Spinal Vertebral Fracture Detection and Fracture Level Assessment Based on Deep Learning

This paper addresses the common orthopedic trauma of spinal vertebral fractures and aims to enhance doctors’diagnostic efficiency.Therefore,a deep-learning-based automated diagnostic systemwithmulti-label segmentation is proposed to recognize the condition of vertebral fractures.The whole spine Computed Tomography(CT)image is segmented into the fracture,normal,and background using U-Net,and the fracture degree of each vertebra is evaluated(Genant semi-qualitative evaluation).The main work of this paper includes:First,based on the spatial configuration network(SCN)structure,U-Net is used instead of the SCN feature extraction network.The attention mechanismandthe residual connectionbetweenthe convolutional layers are added in the local network(LN)stage.Multiple filtering is added in the global network(GN)stage,and each layer of the LN decoder feature map is filtered separately using dot product,and the filtered features are re-convolved to obtain the GN output heatmap.Second,a network model with improved SCN(M-SCN)helps automatically localize the center-of-mass position of each vertebra,and the voxels around each localized vertebra were clipped,eliminating a large amount of redundant information(e.g.,background and other interfering vertebrae)and keeping the vertebrae to be segmented in the center of the image.Multilabel segmentation of the clipped portion was subsequently performed using U-Net.This paper uses VerSe’19,VerSe’20(using only data containing vertebral fractures),and private data(provided by Guizhou Orthopedic Hospital)for model training and evaluation.Compared with the original SCN network,the M-SCN reduced the prediction error rate by 1.09%and demonstrated the effectiveness of the improvement in ablation experiments.In the vertebral segmentation experiment,the Dice Similarity Coefficient(DSC)index reached 93.50%and the Maximum Symmetry Surface Distance(MSSD)index was 4.962 mm,with accuracy and recall of 95.82%and 91.73%,respectively.Fractured vertebrae were also marked as red and normal vertebrae were marked as white in the experiment,and the semi-qualitative assessment results of Genant were provided,as well as the results of spinal localization visualization and 3D reconstructed views of the spine to analyze the actual predictive ability of the model.It provides a promising tool for vertebral fracture detection.

An attention-based cascade R-CNN model for sternum fracture detection in X-ray images

Fracture is one of the most common and unexpected traumas.If not treated in time,it may cause serious consequences such as joint stiffness,traumatic arthritis,and nerve injury.Using computer vision technology to detect fractures can reduce the workload and misdiagnosis of fractures and also improve the fracture detection speed.However,there are still some problems in sternum fracture detection,such as the low detection rate of small and occult fractures.In this work,the authors have constructed a dataset with 1227 labelled X-ray images for sternum fracture detection.The authors designed a fully automatic fracture detection model based on a deep convolution neural network(CNN).The authors used cascade R-CNN,attention mechanism,and atrous convolution to optimise the detection of small fractures in a large X-ray image with big local variations.The authors compared the detection results of YOLOv5 model,cascade R-CNN and other state-of-the-art models.The authors found that the convolution neural network based on cascade and attention mechanism models has a better detection effect and arrives at an mAP of 0.71,which is much better than using the YOLOv5 model(mAP=0.44)and cascade R-CNN(mAP=0.55).

Identification of thermal front dynamics in the northern Malacca Strait using ROMS 3D-model

The thermal front in the oceanic system is believed to have a significant effect on biological activity.During an era of climate change,changes in heat regulation between the atmosphere and oceanic interior can alter the characteristics of this important feature.Using the simulation results of the 3D Regional Ocean Modelling System(ROMS),we identified the location of thermal fronts and determined their dynamic variability in the area between the southern Andaman Sea and northern Malacca Strait.The Single Image Edge Detection(SIED)algorithm was used to detect the thermal front from model-derived temperature.Results show that a thermal front occurred every year from 2002 to 2012 with the temperature gradient at the location of the front was 0.3°C/km.Compared to the years affected by El Ni?o and negative Indian Ocean Dipole(IOD),the normal years(e.g.,May 2003)show the presence of the thermal front at every selected depth(10,25,50,and 75 m),whereas El Ni?o and negative IOD during 2010 show the presence of the thermal front only at depth of 75 m due to greater warming,leading to the thermocline deepening and enhanced stratification.During May 2003,the thermal front was separated by cooler SST in the southern Andaman Sea and warmer SST in the northern Malacca Strait.The higher SST in the northern Malacca Strait was believed due to the besieged Malacca Strait,which trapped the heat and make it difficult to release while higher chlorophyll a in Malacca Strait is due to the freshwater conduit from nearby rivers(Klang,Langat,Perak,and Selangor).Furthermore,compared to the southern Andaman Sea,the chlorophyll a in the northern Malacca Strait is easier to reach the surface area due to the shallower thermocline,which allows nutrients in the area to reach the surface faster.

基于InGaAs单光子探测器的线阵扫描激光雷达及其光子信号处理技术研究

随着探测体系的发展,基于单光子探测技术的光子计数激光雷达受到了广泛关注,有效降低了系统对激光功率的需求,广泛应用在远距离测距及成像领域。针对激光雷达在人眼安全波段的工作需求,基于自由运转模式InGaAs/InP SPAD单光子探测器设计了一套多元收发的远程线阵光子计数激光雷达扫描成像原型系统,对探测器在日光背景下的探测概率影响因素展开了分析,配合主动淬灭电路设计及工作温度、偏压调整获得了系统的最佳工作点,并针对扫描视场中孤立目标特征采用了点云滤波及后脉冲预处理算法,将单个接收通道的原始数据率由200 kbps量级降低至小于1 kbps。与记录单次回波相比,单个测距周期记录四次回波可将有效数据量提升约5%。同时也对探测器的噪声及后脉冲等特性进行了分析。该系统工作波段为1550 nm,探测器线阵规模可达到128元,激光重频为20 kHz,可在2 s内实现水平200°范围内的激光三维成像,作用距离>3 km。经过成像算法处理,该系统在日光条件下成功实现多距离目标三维成像,成像目标清晰。

Fast fluorescence lifetime imaging techniques:A review on challenge and development

Fluorescence lifetime imaging microscopy(FLIM)is increasingly used in biomedicine,material science,chemistry,and other related research fields,because of its advantages of high specificity and sensitivity in monitoring cellular microenvironments,studying interaction between proteins,metabolic state,screening drugs and analyzing their efficacy,characterizing novel materials,and diagnosing early cancers.Understandably,there is a large interest in obtaining FLIM data within an acquisition time as short as possible.Consequently,there is currently a technology that advances towards faster and faster FLIM recording.However,the maximum speed of a recording technique is only part of the problerm.The acquisition time of a FLIM image is a complex function of many factors.These include the photon rate that can be obtained from the sample,the amount of information a technique extracts from the decay functions,the fficiency at which it determines fluorescence decay parameters from the recorded photons,the demands for the accuracy of these parameters,the number of pixels,and the lateral and axial resolutions that are obtained in biological materials.Starting from a discussion of the parameters which determine the acquisition time,this review will describe existing and emerging FLIM techniques and data analysis algo-rithms,and analyze their performance and recording speed in biological and biomedical applications.

Camera Pose Estimation Using Collaborative Databases and Single Building Image

Cities are in constant change and city managers aim to keep an updated digital model of the city for city governance. There are a lot of images uploaded daily on image sharing platforms (as “Flickr”, “Twitter”, etc.). These images feature a rough localization and no orientation information. Nevertheless, they can help to populate an active collaborative database of street images usable to maintain a city 3D model, but their localization and orientation need to be known. Based on these images, we propose the Data Gathering system for image Pose Estimation (DGPE) that helps to find the pose (position and orientation) of the camera used to shoot them with better accuracy than the sole GPS localization that may be embedded in the image header. DGPE uses both visual and semantic information, existing in a single image processed by a fully automatic chain composed of three main layers: Data retrieval and preprocessing layer, Features extraction layer, Decision Making layer. In this article, we present the whole system details and compare its detection results with a state of the art method. Finally, we show the obtained localization, and often orientation results, combining both semantic and visual information processing on 47 images. Our multilayer system succeeds in 26% of our test cases in finding a better localization and orientation of the original photo. This is achieved by using only the image content and associated metadata. The use of semantic information found on social media such as comments, hash tags, etc. has doubled the success rate to 59%. It has reduced the search area and thus made the visual search more accurate.

Hyperspectral Imaging Based on Compressive Sensing: Determining Cancer Margins in Human Pancreatic Tissue <i>ex Vivo</i>, a Pilot Study

Cancer is the second-leading cause of death in the United State and surgery remains the primary treatment for most solid mass tumors. However, accurately identifying tumor margins in real-time remains a challenge. In this study, the design and testing of hyperspectral imaging (HSI) system based on a single-pixel camera engine is discussed. The primary advantage of a single pixel architecture over traditional scanning HSI techniques is its high sensitivity and potential to function at low light levels. The objective for the imaging system described here is to detect changes in the reflectance spectra of tissue and to use these differences to delineate tumor margins. This paper presents the results of a 19-patient pilot study that assesses the ability of the HSI system to use reflectance imaging to delineate adenocarcinoma tumor margins in human pancreatic tissue imaged ex vivo. Pancreatic tissue excised during pancreatectomy was imaged immediately after being sent to the pathology lab. A pathologist sectioned the tissue and placed samples into standard tissue embedding cassettes. These tissue samples were then imaged using the HSI system. After imaging, the samples were returned to the pathologist for processing and analysis. The HSI was later compared to the histological analysis. The spectral angle mapping (SAM) and support vector machine (SVM) algorithms were used to classify pixels in the HSI images as healthy or unhealthy in order to delineate margins. Good agreement between margins determined via HSI (using both SAM and SVM) and histology/white light imaging was found.

Fracture detecting based on Ant Colony Algorithm

Image processing plays an important role in engineering treatment. The authors mainly introduced the feature recognition of borehole image process based on Ant Colony Algorithm (ACA). The most important geological structure-fracture on the borehole image was identified, and quantitative parameters were obtained by HOUGH transform. Several case studies show that the method is feasible.

基于改进Faster RCNN的岩石热红外图像张剪裂纹检测

区分岩石破裂模式对矿山灾害防治具有重要意义,为了能够有效识别岩石破裂模式、监测破坏过程,提出了一种基于改进Faster RCNN的岩石热红外图像张剪裂纹检测算法。首先开展花岗岩单轴压缩试验,使用红外热像仪获取岩石破裂过程中的热红外图像,制作岩石红外裂隙数据集;然后对Faster RCNN网络模型进行改进,通过引入注意力引导的上下文特征金字塔网络对特征提取方法进行优化,采用级联结构提升检测框回归准确度,同时使用岩石红外裂隙数据集对模型进行训练及验证;最后对实测岩石红外图像进行张剪裂纹识别。试验结果表明:该算法检测精度达到了94.15%,每秒检测帧数为19.27 fps,综合性能得到显著提升,研究结果可为预测岩石破裂位置及破裂模式提供一种思路。

基于直线段检测和LT描述符的矿井图像线特征匹配算法

图像匹配是同步定位与地图构建(SLAM)技术中极为重要的一环,用于根据图像之间的变换关系确定相机位姿。基于线特征的图像匹配方法具有较强的鲁棒性和抗噪能力,更加适用于井下图像匹配,基于深度学习的线描述符对线段遮挡等场景具有较高的鲁棒性,性能优于传统描述符,但卷积神经网络架构的描述符将可变长度线段抽象为固定维进行描述,不利于线段长度及视差变化较大图像的匹配。针对上述问题,提出一种基于直线段检测和线描述符的矿井图像线特征匹配算法。在频域利用单参数同态滤波降低图像的照射分量,并增强反射分量,提升亮度及对比度;在YUV空间利用对比度受限的自适应直方图均衡化(CLAHE)算法对亮度分量进行均衡,使亮度分布更加均匀;变换至RGB空间提取直线段检测(LSD)线,引入一种基于Transformer架构的LT描述符构建LSD线的特征向量,最后完成线特征匹配。实验结果表明:该算法结合了同态滤波和CLAHE算法的优点,增强后图像的亮度适中,对比度良好,灰度分布均匀,增强效果优于单参数同态滤波算法、EnlightenGAN算法;该算法提取的线特征数较原图平均提升了32.92%,在不同相似纹理占比、不同程度旋转与平移变化的井下图像匹配中鲁棒性好,平均正确匹配数为61.75对,平均精度为86.83%,优于线二进制描述符(LBD)算法、LBD_NNDR算法、LT算法,能够满足矿井图像稳健匹配的需求。

G-APD阵列——一种具有单光子灵敏度的三维成像探测器

介绍了一种利用盖革模式雪崩二极管(G-APD)作为成像单元的新型阵列光电探测器,重点介绍了该新型成像光电探测器的关键技术、器件研发和系统应用的发展状况。G-APD阵列探测器兼具单光子探测灵敏度和皮秒级时间分辨率两大特点,适用于对极微弱光目标的三维成像探测。同时,G-APD阵列探测器又是一种全固态的光电探测器件,不仅体积小、重量轻、可靠性高,而且还可用现有的微光电子工艺进行规模化生产。因此,G-APD阵列是目前阵列光电探测器件的一个重大发展,必将在各种高端光电成像领域获得广泛的应用。

Single Particle Colorimetric Acid Phosphatase Activity Assay with CeO_(2)-modified Gold Nanoparticles

Acid phosphatase(ACP)is a ubiquitous phosphatase in living organisms.The abnormal variation of ACP is related to various diseases.Herein,we propose a colorimetric method based on CeO_(2)-modified gold core shell nanoparticles(Au@CeO_(2)NPs)to analyze ACP activity with high sensitivity and specificity.In this design,2-phospho-L-ascorbic acid trisodium salt(AAP)is dephosphorylated by ACP and produces reductive ascorbic acid(AA),which makes the CeO_(2)shell decomposition.A remarkable blue shift of localized surface plasmon resonance peak(LSPR,from yellow to green)along with the scattering intensity ratio changes from individual Au@CeO_(2)NPs are observed.ACP activity can be quantified by calculating the ratio changes of individual Au@CeO_(2)NPs.This assay reveals limit of detection(LOD)of 0.044 mU/mL and the linear range of 0.05–5.0 mU/mL,which are much lower than most of spectroscopic measurements in bulk solution.Furthermore,the recovery measurements in real samples are satisfactory and the capacity for practical application is demonstrated.As a consequence,Au@CeO_(2)NPs used in this assay will find new applications for the ultrasensitive detection of enzyme activity.

基于背景建模的VideoSAR动目标阴影检测方法

针对视频合成孔径雷达(video synthetic aperture radar,VideoSAR)数据进行地面运动目标检测的问题,本文提出了一种基于单高斯背景模型的VideoSAR动目标阴影检测方法。该方法使用一个时间维度的滑窗对视频序列进行处理:首先使用RED20深度神经网络模型抑制VideoSAR图像的斑点噪声,随后使用帧间配准算法快速配准窗口内的图像序列,然后对序列进行建模和差分得到窗口末帧的二值化前景,最后通过连通区域筛选和区域生长剔除虚假目标。采用美国Sandia国家实验室公布的VideoSAR视频对本文算法进行了验证,实验表明,该算法能实现对动目标阴影的准确检测。

星载SAR技术在智能交通中的应用浅析

分析星载SAR在交通领域中的应用,对2种传统交通监控方式进行概括说明,指出交通是卫星遥感技术的重要应用方向,并对3种遥感技术——低空遥感技术、星载光学遥感技术和星载SAR技术进行对比分析。重点介绍星载SAR的优缺点,对其在智能交通中的应用进行深刻分析,阐述其在路网信息探测、单车及车辆群运动状态感知3方面的应用前景,并指出其在交通应用中的重点技术突破方向。

运用GMS算法自动识别相似模拟材料实验裂隙场

通常采用沙盘物理模型与近距离摄影测量相结合的方法来探索上覆地层的断裂机制,但由于沙土物理模型裂缝图像的信噪比较低,该算法往往提取得不完整。鉴于此,提出了一种基于计算机视觉的图像梯度原理、图像匹配和区域筛选技术(GMS算法)的裂隙检测算法。首先利用峰峰市九龙煤矿15235工作面的钻孔柱状图建立沙盘物理模型;再利用定焦数码相机拍摄该模型的正射影像;最后根据模型图像的纹理特征,分别采用图像匹配技术、区域筛选技术分割规则的大面积非裂缝纹理和微小非裂缝纹理。研究结果表明,GMS算法具有很强的抗干扰能力,能准确识别并自动提取相似模拟材料中上覆地层的裂隙场。

纵向单裂隙分布位置对洞室围岩失稳特征影响试验研究

为研究纵向裂隙分布位置对洞室围岩失稳特征的影响规律,通过无预制裂隙洞室模型及含不同位置预制裂隙洞室模型双轴加载试验,结合数字图像技术(DIC)对比分析了洞室模型宏观力学参数及破坏模式。试验结果表明,随侧压力系数(λ)增大,洞室模型峰值强度和峰值应变呈先增大后减小趋势,在λ=1时达到最大值,弹性模量与之相反,呈先减小后增大趋势;从破坏模式来看,λ<1时,洞室破坏模式主要由张拉破坏逐渐转为拉剪复合破坏,裂隙位于拱顶,底板破坏明显,而裂隙位于直墙和底脚处,拱顶及底脚均破坏严重,随λ增大,λ≥1时,模型破坏以张拉裂纹为主,相比其他两个位置的裂隙,裂隙位于直墙,洞室稳定性最差;在相同λ下,高应变集中区会随裂隙位置改变而发生转移,但高应变区主要集中在预制裂隙端及洞室两底脚处。

光电膜层光电特性的成像测量

光电探测器的光电膜层的光电特性与膜层上各点的吸收系数和光电转换系数有关.为了测量光电膜层光电特性的二维空间分布,提出了基于单像素成像的膜层光电特性测量方法.在该方法中,光电膜层既是成像对象,又是信号探测器,可以实现自探测成像.采用四步相移条纹投影方法,导出膜层光电特性单像素成像公式;以光电池膜层为研究对象,采用白光、红光、绿光和蓝光对其光电特性进行二维成像.实验结果表明:该方法能够以一定的空间分辨率对光电膜层的光电特性进行成像测量,空域上的灰度平均值和标准方差、频域上的频谱分布特点可以评估膜层的光电特性强弱和均匀性.

基于迅颈模块与单解耦头的航拍车辆检测方法

无人机航拍图像的目标检测需要大量计算资源,导致其在移动端上的应用受到限制,为此提出一种轻量化目标检测网络Faster S。首先,在颈部网络设计了由部分卷积和组卷积组成的轻薄迅颈模块,用以有效聚合不同尺度的信息;其次,在检测头部分设计了一种高效、轻量化的单解耦头输出结构(SDHEAD),用以进一步分离目标检测中分类和定位两个子任务的特征编码。在航拍车辆数据集CARPK上的实验结果表明:与特征金字塔网络(FPN)结构相比,采用迅颈模块提高了模型的检测精度,减少了模型的参数量;相比于其他检测头,SDHEAD具有更强的特征辨别能力;Faster S模型检测的平均精度(AP_(0.5))达到了70.9%,较Yolo-FastestV2提高了12.7%,较Fastestdet提高了3.5%,推理时间仅为29.56 ms,较Nanodet-m降低了76%,模型参数量仅为0.335 M。

数字化X射线摄影与SPECT核素骨显像联合诊断股骨粗隆间骨折的价值

目的:探讨数字化X射线摄影与单光子发射计算机体层扫描(SPECT)核素骨显像对股骨粗隆间骨折的应用价值。方法:选择2017年1月至2020年12月在石家庄市人民医院就诊并诊断为股骨粗隆间骨折的70例患者,按照随机数表法将其分为观察组和对照组,每组35例,观察组采用数字化X射线摄影联合SPECT核素骨显像进行诊断,对照组采用数字化X射线摄影进行诊断,对比两组诊断结果的准确性。结果:经影像学检测,观察组35例患者中确诊31例(占88.6%),对照组35例患者中确诊24例(占68.6%),观察组诊断准确率高于对照组,差异有统计学意义(x^(2)=4.158,P<0.05)。术前经影像诊断,观察组诊断的骨折块数为(3.57±0.50)块,对照组诊断的骨折块数为(2.67±0.40)块,观察组骨折诊断块数高于对照组,差异有统计学意义(t=8.315,P<0.05);观察组中骨质连续性5例,非连续性30例,对照组中骨质稳定性13例,非稳定性22例,观察组更接近术中骨质连续性和稳定性,两组连续性和稳定性比较差异有统计学意义(x^(2)=12.857、4.644,P<0.05)。结论:数字化X射线摄影联合SPECT核素骨显像对股骨粗隆间骨折具有较高的诊断价值,可为临床诊断提供重要的参考依据。

坚硬顶板综放工作面导水裂隙带高度研究

当顶板导水裂隙带发育至水体时,水体会沿着裂隙进入工作面,破坏矿井的生态环境,影响工作安全及效益。以盘城岭煤矿15#煤层150105工作面为研究对象,通过经验计算公式分析导水裂隙带的发育高度,并结合仰孔注水测漏法及钻孔电视成像法,综合确定15#煤层导水裂隙带的发育高度。结果表明,经验计算公式预测导水裂隙带最大发育高度为81.56 m,仰孔注水测漏法为79.99 m,钻孔电视成像法为79.46 m。最终得出经验公式计算的高度与现场实测的结果高度一致,均可为盘城岭煤矿15#煤层水害防治及安全生产提供指导。