Multi-Spectral and Fluorescence Imaging in Prevention of Overdose of Herbicides: The Case of Maize

Evaluation of the impact of herbicides on maize was done through multi- spectral and multi-modal imaging and multi-spectral fluorescence imaging combined with statistical methods. Spectra containing 13 wavelengths ranging from 375 nm to 940 nm were derived from multi-spectral images in transmission, reflection and scattering mode and fluorescence images obtained using high-pass filters (F450 nm, F500 nm, F550 nm, F600 nm, F650 nm) on control maize samples and maize samples treated with Herbextra herbicide were used. The appearance of the spectra allowed us to characterize the effect of the herbicide on the maize pigment concentration. The fluorescence images allowed us to track the fate of absorbed energy and through PLS-DA and SVM-DA to discriminate the two leaf categories with very low error rates for the test, i.e. 4.9% and 2% respectively. The results of this technique can be used in the context of precision agriculture.

Screen-imaging guidance using a modified portable video macroscope for middle cerebral artery occlusion

The use of operating microscopes is limited by the focal length.Surgeons using these instruments cannot simultaneously view and access the surgical field and must choose one or the other.The longer focal length （more than 1 000 mm） of an operating telescope permits a position away from the operating field,above the surgeon and out of the field of view.This gives the telescope an advantage over an operating microscope.We developed a telescopic system using screen-imaging guidance and a modified portable video macroscope constructed from a Computar MLH-10 × macro lens,a DFK-21AU04 USB CCD Camera and a Dell laptop computer as monitor screen.This system was used to establish a middle cerebral artery occlusion model in rats.Results showed that magnification of the modified portable video macroscope was appropriate （5-20 ×） even though the Computar MLH-10 × macro lens was placed 800 mm away from the operating field rather than at the specified working distance of 152.4 mm with a zoom of 1-40 ×.The screen-imaging telescopic technique was clear,life-like,stereoscopic and matched the actual operation.Screen-imaging guidance led to an accurate,smooth,minimally invasive and comparatively easy surgical procedure.Success rate of the model establishment evaluated by neurological function using the modified neurological score system was 74.07%.There was no significant difference in model establishment time,sensorimotor deficit and infarct volume percentage.Our findings indicate that the telescopic lens is effective in the screen surgical operation mode referred to as ＂long distance observation and short distance operation＂ and that screen-imaging guidance using an modified portable video macroscope can be utilized for the establishment of a middle cerebral artery occlusion model and micro-neurosurgery.

Method for Obtaining Line-of-Sight Rate with a Strap-down Imaging Guidance

In the strap-down TV guidance system, the line-of-sight（LOS） rate can not be obtained frora the measured information, the math platform to select missile attitude information must be set up. The LOS rate selecting models based on the missile attitude angle and the rate gyro are set up, the influencing factor and the extracting precision of LOS rate are emulated and analyzed.

A new imaging mode based on X-ray CT as prior image and sparsely sampled projections for rapid clinical proton CT

Proton computed tomography(CT)has a distinct practical significance in clinical applications.It eliminates 3–5%errors caused by the transformation of Hounsfield unit(HU)to relative stopping power(RSP)values when using X-ray CT for positioning and treatment planning systems(TPSs).Following the development of FLASH proton therapy,there are increased requirements for accurate and rapid positioning in TPSs.Thus,a new rapid proton CT imaging mode is proposed based on sparsely sampled projections.The proton beam was boosted to 350 MeV by a compact proton linear accelerator(LINAC).In this study,the comparisons of the proton scattering with the energy of 350 MeV and 230 MeV are conducted based on GEANT4 simulations.As the sparsely sampled information associated with beam acquisitions at 12 angles is not enough for reconstruction,X-ray CT is used as a prior image.The RSP map generated by converting the X-ray CT was constructed based on Monte Carlo simulations.Considering the estimation of the most likely path(MLP),the prior image-constrained compressed sensing(PICCS)algorithm is used to reconstruct images from two different phantoms using sparse proton projections of 350 MeV parallel proton beam.The results show that it is feasible to realize the proton image reconstruction with the rapid proton CT imaging proposed in this paper.It can produce RSP maps with much higher accuracy for TPSs and fast positioning to achieve ultra-fast imaging for real-time image-guided radiotherapy(IGRT)in clinical proton therapy applications.

Identification of a Printed Anti-Counterfeiting Code Based on Feature Guidance Double Pool Attention Networks

The authenticity identification of anti-counterfeiting codes based on mobile phone platforms is affected by lighting environment,photographing habits,camera resolution and other factors,resulting in poor collection quality of anti-counterfeiting codes and weak differentiation of anti-counterfeiting codes for high-quality counterfeits.Developing an anticounterfeiting code authentication algorithm based on mobile phones is of great commercial value.Although the existing algorithms developed based on special equipment can effectively identify forged anti-counterfeiting codes,the anti-counterfeiting code identification scheme based on mobile phones is still in its infancy.To address the small differences in texture features,low response speed and excessively large deep learning models used in mobile phone anti-counterfeiting and identification scenarios,we propose a feature-guided double pool attention network(FG-DPANet)to solve the reprinting forgery problem of printing anti-counterfeiting codes.To address the slight differences in texture features in high-quality reprinted anti-counterfeiting codes,we propose a feature guidance algorithm that creatively combines the texture features and the inherent noise feature of the scanner and printer introduced in the reprinting process to identify anti-counterfeiting code authenticity.The introduction of noise features effectively makes up for the small texture difference of high-quality anti-counterfeiting codes.The double pool attention network(DPANet)is a lightweight double pool attention residual network.Under the condition of ensuring detection accuracy,DPANet can simplify the network structure as much as possible,improve the network reasoning speed,and run better on mobile devices with low computing power.We conducted a series of experiments to evaluate the FG-DPANet proposed in this paper.Experimental results show that the proposed FG-DPANet can resist highquality and small-size anti-counterfeiting code reprint forgery.By comparing with the existing algorithm based on texture,it is shown that the proposed method has a higher authentication accuracy.Last but not least,the proposed scheme has been evaluated in the anti-counterfeiting code blurring scene,and the results show that our proposed method can well resist slight blurring of anti-counterfeiting images.

Robust key point descriptor for multi-spectral image matching

Histogram of collinear gradient-enhanced coding （HCGEC）, a robust key point descriptor for multi-spectral image matching, is proposed. The HCGEC mainly encodes rough structures within an image and suppresses detailed textural information, which is desirable in multi-spectral image matching. Experiments on two multi-spectral data sets demonstrate that the proposed descriptor can yield significantly better results than some state-of- the-art descriptors.

A Systematic Literature Review of Machine Learning and Deep Learning Approaches for Spectral Image Classification in Agricultural Applications Using Aerial Photography

Recently,there has been a notable surge of interest in scientific research regarding spectral images.The potential of these images to revolutionize the digital photography industry,like aerial photography through Unmanned Aerial Vehicles(UAVs),has captured considerable attention.One encouraging aspect is their combination with machine learning and deep learning algorithms,which have demonstrated remarkable outcomes in image classification.As a result of this powerful amalgamation,the adoption of spectral images has experienced exponential growth across various domains,with agriculture being one of the prominent beneficiaries.This paper presents an extensive survey encompassing multispectral and hyperspectral images,focusing on their applications for classification challenges in diverse agricultural areas,including plants,grains,fruits,and vegetables.By meticulously examining primary studies,we delve into the specific agricultural domains where multispectral and hyperspectral images have found practical use.Additionally,our attention is directed towards utilizing machine learning techniques for effectively classifying hyperspectral images within the agricultural context.The findings of our investigation reveal that deep learning and support vector machines have emerged as widely employed methods for hyperspectral image classification in agriculture.Nevertheless,we also shed light on the various issues and limitations of working with spectral images.This comprehensive analysis aims to provide valuable insights into the current state of spectral imaging in agriculture and its potential for future advancements.

Investigation of the Guidance Law for an Image Homing Guidance System

This paper aims at a type of image homing guided missile. The guided trajectory characteristics and the initial condition of the homing guidance are analyzed by calculating the miss distance of the image guided missile. Several modified proportional navigation laws which are easy for engineering implementation are introduced.

Image-Based Mobile Robot Guidance System by Using Artificial Ceiling Landmarks

This paper presents an image-based mobile robot guidance system in an indoor space with installed artificial ceiling landmarks. The overall system, including an omni-directional mobile robot motion control, landmark image processing and image recognition, is implemented on a single FPGA chip with one CMOS image sensor. The proposed feature representation of the artificial ceiling landmarks is invariant with respect to rotation and translation. One unique feature of the proposed ceiling landmark recognition system is that the feature points of landmarks are determined by topological information from both the foreground and background. To enhance recognition accuracy, landmark classification is performed after the mobile robot is moved to a position such that the ceiling landmark is located in the upright- top corner position of the robot’s camera image. The accuracy of the proposed artificial ceiling landmark recognition system using the nearest neighbor classification is 100% in our experiments.

Stereotactic guidance for navigated percutaneous sacroiliac joint fusion

Arthrodesis of the sacroiliac joint（SIJ） for surgical treatment of SIJ dysfunction has regained interest among spine specialists.Current techniques described in the literature most often utilize intraoperative fluoroscopy to aid in implant placement;however,image guidance for SIJ fusion may allow for minimally invasive percutaneous instrumentation with more precise implant placement.In the following cases,we performed percutaneous stereotactic navigated sacroiliac instrumentation using O-arm^（？）multidimensional surgical imaging with StealthStation^（？）navigation（Medtronic,Inc.Minneapolis,MN）.Patients were positioned prone and an image-guidance reference frame was placed contralateral to the surgical site.O-arm^（？） integrated with StealthStation^（？） allowed immediate autoregistration.The skin incision was planned with an image-guidance probe.An image-guided awl,drill and tap were utilized to choose a starting point and trajectory.Threaded titanium cage（s） packed with autograft and/or allograft were then placed.O-arm^（？） image-guidance allowed for implant placement in the SIJ with a small skin incision.However,we could not track the cage depth position with our current system,and in one patient,the SIJ cage had to be revised secondary to the anterior breach of sacrum.

Actuation Delay-Time Estimation with Imaging Fuze

Generally,Doppler fuze can only estimate actuation delay-time with a limited precision. As an improvement,imaging fuze can estimate actuation delay-time more precisely with the available two-dimensional image of the target. In this paper,imprecision of actuation delay-time estimation with Doppler fuze is first analyzed theoretically in brief. Secondly,feasibility analysis and theoretical model of imaging fuze are described,in which a criterion is established for the actuation delay-time based on the image,and then an image based gray-value weighted least square（ GWLS） algorithm is presented to calculate actuation delay-time of the imaging fuze. Finally,a simulation model of missiletarget near-field encounter is established. Simulation results indicate that actuation delay-time of the imaging fuze is estimated more precisely than by the Doppler fuze.

MICROENDOSCOPIC SPECTRAL IMAGING AS A TOOL FOR SMALL DUCTUAL DIAGNOSTICS:PRELIMINARY EXPERIENCE

A technical feasibility of autofluorescence ductoscopy in breast milk ducts as blood vessels phantoms has been assessed as successful.Malignant tumor can be clearly identified through the milk ducts.We also present the operation principle as well as the preliminary experimental results of a new type of microsize multicorefiber that enables imaging through blood vessel phantoms.Imaging of a manipulated microwire through a drilled phantom is presented.

LIMITATIONS OF CANCER MARGIN DELINEATION BY MEANS OF AUTOFLUORESCENCE IMAGING UNDER CONDITIONS OF LASER SURGERY

Limitations of cancer margin delineation and surgical guidance by means of autofluorescence imaging under conditions of laser ablation were investigated and preliminary results are presented.PinPoint^(TM)(Novadaq Technologies Inc.,Canada)was used to capture digital images and Er:YAG laser(2.94μm,Glissando,WaveLight^(TM),Germany)was exploited to cause laser ablation on both normal and cancer sites of the specimen.It was shown that changes of the autofluorescence image after ablation extend beyond the actual sizes of the ablation loci.The tumor tissue after the laser ablation starts to emit fluorescent light within the green wavelength band(490-550nm)similar to normal tissue stating that the current technology of in-process tissue classification fails.However,when the autofluorescence was collected in the red range(600-750nm),then the abnormal/normal contrast was reduced,but still present even after the laser ablation.The present study highlights the importance of finding a proper technology for surgical navigation of cancer removal under conditions of high power effects in biological tissues.

Ultrasound Needle Guidance System for Precision Vaccinations and Drug Deliver

Image-guided needles are currently used for drug delivery in bodies, but the additional time associated with aligning and maintaining the needle’s position results in increased patient discomfort or risk of invasion of the human body. In this paper, a needle guidance system using piezoelectric materials is designed and analyzed for precise drug delivery without damaging parts of the body and improving processing time. A piezoelectric generates an ultrasound wave that can propagate through different mediums, and a second piezoelectric crystal can receive that energy and convert it into voltage. A 1D real-time image represents the changes of the voltage induced in the double piezoelectric crystal. Extensive data analysis and visualization are done using different obstacles and location of the needle verified for other mediums. The presence of obstacles in between those crystals can be identified in the real-time grayscale image. The needle can reach its destination using this image information as directional guidance. This guided drug delivery improves patient recovery time and eliminates extra injuries that can be caused due to wrong needle injections, such as lumbar puncture-related nerve damage.

Application of PCA Numalgorithm in Remote Sensing Image Processing

A numerical algorithm of principal component analysis (PCA) is proposed and its application in remote sensing image processing is introduced: (1) Multispectral image compression;(2) Multi-spectral image noise cancellation;(3) Information fusion of multi-spectral images and spot panchromatic images. The software experiments verify and evaluate the effectiveness and accuracy of the proposed algorithm.

CTA/CTP评估在缺血性脑血管病介入治疗中的应用

目的探讨CT血管成像(CTA)/CT灌注成像(CTP)在缺血性脑血管病介入治疗中的应用价值。方法选取2021年1月至2023年9月我院收治的200例缺血性脑血管病患者,均在入院后接受CTA及CTP检查,分析其影像资料,探究CTA及CTP缺血性脑血管病介入治疗中的应用价值。结果脑血容量(CBV)比较:缺血半暗带>健侧>梗死区(P<0.05);脑血流量(CBF)比较:健侧>缺血半暗带>梗死区(P<0.05);平均通过时间(MTT)、目标组织中浓度达峰时间(TTP)、目标组织中所有残余功能全部达峰时间(Tmax)比较:健侧<缺血半暗带<梗死区(P<0.05)。CTA检出左侧、右侧大脑中动脉(MCA)闭塞或狭窄分别59例(29.50%)、91例(45.50%),左侧、右侧颈内动脉(ICA)闭塞分别16例(8.00%)、12例(6.00%),双侧ICA狭窄为6例(3.00%);代偿分支血管显影基本满意129例(64.50%),显影不足71例(35.50),其余16例(8.00%)患者CTA影像资料显示无异常,敏感度为92.00%。预后不良组患侧CBV、CBF小于预后良好组,MTT、TTP、Tmax长于预后良好组,代偿血管建立比例低于预后良好组(P<0.05)。采用受试者工作特征曲线分析显示,CBV、CBF、MTT、TTP、Tmax对介入治疗预后均有一定的预测效能(P<0.05),其曲线下面积分别为0.839、0.815、0.673、0.713、0.710,其中CBV预测效能最高,敏感性为83.20%,特异性为73.33%。结论CTA/CTP可反映大脑、颈内动脉狭窄或闭塞、代偿分支建立情况,也可反映血流灌注情况,在介入治疗合理时机的判断方面可提供准确依据,提高患者预后。

一种基于优化引导的无线联邦学习异步训练机制

针对在数据异构和资源异构的无线网络中联邦学习训练效率低及训练能耗高的问题,面向图像识别任务,提出了基于优化引导的异步联邦学习算法AFedGuide。利用较高样本多样性的客户端模型的引导作用,提高单轮聚合有效性。采用基于训练状态的模型增量异步更新机制,提高模型更新实时性以及信息整合能力。设计基于模型差异性的训练决策,修正优化方向。仿真结果显示,相较于对比算法,AFedGuide的训练时长平均减少67.78%,系统能耗平均节省65.49%,客户端的准确率方差平均减少25.5%,说明在客户端数据异构和资源异构的无线网络下,AFedGuide可以在较短的训练时间内以较小的训练能耗完成训练目标,并维持较高的训练公平性和模型适用性。

基于局部-全局特征耦合与边界引导的遥感图像建筑物变化检测

针对现有变化检测方法局部特征和全局特征难以兼顾、变化对象和背景之间分界模糊的问题,提出了一种基于局部-全局特征耦合与边界引导的遥感图像建筑物变化检测方法。该方法在编码阶段采用并行的卷积神经网络和Transformer分别提取遥感图像的局部特征与全局表示。在不同尺度下,使用局部-全局特征耦合模块融合局部特征和全局特征表示,以增强图像特征的表达能力。引入边界引导分支获取变化对象的先验边界信息,使其引导变化图突出建筑物的结构特征,促进边界精确定位。该方法在LEVIRCD和WHU数据集上进行实验验证,其F 1-score分别为91.25%和91.27%,IoU分别为83.90%和83.95%。实验结果表明,该方法在检测精度上有较大的提升,且具有良好的泛化能力。

磁共振介入成像及其临床应用进展

介入治疗在神经、血管和乳腺等手术中广泛使用。在影像学检查引导下,机器人辅助的介入治疗可以有效提高介入治疗的精准性和安全性,已成为当前介入手术的重要发展方向。与其他介入成像方法相比,磁共振介入成像(interventional magnetic resonance imaging, i-MRI)具有高软组织对比度、多对比度、可定量成像、无电离辐射等优点,在介入治疗的引导中具有巨大优势。然而,磁共振成像(magnetic resonance imaging,MRI)的成像速度相对较慢,对介入器械的兼容性要求高,是当前i-MRI引导治疗中面临的主要挑战。得益于快速i-MRI以及磁兼容介入设备等技术的发展,i-MRI在神经介入、心血管介入、前列腺介入以及乳腺介入等临床手术中发挥了重要的作用。本文总结i-MRI技术的发展现状及i-MRI的临床应用现状,分析i-MRI目前所面临的成像速度慢和时空分辨率难以平衡等挑战,并对i-MRI在多模态成像、实时MRI以及i-MRI引导下的介入机器人手术等方面的发展机遇进行展望。

基于照度图引导的低照度图像增强网络

在低照度环境下采集的图像,由于光照的不均匀性,存在能见度差、对比度低和颜色失真等问题.现有的大多数低照度图像增强方法存在过增强或欠增强的现象,影响视觉感知和后续目标检测任务.针对上述问题,提出一种基于照度图引导的低照度图像增强网络.首先根据低照度图像的灰度分布特点构造对应的照度图,度量低照度图像不同区域块的明暗程度;然后利用照度图作为网络增强的引导图,与低照度图像一起送入图像增强网络来获得增强后的图像.为了解决训练数据不足的问题,提出一种基于内循环和概率旋转的数据增强方法来扩充训练数据样本的数量和多样性;同时,针对目前图像增强方法中普遍存在照度不均匀的问题,基于直方图匹配的思想构建一种直方图损失函数,约束并指导网络的训练.在合成数据集LOL和真实图像上的实验结果表明,所提网络在低照度图像增强方面获得了更好的主观视觉效果;与经典的RetinexNet方法相比,所提方法在PSNR和SSIM客观定量指标上分别提高了7.905 dB和0.328;该网络对后续目标检测任务的检测率可提高10.17%~17.19%.