这些问题,本文提出了一种全新的视网膜血管分割模型,命名为Dual Swin Transformer Fusion(DS-TransFusion).首先,DS-TransFusion采用基于Swin Transformer的双尺度编码器子网络,以提取视网膜血管的粗粒度和细粒度特征.其次,在跳跃连接处引入了Transformer交互融合注意力(TIFA)模块,用于丰富跨视图上下文建模和语义依赖,同时捕获来自不同图像视图的数据之间的长期相关性.最后,在编码器和解码器之间,DS-TransFusion采用了多尺度注意力(MA),用于收集多尺度特征表示的全局对应关系,进一步优化模型的分割效果.实验结果表明,DS-TransFusion在公共数据集STARE、CHASEDB1和DRIVE上表现出色,准确率分别达到了96.50%、97.22%和97.80%,灵敏度达到84.10%、84.55%和83.17%.实验表明DS-TransFusion能有效提高视网膜血管分割的精度,准确分割出细小血管.对视网膜血管分割的准确度、灵敏度和特异性都有大幅提高,与现有的SOTA方法相比具有更好的分割性能.

Semantic Segmentation Based Remote Sensing Data Fusion on Crops Detection

Data fusion is usually an important process in multi-sensor remotely sensed imagery integration environments with the aim of enriching features lacking in the sensors involved in the fusion process. This technique has attracted much interest in many researches especially in the field of agriculture. On the other hand, deep learning (DL) based semantic segmentation shows high performance in remote sensing classification, and it requires large datasets in a supervised learning way. In the paper, a method of fusing multi-source remote sensing images with convolution neural networks (CNN) for semantic segmentation is proposed and applied to identify crops. Venezuelan Remote Sensing Satellite-2 (VRSS-2) and the high-resolution of Google Earth (GE) imageries have been used and more than 1000 sample sets have been collected for supervised learning process. The experiment results show that the crops extraction with an average overall accuracy more than 93% has been obtained, which demonstrates that data fusion combined with DL is highly feasible to crops extraction from satellite images and GE imagery, and it shows that deep learning techniques can serve as an invaluable tools for larger remote sensing data fusion frameworks, specifically for the applications in precision farming.

A Local Contrast Fusion Based 3D Otsu Algorithm for Multilevel Image Segmentation

To overcome the shortcomings of 1 D and 2 D Otsu’s thresholding techniques, the 3 D Otsu method has been developed.Among all Otsu’s methods, 3 D Otsu technique provides the best threshold values for the multi-level thresholding processes. In this paper, to improve the quality of segmented images, a simple and effective multilevel thresholding method is introduced. The proposed approach focuses on preserving edge detail by computing the 3 D Otsu along the fusion phenomena. The advantages of the presented scheme include higher quality outcomes, better preservation of tiny details and boundaries and reduced execution time with rising threshold levels. The fusion approach depends upon the differences between pixel intensity values within a small local space of an image;it aims to improve localized information after the thresholding process. The fusion of images based on local contrast can improve image segmentation performance by minimizing the loss of local contrast, loss of details and gray-level distributions. Results show that the proposed method yields more promising segmentation results when compared to conventional1 D Otsu, 2 D Otsu and 3 D Otsu methods, as evident from the objective and subjective evaluations.

一种基于暗亮通道分割融合的低照度环境图像去尘雾及增强方法

受煤矿井下粉尘、水雾和低照度环境影响,对皮带运输系统的监测图像精准识别极为困难。针对现有去尘雾方法的图像处理结果和效率欠佳的问题,提出一种基于暗亮通道分割融合的低照度环境图像去尘雾及增强方法。首先利用阈值分割结合伽马变换修正通道差,解决因低照度环境影响导致的尘雾浓度较大区域与其他区域间像素值差异不明显的问题,修正后通过引导尘雾图像做引导滤波得到更加符合实际情况的全局大气光强;然后为解决暗通道先验在尘雾浓度较大区域失效问题,引入亮通道先验进行补充,使用通道分量来辅助暗通道及亮通道透射率融合,避免因多次分割而导致的边缘像素归属问题;最后将去雾后RGB图像转至HSV空间,对亮度分量进行直方图均衡化并将均衡化前后的亮度分量进行加权融合,采用客观指标评价,选择最优聚合权值进行聚合,同时考虑去雾过程中饱和度损失和亮度分量与饱和度分量间的相关性提出饱和度自适应矫正函数,对图像饱和度进行矫正,色调分量保持不变,随后将图像转回至RGB空间,得到亮度适中、信息保留丰富和色彩鲜艳的图像;为验证所提方法的有效性,采用主观视觉、客观指标和目标检测精度及置信度进行算法对比,实验结果表明所提方法在上述4个指标上均优于被对比算法,其图像细节保留丰富,图像视觉观感更佳。

Treatment of Single Level Lumbar Spondylolisthesis with Lumbar Interbody Fusion via Oblique Lateral Approach (OLIF)

Objectives: To investigate the effect of lumbar interbody fusion via the oblique lateral approach (OLIF) in the treatment of single level lumbar spondylolisthesis. Methods: Retrospective analysis was made on 32 cases of single level lumbar spondylolisthesis treated by lumbar interbody fusion via the oblique lateral approach from July 2020 to July 2021. 14 males and 18 females;the age was (66.5 ± 11.5) years (55 - 82 years). 1) The operation time, intraoperative blood loss and complications were recorded;2) the scores of visual analog scale. VAS and Oswestry disability index (ODI) of low back pain and lower limb pain were collected before operation and at the last follow-up;by observing the imaging data, the height of the intervertebral space, the anterior convex angle of the intervertebral space, the anterior convex angle of the lumbar spine, the sagittal diameter of the dural sac and the spondylolisthesis were measured. Results: All patients successfully completed the operation, the average operation time was (103.9 ± 21.1) min, the average intraoperative bleeding volume was (72.3 ± 16.4) ml. There was no vascular injury during the operation, no infection occurred in all surgical incisions, and Class I/A healing was achieved. The VAS scores of low back pain and leg pain before operation and at the last follow-up were lower than those before operation, and the difference was statistically significant (P < 0.05);the ODI at the last follow-up was lower than that before operation, and the difference was statistically significant (P < 0.05). At the last follow-up, the height of intervertebral space, the height of intervertebral foramen and the sagittal diameter of dural sac were greater than those before operation, with statistically significant differences (P < 0.05);the spondylolisthesis rate at the last follow-up was lower than that before operation, with a statistically significant difference (P < 0.05). Left thigh surface numbness occurred in 2 cases (6.3%) and disappeared after 1 week;Hip flexion weakness occurred in 1 case (0.03%), which recovered after 12 days;there were no complications such as retroperitoneal hematoma, ureteral injury, retrograde ejaculation, intestinal and lumbar plexus injury. Conclusion: The early clinical effect of OLIF in the treatment of single level lumbar spondylolisthesis is significant. This surgical method is minimally invasive, safe and effective, which can significantly reduce the amount of intraoperative bleeding and reduce the risk of postoperative complications. Its main working principle is to make the annulus fibrosus, posterior longitudinal ligament and ligamentum flavum shrink and recover the height of the intervertebral space through decompression, loosening and stretching of the intervertebral space, so as to achieve the reduction of the slipped vertebral body, increase the height of the intervertebral foramen Enlarge the spinal canal volume and eliminate dynamic compression to play an indirect decompression role, improve the symptoms of low back and leg pain, and reconstruct the stability of the spine through interbody fusion.

基于多维分割和特征融合的车辆重识别算法

针对车辆重识别算法受类内差异性和类间相似性干扰,细粒度特征提取不充分的问题,本文提出一种融合全局与局部信息,基于卷积和自注意力机制的车辆重识别算法。采用双分支架构对车辆语义进行编码,更好地捕捉车辆信息,为了增强局部语义信息的提取,针对不同维度上的注意力模块,通过设计全局局部交互模块,将全局信息更好地融入局部特征。在公开数据集VeRi 776与VehicleID数据集进行实验验证,实验结果证明所提方法的优越性。

改进自适应加权的海面目标距离测量和跟踪

海上目标距离探测和跟踪是海洋安全和军事应用中的关键任务之一,针对复杂海面环境在海杂波等影响因素下目标距离测量精度低的问题,提出了一种改进的多传感器数据融合算法。该算法利用海面舰船雷达及陆地雷达联合探测结果,先对多个数据源数据进行坐标系转换,利用Robust Z-score方法进行纵向数据预处理剔除异常数据,再通过重新定义置信距离度量,将置信度较高的传感器结果代替被踢除数据后,对结果进行自适应加权融合。同时,为了进一步提高数据精度,引入了一种分段融合机制,将改进的传感器数据融合算法与阶梯式自适应加权融合算法进行级联,通过度量各分段融合结果的相似度,设定一个置信阈值,通过该置信阈值确定最终的融合结果。仿真实验结果证实了算法的有效性和准确性。

基于改进DeepLabv3的自然图像语义分割算法

针对DeepLabv3模型对自然图像语义分割时存在的图像局部细节信息丢失导致的误分割和物体边缘分割不完整的问题,提出了一种改进DeepLabv3模型的自然图像语义分割网络,能够以更高的准确率实现自然图像的语义分割.首先,使用ResNet101作为骨干网络进行特征提取,把ResNet101网络最后两层提取到的特征图输入到设计的ACMix多重融合模块(ACMix Multiple Fusion Module,AMFM)中,有效获取不同尺度的空间特征信息,将融合之后的结果作为空洞空间金字塔池化模块(Atrous Spatial Pyramid Pooling,ASPP)的输入.其次,添加辅助分支模块(Auxiliary Branch Module,ABM),将ResNet101网络第三层提取到的特征图输入到ABM中,有效提取更丰富的边缘特征信息.最后,将主分支和辅助分支的结果融合作为输出,融合后的输出不仅追踪到了不同尺度的空间特征信息,而且提取到了完整的边缘特征信息,从而使模型更有效地提高分割精度.PASCAL VOC 2012数据集的结果表明,改进后的模型相比于原模型分割精度提升了3.21%,与其它网络模型相比,也具有较好的分割精度.

自然环境下苹果点云多维度特征分割方法研究

为了解决自然环境下苹果果园复杂场景及光照变化对果实精准定位和空间形态评估带来的困难,对基于多维度特征的苹果点云分割方法进行了研究。研究中,通过融合欧氏距离、曲率分析和颜色特征创建苹果点云分割掩膜,对苹果点云进行分割;引入K-D Tree进行聚类修正,拟合后获取最终果实空间全面信息。试验结果显示:在自然果园环境下,该方法在逆光、顺光和侧光条件下分别取得了96.20%、97.67%和97.93%的分割纯净率,与仅基于欧氏距离或颜色特征的单一特征分割方法相比,该方法的纯净率分别提高了37.57%和14.53%,且聚类误分问题得到有效解决。该方法具有良好的鲁棒性和精确性,可为苹果智能化采摘作业的精确性和可靠性提供技术支持。

MCFNet:融合上下文信息的多尺度视网膜动静脉分类网络

针对由于血管类间具有强相似性造成的动静脉错误分类问题,提出了一种新的融合上下文信息的多尺度视网膜动静脉分类网络(multi-scale retinal artery and vein classification network,MCFNet),该网络使用多尺度特征(multi-scale feature,MSF)提取模块及高效的全局上下文信息融合(efficient global contextual information aggregation,EGCA)模块结合U型分割网络进行动静脉分类,抑制了倾向于背景的特征并增强了血管的边缘、交点和末端特征,解决了段内动静脉错误分类问题。此外,在U型网络的解码器部分加入3层深度监督,使浅层信息得到充分训练,避免梯度消失,优化训练过程。在2个公开的眼底图像数据集(DRIVE-AV,LES-AV)上,与3种现有网络进行方法对比,该模型的F1评分分别提高了2.86、1.92、0.81个百分点,灵敏度分别提高了4.27、2.43、1.21个百分点,结果表明所提出的模型能够很好地解决动静脉分类错误的问题。

Adjacent Segment Disease after Long Spinal Fusion Ending at L5 for Adult Spinal Deformity: A Retrospective Cohort Study

Study Design: This is a retrospective cohort study using data from the adult spinal deformity (ASD) database of a single institution. Purpose: To investigate the incidence of proximal junctional failure and distal junctional failure (DJF) after ASD surgery with a lower instrumented vertebra (LIV) at L5. Overview of Literature: Spinopelvic fixation from the lower thoracic vertebra to the pelvis is the current gold standard treatment for ASD. However, the LIV at L5 is acceptable in some cases. Methods: Fifty-six patients who underwent corrective surgery for ASD with LIV at L5 were included. The upper instrumented vertebra (UIV) was T7 in one patient, T9 in 14, T10 in three, T11 in four, T12 in eight, L1 in 10, and L2 in 16. Regarding clinical parameters, age, sex, curve types of Scoliosis Research Society-Schwab classification, number of levels fused, follow-up period, hip bone mallow density, revision surgery rate, and radiographic measurements were compared between the T (UIV: T7 - 10) and TL (UIV: T11 - L2) groups. Results: The revision surgery rate was 19.6% overall. In the T and TL groups, it was 27.8%, and 15.8%, respectively (p = 0.305). The rate of DJF in the T group (33.3%) was significantly higher than in the TL group (5.3%). The rate of proximal junctional kyphosis in the T group (55.6%) was higher than in the TL group (28.9%), with no significant difference. The mean global alignment, sagittal vertical axis, and C7 plumb line-central sacral vertical line were not different between both groups. Conclusions: ASD surgery with LIV set at L5 and UIV set at the thoracic vertebrae (T7 - T10) has a risk of adjacent segment disease.

单侧双通道内镜下(UBE-TLIF)与微创经椎间孔腰椎融合术(MIS-TLIF)治疗退变性腰椎椎管狭窄症的疗效比较

目的 比较单侧双通道内镜下经椎间孔腰椎椎间融合术(unilateral biportal endoscopic transforaminal lumbar interbodyfusion,UBE-TLIF)与微创经椎间孔入路腰椎椎间融合术(minimal invasive transforaminal lumbar interbody fusion, MIS-TLIF)治疗单节段退行性腰椎椎管狭窄症的疗效。方法 回顾性分析2021年1月至2021年12月成都中医药大学附属医院符合纳入标准的68例单节段退行性腰椎椎管狭窄症患者的临床资料,按手术方式分为UBE-TLIF组(27例)与MIS-TLIF组(41例)。对比两组患者的手术相关指标(手术时间、术中出血量、术后引流量、术后住院天数、并发症发生率等);实验室检查结果[全血C反应蛋白(C-reactive protein, CRP)、血清磷酸肌酸激酶(creatine kinase, CK)]及临床疗效评价[腰痛及下肢疼痛视觉模拟评分(visual analogue scale,VAS)、Oswestry功能障碍指数(Oswestry disability index, ODI)、改良MacNab标准评价优良率、Brantigan标准评价椎间融合率]等。结果 68例患者均获得随访,随访时间12~20个月。与MIS-TLIF组相比,UBE-TLIF组患者的手术时间、住院时间更长,但术中出血量、术后引流量更短(P<0.05)。实验室检查方面:术前两组实验室检查差异无统计学意义(P>0.05);术后3 d UBE-TLIF组全血C反应蛋白含量较MIS-TLIF组低(P<0.05);术后1、3 dUBE-TLIF组血清磷酸肌酸激酶水平均低于MIS-TLIF组(P<0.05)。临床疗效评价:术前两组间患者腰痛及下肢疼痛视觉模拟评分及Oswestry功能障碍指数比较,差异无统计学意义(P>0.05),术后各时间点上述评分均较术前显著下降(P<0.05);组间比较发现各组术后3 d、1个月、6个月、12个月的腰痛及下肢疼痛视觉模拟评分,术后3、12个月Oswestry功能障碍指数,末次随访优良率,椎间融合率比较,差异无统计学意义(P>0.05)。并发症方面:UBE-TLIF组无并发症发生,MIS-TLIF组发生并发症2例,包括术后切口感染1例及术后下肢麻木1例,两组间并发症发生率比较,差异无统计学意义(P>0.05)。结论 UBE-TLIF手术方式可达到与MIS-TLIF手术方式相似的术后腰痛疼痛评分、腿疼痛评分、功能障碍指数,且较MIS-TLIF肌肉损伤释放的CK更少、组织出血量更少、术后恢复更快。

多层级视频会议系统跨网段融合技术的应用

通过介绍天津市地震局应急视频会议系统接入中国地震局视频会议系统、天津市政府视频系统和天津应急管理局视频系统的基本情况,结合地震应急视频会议系统现状,分析多类型、多层级、多网段视频会议系统的架构特点,着重介绍了多网段、多视频源视频转发优化技术在视频会议系统融合中的应用。通过该技术的应用,实现了天津市地震应急视频会议系统与各相关单位视频会议系统的全部连通。

基于复杂纹理特征融合的材料图像分割方法

为解决材料图像分割中存在小样本、纹理复杂和数据分布不平衡的问题,抓住材料图像同相像素具有高度相似性的特性,提出一种基于复杂纹理特征融合的材料图像分割方法。在编码阶段,使用全卷积神经网络(FCN)作为基础网络,VGG16作为骨干网络;将改进的FCN的每层的特征图放入设计的级联的特征融合模块(CFF block),融合高低层语义信息;将融合的特征图放入多尺度学习模块(multi-scale block)进一步提取纹理特征。在解码阶段,对特征图施加注意力机制(Attention block),保留关键的特征图;针对材料图像中数据不平衡问题,采用并改进Dice损失,优化分割结果。通过对比实验和消融实验验证该方法的mIoU在多个数据集上均优于经典的深度学习方法。

基于注意力机制及多分支特征融合的实时语义分割算法

为了合理平衡语义分割中的精确度与实时性,基于快速卷积神经网络模型(Fast-SCNN)提出了一种基于注意力机制及多分支特征融合的实时语义分割算法模型。该算法模型首先通过注意力模块捕获空间特征之间的相互联系,增强空间细节信息;然后合理设计融合模块,最大化利用各分支信息,实现深层特征与浅层特征更好的融合;最后引入自适应特征增强注意力模块,捕获长距离像素间的相互依赖关系。实验结果表明,文中算法模型在Cityscapes数据集上获得了71.55%的分割精度,推理速度FPS达到97.6帧/s,模型参数量为1.39 M,验证了该算法所构成网络模型的有效性。

复杂场景下自适应注意力机制融合实时语义分割

实现高准确度和低计算负担是卷积神经网络(CNN)实时语义分割面临的严峻挑战。针对复杂城市街道场景目标种类众多、光照变化大等特点,该文设计了一种高效的实时语义分割自适应注意力机制融合网络(AAFNet)分别提取图像空间细节和语义信息,再经过特征融合网络(FFN)获得准确语义图像。AAFNet采用扩展的深度可分离卷积(DDW)可增大语义特征提取感受野,提出自适应平均池化(Avp)和自适应最大池化(Amp)构成自适应注意力机制融合模块(AAFM),可细化目标边缘分割效果并降低小目标的漏分率。最后在复杂城市街道场景Cityscapes和CamVid数据集上分别进行了语义分割实验,所设计的AAFNet以32帧/s(Cityscapes)和52帧/s(CamVid)的推理速度获得73.0%和69.8%的平均分割精度(mIoU),且与扩展的空间注意力网络(DSANet)、多尺度上下文融合网络(MSCFNet)以及轻量级双边非对称残差网络(LBARNet)相比,AAFNet平均分割精度最高。

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。

基于度量学习的电路焊点缺陷检测方法

针对目前电路焊点缺陷检测方法效率低、准确度差、焊点图像样本量小的问题,提出了一种基于度量学习的快速识别焊点缺陷的方法.首先利用工业相机搭配远心镜头获取焊点图像.通过挖掘焊点图像特征,设计交点检测法来分割焊接单元图像,制作焊点缺陷数据集.在此基础上,设计焊点图像全局特征与局部表征提取方法来对焊点的两类特征进行融合,并对注意力机制进行改进,加入到全局特征提取模块中.对焊点缺陷的检测实验结果表明该方法最终实现了准确率达到98.4%,满足焊点缺陷检测的实际生产要求.

预指导的多阶段特征融合的图像语义分割网络

针对目前语义分割对图像边缘和小物体不能进行精确识别,以及简单融合多阶段特征会造成信息冗余、混杂不清等问题,提出了一个预指导的多阶段特征融合的网络(pre-guidanced multi-stage feature fusion network,PGMFFNet),PGMFFNet采用编解码器结构,编码阶段利用预指导模块对各阶段信息进行指导,增强各阶段特征之间的联系,解决各阶段特征在后续融合过程中产生的语义混杂问题。在解码阶段,利用多路径金字塔上采样模块融合高级语义特征,然后使用改进的密集空洞空间金字塔池化模块对融合后的特征进一步扩大感受野,最后将高低层次的特征信息融合,使得对小物体的分割效果更优。PGMFFNet在CityScapes公开数据集上进行了验证,得到了78.38%的平均交并比(mean intersection over union,MIoU),分割效果较好。