Multi-class classification of pathological myopia based on fundus photography

Pathological myopia(PM)is a severe ocular disease leading to blindness.As a traditional noninvasive diagnostic method,fundus color photography(FCP)is widely used in detecting PM due to its highfidelity and precision.However,manual examination of fundus photographs for PM is time-consuming and prone to high error rates.Existing automated detection technologies have yet to study the detailed classification in diagnosing different stages of PM lesions.In this paper,we proposed an intelligent system which utilized Resnet101 technology to multi-categorically diagnose PM by classifying FCPs with different stages of lesions.The system subdivided different stages of PM into eight subcategories,aiming to enhance the precision and efficiency of the diagnostic process.It achieved an average accuracy rate of 98.86%in detection of PM,with an area under the curve(AUC)of 98.96%.For the eight subcategories of PM,the detection accuracy reached 99.63%,with an AUC of 99.98%.Compared with other widely used multi-class models such as VGG16,Vision Transformer(VIT),EfficientNet,this system demonstrates higher accuracy and AUC.This artificial intelligence system is designed to be easily integrated into existing clinical diagnostic tools,providing an efficient solution for large-scale PM screening.

Warhead fragments motion trajectories tracking and spatio-temporal distribution reconstruction method based on high-speed stereo photography

High speed photography technique is potentially the most effective way to measure the motion parameter of warhead fragment benefiting from its advantages of high accuracy,high resolution and high efficiency.However,it faces challenge in dense objects tracking and 3D trajectories reconstruction due to the characteristics of small size and dense distribution of fragment swarm.To address these challenges,this work presents a warhead fragments motion trajectories tracking and spatio-temporal distribution reconstruction method based on high-speed stereo photography.Firstly,background difference algorithm is utilized to extract the center and area of each fragment in the image sequence.Subsequently,a multi-object tracking(MOT)algorithm using Kalman filtering and Hungarian optimal assignment is developed to realize real-time and robust trajectories tracking of fragment swarm.To reconstruct 3D motion trajectories,a global stereo trajectories matching strategy is presented,which takes advantages of epipolar constraint and continuity constraint to correctly retrieve stereo correspondence followed by 3D trajectories refinement using polynomial fitting.Finally,the simulation and experimental results demonstrate that the proposed method can accurately track the motion trajectories and reconstruct the spatio-temporal distribution of 1.0×10^(3)fragments in a field of view(FOV)of 3.2 m×2.5 m,and the accuracy of the velocity estimation can achieve 98.6%.

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.

Atmospheric transmission algorithm for pulsed X-rays from high-altitude nuclear detonations based on scattering correction

In high-altitude nuclear detonations,the proportion of pulsed X-ray energy can exceed 70%,making it a specific monitoring signal for such events.These pulsed X-rays can be captured using a satellite-borne X-ray detector following atmospheric transmission.To quantitatively analyze the effects of different satellite detection altitudes,burst heights,and transmission angles on the physical processes of X-ray transport and energy fluence,we developed an atmospheric transmission algorithm for pulsed X-rays from high-altitude nuclear detonations based on scattering correction.The proposed method is an improvement over the traditional analytical method that only computes direct-transmission X-rays.The traditional analytical method exhibits a maximum relative error of 67.79% compared with the Monte Carlo method.Our improved method reduces this error to within 10% under the same conditions,even reaching 1% in certain scenarios.Moreover,its computation time is 48,000 times faster than that of the Monte Carlo method.These results have important theoretical significance and engineering application value for designing satellite-borne nuclear detonation pulsed X-ray detectors,inverting nuclear detonation source terms,and assessing ionospheric effects.

Pulmonary Edema and Pleural Effusion Detection Using Efficient Net-V1-B4 Architecture and AdamW Optimizer from Chest X-Rays Images

This paper presents a novelmulticlass systemdesigned to detect pleural effusion and pulmonary edema on chest Xray images,addressing the critical need for early detection in healthcare.A new comprehensive dataset was formed by combining 28,309 samples from the ChestX-ray14,PadChest,and CheXpert databases,with 10,287,6022,and 12,000 samples representing Pleural Effusion,Pulmonary Edema,and Normal cases,respectively.Consequently,the preprocessing step involves applying the Contrast Limited Adaptive Histogram Equalization(CLAHE)method to boost the local contrast of the X-ray samples,then resizing the images to 380×380 dimensions,followed by using the data augmentation technique.The classification task employs a deep learning model based on the EfficientNet-V1-B4 architecture and is trained using the AdamW optimizer.The proposed multiclass system achieved an accuracy(ACC)of 98.3%,recall of 98.3%,precision of 98.7%,and F1-score of 98.7%.Moreover,the robustness of the model was revealed by the Receiver Operating Characteristic(ROC)analysis,which demonstrated an Area Under the Curve(AUC)of 1.00 for edema and normal cases and 0.99 for effusion.The experimental results demonstrate the superiority of the proposedmulti-class system,which has the potential to assist clinicians in timely and accurate diagnosis,leading to improved patient outcomes.Notably,ablation-CAM visualization at the last convolutional layer portrayed further enhanced diagnostic capabilities with heat maps on X-ray images,which will aid clinicians in interpreting and localizing abnormalities more effectively.

Single Tooth Segmentation on Panoramic X-Rays Using End-to-End Deep Neural Networks

In dentistry, panoramic X-ray images are extensively used by dentists for tooth structure analysis and disease diagnosis. However, the manual analysis of these images is time-consuming and prone to misdiagnosis or overlooked. While deep learning techniques have been employed to segment teeth in panoramic X-ray images, accurate segmentation of individual teeth remains an underexplored area. In this study, we propose an end-to-end deep learning method that effectively addresses this challenge by employing an improved combinatorial loss function to separate the boundaries of adjacent teeth, enabling precise segmentation of individual teeth in panoramic X-ray images. We validate the feasibility of our approach using a challenging dataset. By training our segmentation network on 115 panoramic X-ray images, we achieve an intersection over union (IoU) of 86.56% for tooth segmentation and an accuracy of 65.52% in tooth counting on 87 test set images. Experimental results demonstrate the significant improvement of our proposed method in single tooth segmentation compared to existing methods.

光照不均匀条件下无人机航拍低照度图像增强方法

增强图像时高低频参数未增强,没有更好地保留图像的细节和平衡图像的亮度,因此,提出一种光照不均匀条件下无人机航拍低照度图像增强方法。首先通过高斯滤波预处理无人机航拍图像,实现无人机航拍图像中的噪声抑制,将预处理后的图像通过小波分解得到图像的高频参数和低频参数,分别通过双边滤波算法、软阈值方法和直方图对图像的低频参数和高频参数进行增强,采用小波重构对增强后的图像高频参数和低频参数进行重构,得到增强后的无人机航拍图像。通过实验验证,该方法能够实现一种效果较好的图像增强,在原始图像基础上,通过文中方法增强原始亮度8.14%、对比度提高了37.90%以及清晰度增加了31.01%,使得图像的整体质量得到了显著提升,为后续的图像分析、处理提供了更加准确、丰富的信息。

Investigating Jet Appearance in Different Background Lights with High-Speed Frame Photography

Shaped charge jet formation process is studied under the conditions of different background lights by means of high speed frame photography. In order to shoot true jet appearance, the glass tube in which jet moves is vacuumized. The experiment results show that observing jet appearance with the double reflecting mirrors system is feasible as long as the vacuum of the glass tube can meet the requirement of experiment.

肺癌骨转移^(99m)Tc-MDP骨显像的临床价值及与CT、X-rays检查对比观察

目的 评价99mTc MDP骨显像诊断肺癌骨转移的临床价值。方法 12 8例肺癌骨转移患者常规行99mTc MDP骨显像检查。 91例患者同时行骨显像、CT检查 :74例病变部位相符者同时行骨显像、X rays检查。分别对比观察99mTc MDP骨显像与CT、X rays诊断肺癌骨转移的阳性检出率 ,并分析相互之间产生差异的原因和机制。结果 全部病例中 ,99mTc MDP骨显像阳性检出率为 91.4% (117/12 8) ,假阳性率为 12 .0 % (16/13 3 ) ,假阴性率 8.5 9% (11/12 8) ;对比观察99mTc MDP骨显像与CT ,阳性检出率分别为 85 .7% (78/91)、2 9.7% (2 2 /74) ,(P <0 .0 1,已剔除部位不相符因素 ,但未剔除X线检查部位包括不全因素 )。结论 99mTc MDP骨显像诊断肺癌骨转移具有较高的临床价值 ,辅以CT、X rays检查可提高阳性诊断的准确性。

Structure and electrochemical performance of delafossite AgFeO_(2)nanoparticles for supercapacitor electrodes

Delafossite AgFeO_(2)nanoparticles with a mixture of 2H and 3R phases were successfully fabricated by using a simple co-precipitation method.The resulting precursor was calcined at temperatures of 100,200,300,400,and 500℃to obtain the delafossite AgFe0_(2)phase.The morphology and microstructure of the prepared AgFeO_(2)samples were characterized by using field emission scanning electron microscopy(FESEM),transmission electron microscopy(TEM),N_(2) adsorption/desorption,X-ray absorption spectroscopy(XAS),and Xray photoelectron spectroscopy(XPS)techniques.A three-electrode system was employed to investigate the electrochemical properties of the delafossite AgFeO_(2)nanoparticles in a 3 M KOH electrolyte.The delafossite AgFeO_(2)nanoparticles calcined at 100℃(AFO100)exhibited the highest surface area of 28.02 m^(2)·g^(-1)and outstanding electrochemical performance with specific capacitances of 229.71 F·g^(-1)at a current density of 1 A·g^(-1)and 358.32 F·g^(-1)at a scan rate of 2 mV·s^(-1).This sample also demonstrated the capacitance retention of 82.99% after 1000 charge/discharge cycles,along with superior specific power and specific energy values of 797.46 W·kg^(-1)and 72.74Wh·kg^(-1),respectively.These findings indicate that delafossite AgFeO_(2)has great potential as an electrode material for supercapacitor applications.

Investigation of bubbles escape behavior from low basicity mold flux for high-Mn high-Al steels using 3D X-ray microscope

During the continuous casting process of high-Mn high-Al steels,various types of gases such as Ar need to escape through the top of the mold.In which,the behavior of bubbles traversing the liquid slag serves as a restrictive link,closely associated with viscosity and the thickness of liquid slag.In contrast to two-dimensional surface observation,three-dimensional(3D)analysis method can offer a more intuitive,accurate,and comprehensive information.Therefore,this study employs a 3D X-ray microscope(3D-XRM)to obtained spatial distribution and 3D morphological characteristics of residual bubbles in mold flux under different basicity of liquid slag,different temperatures,and different holding times.The results indicate that as basicity of slag increases from 0.52 to 1.03,temperature increases from 1423 to 1573 K,the viscosity of slag decreases,the floating rate of bubbles increases.In addition,when holding time increases from 10 to 30 s,the bubbles floating distance increases,and the volume fraction and average equivalent sphere diameter of the bubbles solidified in the mold flux gradually decreases.In one word,increasing the basicity,temperature,and holding time leading to an increase in the removal rate of bubbles especially for the large.These findings of bubbles escape behavior provide valuable insights into optimizing low basicity mold flux for high-Mn high-Al steels.

Problems and improvement strategies of photography education in Colleges and Universities

In recent years, with the development of social economy, college photography education career has been developing rapidly, but at the same time, some problems have appeared. In the construction of photography specialty, a series of problems, such as unreasonable course arrangement, outdated hardware facilities and imperfect teaching software system, are hindering the de-velopment of photography education in universities. Therefore, college educators should seriously sum up the problems existing in college photography education, and carry out photography teaching reasonably and scientifically.

On the Improvement Method of Photography Practice Teaching

Photography teaching is different from general culture teaching.There are obvious differences in teaching methods and teachers' teaching styles.To this end,photography teaching should be innovative,really interested in students,love the photography course,and put photography knowledge into practice.At present,some photography teachers have some problems in the way of explai-ning photography knowledge,which makes it difficult for students to really grasp the practical knowledge of photography,and is not conducive to arousing students' interest in learning. The reason is that photography teachers do not attach importance to practical teaching.

基于线性特征边界线的实景三维动态更新关键技术研究

实景三维中国建设是落实数字中国、平安中国、数字经济战略的重要举措,是新时期国家重要新型基础设施,是服务生态文明建设和经济社会发展的基础支撑。“十四五”以来,各地已经陆续开展了一定规模的实景三维建设项目,积累了不同尺度的实景三维底板数据。如何充分利用已有建设成果,且持续保障实景三维数据的时效性、可用性,已经成为下一个亟需解决的问题。文章针对实景三维数据的场景特征属性,提出一种线性特征边界线的实景三维动态更新和场景融合的方案。基于原有场景数据,将目标更新区域最邻近线性特征边界线作为实际更新范围,对其进行切割、拼接、调色、融合等处理,实现多期实景三维数据的无缝融合。

Full-field mapping of internal strain distribution in red sandstone specimen under compression using digital volumetric speckle photography and X-ray computed tomography

It is always desirable to know the interior deformation pattern when a rock is subjected to mechanicalload. Few experimental techniques exist that can represent full-field three-dimensional （3D） straindistribution inside a rock specimen. And yet it is crucial that this information is available for fully understandingthe failure mechanism of rocks or other geomaterials. In this study, by using the newlydeveloped digital volumetric speckle photography （DVSP） technique in conjunction with X-ray computedtomography （CT） and taking advantage of natural 3D speckles formed inside the rock due to materialimpurities and voids, we can probe the interior of a rock to map its deformation pattern under load andshed light on its failure mechanism. We apply this technique to the analysis of a red sandstone specimenunder increasing uniaxial compressive load applied incrementally. The full-field 3D displacement fieldsare obtained in the specimen as a function of the load, from which both the volumetric and the deviatoricstrain fields are calculated. Strain localization zones which lead to the eventual failure of the rock areidentified. The results indicate that both shear and tension are contributing factors to the failuremechanism. 2015 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Production and hosting byElsevier B.V. All rights reserved.

ValueofDigitalX—RayPhotographyinDiagnosisofCongenitalHeartDisease

目的探讨数字化X线摄影在先天性心脏病诊断中的应用价值。方法收集我院2009-01-01—10-31经数字化X线摄影检查阳性并经临床随访或手术证实的先天性心脏病患者97例,对其临床及影像学资料进行回顾性分析。结果 97例患者中,房间隔缺损46例（47.4%）,动脉导管未闭17例（17.5%）,室间隔缺损13例（13.4%）,法洛四联症5例（5.2%）,肺动脉瓣狭窄3例（3.1%）,镜面右位心4例（4.1%）,右位主动脉弓7例（7.2%）,其他复杂畸形2例（2.1%）。X线表现为：肺血增多、肺血减少及心影形态失常。结论数字化X线摄影准备简单、安全、快捷,禁忌证少,整体感强,同时还是术后随访的重要检查手段,目前仍然能够为先天性心脏病的诊断提供独特和有价值的信息。

A Model for Estimating Total Forest Coverage with Ground-Based Digital Photography

Vegetation fractional coverage (VFC) is one of the key indicators of vegetation distribution. In the work a measurement-based model was developed to derive total forest VFC (TG) as well as the VFC of trees (T) and shrub-grasses (G) separately in a subtropical forest area in Nanjing, China. Both upward and downward photographs were taken with a digital camera in 72 quadrats (10 m × 10 m each). Fifteen models were established and validated. Models jointly using both T and G performed better than those using the T and G separately. The best model, TG = T + G- 1.134 × T × G- 0.025 (R2 = 0.9115, P < 0.01, root mean squared error = 0.0789), is recommended for application. This model provides a good way to obtain total forest VFC values through taking tree and shrub-grass photos on ground below tree canopy rather than above tree canopy.

Study on Gardening Photography

Through analyzing the concept,development history and works of gardening photography,unique status and charm of gardening photography in the field of photography art was explored.It was proposed that professional knowledge about gardening disciplines should be grasped,and the shoot targets shouid be fully investigated to present excellent works of gardening photography.In addition,photographers should have strong artistic sense,and be able to grasp the means of expressing image language,so that they will produce works with outstanding themes,proper light,concise composition,harmonious hue color and shadow tone.Sophisticated equipment and post processing skills are also needed.

Analysis of droplet transfer of pulsed MIG welding based on electrical signal and high-speed photography

In order to study how welding parameters affect welding quality and droplet transfer, a synchronous acquisition and analysis system is established to acquire and analyze electrical signal and instantaneous images of droplet transfer simultaneously, which is based on a self-developed soft-switching inverter. On the one hand, welding current and voltage signals are acquired and analyzed by a self-developed dynamic wavelet analyzer. On the other hand, images are filtered and optimized after they are captured by high-speed camera. The results show that instantaneous waveforms and statistical data of electrical signal contribute to make an overall assessment of welding quality, and that optimized high-speed images allow a visual and clear observation of droplet transfer process. The analysis of both waveforms and images leads to a further research on droplet transfer mechanism and provides a basis for precise control of droplet transfer.

Does bird photography affect nest predation and feeding frequency?

Bird photography is a popular and growing form of ecotourism that contributes to the economic growth of local communities,but its disturbance to bird reproduction remains understudied.We worked in a tropical forest of southern China,which has experienced a sharp increase in the number of photographers in recent years.We compared nests that were photographed and those that were not,in their nest predation and parental feeding rates.Including nests of 42 species,the results demonstrate that the predation rate of nests that were not photographed(incubation stage:43.3%of 194 nests;nestling stage:34.5%of 110 nests)was significantly higher than that of photographed ones(incubation:2.4%of 83 nests;nestling:11.1%of 81 nests).Among different nest types,open cup nests in shrub and trees were most affected by photography,in both incubation and nestling stages.Of five factors investigated,including three natural factors(nest stage,structure and position),and two anthropogenic factors(photography and distance to forest edge),only photographic disturbance and nest structure had significant effects(open nests had higher predation).The feeding frequency at nests when photographers were present was not strongly different from when they were not present.Human activity therefore had no negative effects on the birds,but showed a positive effect on their nesting success,in terms of reducing nest predation rates.However,there needs to be further assessment of other aspects of nesting(e.g.,clutch size,duration of nestlings in nests),and other kinds of stress responses(e.g.,hormonal changes),before the total effect of bird photography can be understood.