Drishti Paint 3.2:a new open-source tool for both 2D and 3D segmentation

X-ray computed tomography(CT)has been an important technology in paleontology for several decades.It helps researchers to acquire detailed anatomical structures of fossils non-destructively.Despite its widespread application,developing an efficient and user-friendly method for segmenting CT data continues to be a formidable challenge in the field.Most CT data segmentation software operates on 2D interfaces,which limits flexibility for real-time adjustments in 3D segmentation.Here,we introduce Curves Mode in Drishti Paint 3.2,an open-source tool for CT data segmentation.Drishti Paint 3.2 allows users to manually or semi-automatically segment the CT data in both 2D and 3D environments,providing a novel solution for revisualizing CT data in paleontological studies.

Infrared image segmentation method based on 2D histogram shape modification and optimal objective function

In the methods of image thresholding segmentation, such methods based on two-dimensional （2D） histogram and optimal objective functions are important. However, when they are used for infrared image segmentation, they are weak in suppressing background noises and worse in segmenting targets with non-uniform gray level. The concept of 2D histogram shape modification is proposed, which is realized by target information prior restraint after enhancing target information using plateau histogram equalization. The formula of 2D minimum Renyi entropy is deduced for image segmentation, then the shape-modified 2D histogram is combined wfth four optimal objective functions （i.e., maximum between-class variance, maximum entropy, maximum correlation and minimum Renyi entropy） respectively for the appli- cation of infrared image segmentation. Simultaneously, F-measure is introduced to evaluate the segmentation effects objectively. The experimental results show that F-measure is an effective evaluation index for image segmentation since its value is fully consistent with the subjective evaluation, and after 2D histogram shape modification, the methods of optimal objective functions can overcome their original forms＇ deficiency and their segmentation effects are more or less improvements, where the best one is the maximum entropy method based on 2D histogram shape modification.

Defect detection method based on 2D entropy image segmentation

In order to improve the work efficiency of non-destructive testing(NDT)and the reliability of NDT results,an automatic method to detect defects in the ultrasonic image was researched.According to the characterization of ultrasonic D-scan image,clutter wave suppression and de-noising were presented firstly.Then,the image is processed by binaryzation using KSW 2 D entropy based on image segmentation method.The results showed that,the global threshold based segmentation method was somewhat ineffective for D-scan image because of under-segmentation.Especially,when the image is big in size,small targets which are composed by a small amount of pixels are often undetected.Whereas,local threshold based image segmentation method is effective in recognizing small defects because it takes local image character into account.

Real-time instance segmentation based on contour learning

Instance segmentation plays an important role in image processing.The Deep Snake algorithm based on contour iteration deforms an initial bounding box to an instance contour end-to-end,which can improve the performance of instance segmentation,but has defects such as slow segmentation speed and sub-optimal initial contour.To solve these problems,a real-time instance segmentation algorithm based on contour learning was proposed.Firstly,ShuffleNet V2 was used as backbone network,and the receptive field of the model was expanded by using a 5×5 convolution kernel.Secondly,a lightweight up-sampling module,multi-stage aggregation(MSA),performs residual fusion of multi-layer features,which not only improves segmentation speed,but also extracts effective features more comprehensively.Thirdly,a contour initialization method for network learning was designed,and a global contour feature aggregation mechanism was used to return a coarse contour,which solves the problem of excessive error between manually initialized contour and real contour.Finally,the Snake deformation module was used to iteratively optimize the coarse contour to obtain the final instance contour.The experimental results showed that the proposed method improved the instance segmentation accuracy on semantic boundaries dataset(SBD),Cityscapes and Kins datasets,and the average precision reached 55.8 on the SBD;Compared with Deep Snake,the model parameters were reduced by 87.2%,calculation amount was reduced by 78.3%,and segmentation speed reached 39.8 frame·s−1 when instance segmentation was performed on an image with a size of 512×512 pixels on a 2080Ti GPU.The proposed method can reduce resource consumption,realize instance segmentation tasks quickly and accurately,and therefore is more suitable for embedded platforms with limited resources.

FIR-YOLACT:Fusion of ICIoU and Res2Net for YOLACT on Real-Time Vehicle Instance Segmentation

Autonomous driving technology has made a lot of outstanding achievements with deep learning,and the vehicle detection and classification algorithm has become one of the critical technologies of autonomous driving systems.The vehicle instance segmentation can perform instance-level semantic parsing of vehicle information,which is more accurate and reliable than object detection.However,the existing instance segmentation algorithms still have the problems of poor mask prediction accuracy and low detection speed.Therefore,this paper proposes an advanced real-time instance segmentation model named FIR-YOLACT,which fuses the ICIoU(Improved Complete Intersection over Union)and Res2Net for the YOLACT algorithm.Specifically,the ICIoU function can effectively solve the degradation problem of the original CIoU loss function,and improve the training convergence speed and detection accuracy.The Res2Net module fused with the ECA(Efficient Channel Attention)Net is added to the model’s backbone network,which improves the multi-scale detection capability and mask prediction accuracy.Furthermore,the Cluster NMS(Non-Maximum Suppression)algorithm is introduced in the model’s bounding box regression to enhance the performance of detecting similarly occluded objects.The experimental results demonstrate the superiority of FIR-YOLACT to the based methods and the effectiveness of all components.The processing speed reaches 28 FPS,which meets the demands of real-time vehicle instance segmentation.

Image Segmentation Based on Intuitionistic Type-2 FCM Algorithm

Due to using the fuzzy clustering algorithm,the accuracy of image segmentation is not high enough.So one hybrid clustering algorithm combined with intuitionistic fuzzy factor and local spatial information is proposed.Experimental results show that the proposed algorithm is superior to other methods in image segmentation accuracy and improves the robustness of the algorithm.

基于Gaofen-2影像和面向对象的椰子林分类研究

椰子是重要的热带经济作物,海南椰子种植面积占全国的90%以上。快速获取椰子种植面积及其空间分布信息对热带作物产业规划具有十分重要的作用。本研究基于国产Gaofen-2高分辨率卫星影像,以文昌市东郊镇为试验区,开展椰子林遥感分类研究。基于最优分割尺度的面向对象分类方法,选取4个光谱特征、5个植被指数和32个纹理特征为辅助参量,构建了4种不同的面向对象分类组合(光谱特征、光谱特征+纹理特征组合、光谱特征+植被指数组合、光谱特征+纹理特征+植被指数特征组合)进行椰子林分类提取,并与基于像元的椰子林分类结果进行对比分析。结果表明:(1)仅采用基于像元分类方法,椰子林的总体分类精度(overall accuracy,OA)和用户精度(user’s accuracy,UA)分别达到87.05%和85.21%。(2)相比基于像元分类,4种面向对象分类组合的OA值提高了5.51%~8.72%。(3)光谱特征和纹理特征组合提取椰子林分类结果最优,OA值和UA值分别达到95.77%和97.15%;光谱特征和植被指数的组合也得到了较好的分类结果,OA值和UA值分别为94.88%和94.42%;所有的光谱特征、植被指数和纹理特征全部参与分类得到的OA值和UA值分别为94.67%和94.17%,低于仅使用光谱特征或者植被指数的组合。综上,国产高分辨率Gaofen-2影像在椰子林遥感精准识别中具有很大的潜力,结合纹理特征的面向对象分类方法可以更准确地提取椰子林分类信息,研究结果可为多云多雨地区大尺度椰子林遥感识别提供技术参考。

血清LTBP-2、COMP水平与ST段抬高型心肌梗死患者病情、预后的关系

目的分析ST段抬高型心肌梗死(STEMI)患者血清潜在转化生长因子结合蛋白2(LTBP-2)和软骨寡聚基质蛋白(COMP)的表达水平,探讨其与患者的病情及预后的关系。方法以2019年1月至2020年12月郑州大学第五附属医院收治的135例STEMI患者为STEMI组,另外选取135名健康体检人员为对照组,STEMI患者根据出院1年随访中是否出现主要不良心脏事件(MACE)分为MACE组和非MACE组;ELISA法检测血清中LTBP-2和COMP的表达水平;采用Pearson法分析STEMI组患者LTBP-2与COMP表达的相关性;采用多因素logistic回归分析影响STEMI患者术后出现MACE的危险因素。结果与对照组相比,STEMI组患者的LTBP-2、COMP表达水平以及饮酒史、吸烟史的人数升高(P<0.05);Gensini积分≤38分的STEMI患者血清LTBP-2、COMP水平明显低于Gensini积分>38分的患者(P<0.05);Pearson法分析显示,STEMI患者血清中LTBP-2和COMP表达呈正相关(r=0.660,P<0.05);STEMI患者术后出现MACE的例数为30/135(22.22%),MACE组患者中发病时间>6 h,Gensini积分>38分、Killip分级Ⅲ~Ⅳ级比例、支架植入个数、血清LTBP-2与COMP表达水平明显高于非MACE组(P<0.05);多因素logistic回归分析表明,发病时间>6 h、Gensini积分>38分、Killip分级Ⅲ~Ⅳ级、支架植入个数≥3、LTBP-2≥39.36 ng/mL和COMP≥35.73 ng/mL是影响STEMI患者术后出现MACE的危险因素(P<0.05)。结论STEMI患者血清中LTBP-2、COMP的表达水平升高,二者与STEMI患者的病情严重程度及预后密切相关。

Segmentation of retinal fluid based on deep learning:application of three-dimensional fully convolutional neural networks in optical coherence tomography images

AIM: To explore a segmentation algorithm based on deep learning to achieve accurate diagnosis and treatment of patients with retinal fluid.METHODS: A two-dimensional(2D) fully convolutional network for retinal segmentation was employed. In order to solve the category imbalance in retinal optical coherence tomography(OCT) images, the network parameters and loss function based on the 2D fully convolutional network were modified. For this network, the correlations of corresponding positions among adjacent images in space are ignored. Thus, we proposed a three-dimensional(3D) fully convolutional network for segmentation in the retinal OCT images.RESULTS: The algorithm was evaluated according to segmentation accuracy, Kappa coefficient, and F1 score. For the 3D fully convolutional network proposed in this paper, the overall segmentation accuracy rate is 99.56%, Kappa coefficient is 98.47%, and F1 score of retinal fluid is 95.50%. CONCLUSION: The OCT image segmentation algorithm based on deep learning is primarily founded on the 2D convolutional network. The 3D network architecture proposed in this paper reduces the influence of category imbalance, realizes end-to-end segmentation of volume images, and achieves optimal segmentation results. The segmentation maps are practically the same as the manual annotations of doctors, and can provide doctors with more accurate diagnostic data.

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.

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.

超声造影评估2型糖尿病肾病肾脏血流灌注的价值

目的探讨超声造影定量评估肾脏血流灌注辅助诊断2型糖尿病肾病的应用价值。资料与方法前瞻性纳入2017年5月—2019年12月解放军总医院第一医学中心41例伴肾功能异常拟行肾脏穿刺的2型糖尿病患者,均行肾脏超声造影检查。比较糖尿病肾病和局灶节段性肾小球硬化症造影参数(肾皮质达峰时间、峰值强度、平均渡越时间、肾血流量曲线下面积)的差异,并分析造影参数与病理结果的相关性。结果41例患者中,病理诊断为糖尿病肾病30例,局灶节段性肾小球硬化症11例。糖尿病肾病组峰值强度和曲线下面积明显低于局灶节段性肾小球硬化症[峰值强度:3837.16(2449.16,5929.16)比8508.00(4334.88,21201.00),Z=-2.766,P=0.006;曲线下面积:0.14±0.05比0.19±0.05,t=-3.135,P=0.003]。糖尿病肾病组峰值强度与肾小球全球硬化率呈负相关(r=-0.489,P=0.006)。结论超声造影能够定量评估肾脏的血流灌注,对于辅助诊断2型糖尿病肾病具有一定临床价值。

基于改进U^(2)Net的岩石薄片图像分割

了解岩石的孔隙度、孔径分布、孔隙连通性等特征对于油气的寻找和开采有着重要的意义,而这些特征的分析和判断需要借助岩石薄片图像分割技术.岩石薄片图像有大量细小颗粒,这些颗粒之间的边缘特征十分相似,无法做出精准的区分,同时制造切片过程中染色不均会造成薄片孔隙的颜色特征不平衡而导致无法分割.因此为了改善岩石薄片分割效果,本文提出基于一种改进的U^(2)Net的分割算法.主要内容如下:(1)以U^(2)Net网络为骨干进行改进,结合coordinate attention注意力机制,用来提高模型对图像特征的表达能力.(2)通过引入多尺度特征提取模块,增加卷积层的感知区域,且能够利用特征图的多尺度特征信息.实验证明,该方法与传统分割方法和其他分割网络相比在较小颗粒的分割上表现更好,所提出的算法具有较高的分割准确度和鲁棒性.

基于边缘U^(2)-Net的视盘分割方法

彩色眼底图像中的视盘分割在识别眼科疾病中起着关键作用。针对因各种因素影响的视盘边缘分割不准确及分割算法效率低问题,提出一种基于轻量级U^(2)-Net、融入边缘注意力机制的视盘自动分割方法。该方法以轻量级U^(2)-Net为主干网络,使用视盘感兴趣区域提取的预处理方式去除无关特征,同时引入边缘注意力机制增强对视盘边缘特征的提取能力。在Drishti_GS和REFUGE两个公开数据集上的F1分数分别达到97.82%和97.36%,Dice相似系数分别达到97.15%和96.64%,IOU分别达到94.47%和93.50%,与其他网络模型相比表现出优越的分割性能,具有临床应用价值。

基于U^(2)-Net+的透水混凝土CT影像孔隙分割

针对现阶段主流的透水混凝土CT影像孔隙分割方法存在的问题,提出了一种堆叠高效RSU模块的U^(2)-Net+的图像分割方法。该方法通过堆叠高效的RSU模块,在网络中引入了更多的上采样节点和跳跃连接,还原了更多下采样阶段丢失的特征图细节;在编码阶段增加了一个可学习的下采样操作,进一步提升了网络对细节的捕获能力;简化了原网络的深度监督,避免了底层特征图对融合输出特征图的负面影响;将单一的标准二分类交叉熵损失函数改为Focal loss和IoU loss组成的混合损失函数,提升了网络对高噪声孔隙的关注度;最后由于数据集的特点加网络改进的提升,原网络中各模块的中间通道数得以进一步缩减,减小了网络体积。试验结果表明,U^(2)-Net+相比U^(2)-Net†在保证轻量化和快速性的同时,平均交并比、精确度、F1得分由94.12%、88.89%、93.28%分别提升至94.24%、91.15%、94.29%;U^(2)-Net+综合指标优于U-Net、U-Net++、U-Net3+、U^(2)-Net、U^(2)-Net†,各指标相较于主流的阈值分割算法至少提高23.29%,实现了透水混凝土CT影像孔隙的精准、快速分割。

Semantic Pneumonia Segmentation and Classification for Covid-19 Using Deep Learning Network

Early detection of the Covid-19 disease is essential due to its higher rate of infection affecting tens of millions of people,and its high number of deaths also by 7%.For that purpose,a proposed model of several stages was developed.The first stage is optimizing the images using dynamic adaptive histogram equalization,performing a semantic segmentation using DeepLabv3Plus,then augmenting the data by flipping it horizontally,rotating it,then flipping it vertically.The second stage builds a custom convolutional neural network model using several pre-trained ImageNet.Finally,the model compares the pre-trained data to the new output,while repeatedly trimming the best-performing models to reduce complexity and improve memory efficiency.Several experiments were done using different techniques and parameters.Accordingly,the proposed model achieved an average accuracy of 99.6%and an area under the curve of 0.996 in the Covid-19 detection.This paper will discuss how to train a customized intelligent convolutional neural network using various parameters on a set of chest X-rays with an accuracy of 99.6%.

A Systematic Literature Review of Deep Learning Algorithms for Segmentation of the COVID-19 Infection

Coronavirus has infected more than 753 million people,ranging in severity from one person to another,where more than six million infected people died worldwide.Computer-aided diagnostic(CAD)with artificial intelligence(AI)showed outstanding performance in effectively diagnosing this virus in real-time.Computed tomography is a complementary diagnostic tool to clarify the damage of COVID-19 in the lungs even before symptoms appear in patients.This paper conducts a systematic literature review of deep learning methods for classifying the segmentation of COVID-19 infection in the lungs.We used the methodology of systematic reviews and meta-analyses(PRISMA)flow method.This research aims to systematically analyze the supervised deep learning methods,open resource datasets,data augmentation methods,and loss functions used for various segment shapes of COVID-19 infection from computerized tomography(CT)chest images.We have selected 56 primary studies relevant to the topic of the paper.We have compared different aspects of the algorithms used to segment infected areas in the CT images.Limitations to deep learning in the segmentation of infected areas still need to be developed to predict smaller regions of infection at the beginning of their appearance.

基于Sentinel-1/2数据的洪水淹没范围提取模型

遥感是监测洪水淹没范围、掌握洪涝灾情演变的重要手段,而光学影像在洪水发生时往往有较多缺失,全天候的SAR影像在提取水体时精度略低。为快速、精准提取洪水淹没范围,构建了一种综合利用Sentinel-2光学影像和Sentinel-1雷达影像数据的洪水淹没范围提取模型,采用一种自适应阈值分割算法即大津算法(OTSU)分别对两种数据以及该模型进行了水体范围提取试验,并以河北省保定市为例进行了应用分析。结果显示:云量较少的Sentinel-2影像水体提取效果最好,总体精度(OA)达到95.6%;所构建的模型在引入部分可用Sentinel-2数据后,OA达到95%,相比单独使用Sentinel-1数据OA和Kappa系数分别提升1.2%和2.4%。该模型搭载于Google Earth Engine平台,能实现快速、准确、低成本的地表水体空间范围连续输出,不受限于云雾且比单独使用Sentinel-1影像的提取精度更高,在云覆盖严重导致Sentinel-2数据缺少的情况下,该模型可作为洪水淹没范围提取方法的一种选择。

SGLT-2抑制剂治疗STEMI患者PCI术后合并心力衰竭的效果观察

目的 探讨早期应用钠-葡萄糖协同转运蛋白2(SGLT-2)抑制剂联合标准治疗对ST段抬高型心肌梗死(STEMI)经皮冠状动脉介入(PCI)术后合并心力衰竭患者再住院的影响,为PCI术后早期新药干预提供循证依据。方法 采用回顾性队列研究方法,收集2019年1月至2023年1月新疆维吾尔自治区人民医院收治的STEMI PCI术后合并心力衰竭的患者。将以SGLT-2抑制剂联合标准治疗的78例患者纳入研究组,92例予以标准治疗者纳入对照组,比较2组患者治疗前后心功能变化、临床疗效以及心力衰竭再住院率。结果 治疗前后2组患者的左室舒张期内径、左室收缩期内径比较,差异均无统计学意义(P均> 0.05)。研究组治疗后B型利钠肽、左心室射血分数(LVEF)及治疗前后LVEF差值优于对照组,差异均有统计学意义(P均<0.05)。研究组与对照组因心力衰竭再住院发生率分别为15.4%和32.6%,差异有统计学意义(P <0.05)。多因素Cox回归分析显示,未服用SGLT-2抑制剂的标准治疗患者的因心力衰竭再住院风险比服用SGLT-2抑制剂的患者高1.235倍[HR(95%CI)=2.235(1.094~4.563),P <0.05]。结论 SGLT-2抑制剂联合标准治疗能降低STEMI PCI术合并心力衰竭患者因心力衰竭再住院风险。

级联语义分割和边缘检测的GF-2影像耕地提取

针对山地丘陵区的坡耕地和小面积耕地碎片边界模糊不清、分类提取困难的问题,以GF-2影像为数据源,提出了一种级联语义分割和边缘检测模型的遥感影像耕地信息提取方法。首先,针对不同类型耕地的特点选择级联方式;其次,将耕地边缘作为独立的特征类别,结合改进U-Net、DeeplabV3+和DexiNed模型,融合面特征和线特征,使得耕地边缘特征与语义特征能够进行互补,从而提高耕地提取的准确性,实现对复杂地形背景噪声的抑制和不同类型耕地的提取。实验结果表明,对比单一模型DeeplabV3+和U-Net,级联模型的耕地信息提取的总体精度、Kappa系数和F1值均有大幅度提升,针对不同类型耕地级联模型提取的耕地结果更接近真实耕地标注,漏提、误提区域远低于单一模型。