Classification of congenital cataracts based on multidimensional phenotypes and its association with visual outcomes

●AIM:To establish a classification for congenital cataracts that can facilitate individualized treatment and help identify individuals with a high likelihood of different visual outcomes.●METHODS:Consecutive patients diagnosed with congenital cataracts and undergoing surgery between January 2005 and November 2021 were recruited.Data on visual outcomes and the phenotypic characteristics of ocular biometry and the anterior and posterior segments were extracted from the patients’medical records.A hierarchical cluster analysis was performed.The main outcome measure was the identification of distinct clusters of eyes with congenital cataracts.●RESULTS:A total of 164 children(299 eyes)were divided into two clusters based on their ocular features.Cluster 1(96 eyes)had a shorter axial length(mean±SD,19.44±1.68 mm),a low prevalence of macular abnormalities(1.04%),and no retinal abnormalities or posterior cataracts.Cluster 2(203 eyes)had a greater axial length(mean±SD,20.42±2.10 mm)and a higher prevalence of macular abnormalities(8.37%),retinal abnormalities(98.52%),and posterior cataracts(4.93%).Compared with the eyes in Cluster 2(57.14%),those in Cluster 1(71.88%)had a 2.2 times higher chance of good best-corrected visual acuity[<0.7 logMAR;OR(95%CI),2.20(1.25–3.81);P=0.006].●CONCLUSION:This retrospective study categorizes congenital cataracts into two distinct clusters,each associated with a different likelihood of visual outcomes.This innovative classification may enable the personalization and prioritization of early interventions for patients who may gain the greatest benefit,thereby making strides toward precision medicine in the field of congenital cataracts.

Fine-Grained Classification of Remote Sensing Ship Images Based on Improved VAN

The remote sensing ships’fine-grained classification technology makes it possible to identify certain ship types in remote sensing images,and it has broad application prospects in civil and military fields.However,the current model does not examine the properties of ship targets in remote sensing images with mixed multi-granularity features and a complicated backdrop.There is still an opportunity for future enhancement of the classification impact.To solve the challenges brought by the above characteristics,this paper proposes a Metaformer and Residual fusion network based on Visual Attention Network(VAN-MR)for fine-grained classification tasks.For the complex background of remote sensing images,the VAN-MR model adopts the parallel structure of large kernel attention and spatial attention to enhance the model’s feature extraction ability of interest targets and improve the classification performance of remote sensing ship targets.For the problem of multi-grained feature mixing in remote sensing images,the VAN-MR model uses a Metaformer structure and a parallel network of residual modules to extract ship features.The parallel network has different depths,considering both high-level and lowlevel semantic information.The model achieves better classification performance in remote sensing ship images with multi-granularity mixing.Finally,the model achieves 88.73%and 94.56%accuracy on the public fine-grained ship collection-23(FGSC-23)and FGSCR-42 datasets,respectively,while the parameter size is only 53.47 M,the floating point operations is 9.9 G.The experimental results show that the classification effect of VAN-MR is superior to that of traditional CNNs model and visual model with Transformer structure under the same parameter quantity.

VMCTE:Visualization-BasedMalware Classification Using Transfer and Ensemble Learning

The Corona Virus Disease 2019(COVID-19)effect has made telecommuting and remote learning the norm.The growing number of Internet-connected devices provides cyber attackers with more attack vectors.The development of malware by criminals also incorporates a number of sophisticated obfuscation techniques,making it difficult to classify and detect malware using conventional approaches.Therefore,this paper proposes a novel visualization-based malware classification system using transfer and ensemble learning(VMCTE).VMCTE has a strong anti-interference ability.Even if malware uses obfuscation,fuzzing,encryption,and other techniques to evade detection,it can be accurately classified into its corresponding malware family.Unlike traditional dynamic and static analysis techniques,VMCTE does not require either reverse engineering or the aid of domain expert knowledge.The proposed classification system combines three strong deep convolutional neural networks(ResNet50,MobilenetV1,and MobilenetV2)as feature extractors,lessens the dimension of the extracted features using principal component analysis,and employs a support vector machine to establish the classification model.The semantic representations of malware images can be extracted using various convolutional neural network(CNN)architectures,obtaining higher-quality features than traditional methods.Integrating fine-tuned and non-fine-tuned classification models based on transfer learning can greatly enhance the capacity to classify various families ofmalware.The experimental findings on the Malimg dataset demonstrate that VMCTE can attain 99.64%,99.64%,99.66%,and 99.64%accuracy,F1-score,precision,and recall,respectively.

Discussion on classification and naming scheme of fine-grained sedimentary rocks

Based on reviews and summaries of the naming schemes of fine-grained sedimentary rocks, and analysis of characteristics of fine-grained sedimentary rocks, the problems existing in the classification and naming of fine-grained sedimentary rocks are discussed. On this basis, following the principle of three-level nomenclature, a new scheme of rock classification and naming for fine-grained sedimentary rocks is determined from two perspectives: First, fine-grained sedimentary rocks are divided into 12 types in two major categories, mudstone and siltstone, according to particle size(sand, silt and mud). Second,fine-grained sedimentary rocks are divided into 18 types in four categories, carbonate rock, fine-grained felsic sedimentary rock,clay rock and mixed fine-grained sedimentary rock according to mineral composition(carbonate minerals, felsic detrital minerals and clay minerals as three end elements). Considering the importance of organic matter in unconventional oil and gas generation and evaluation, organic matter is taken as the fourth element in the scheme. Taking the organic matter contents of 0.5% and 2% as dividing points, fine grained sedimentary rocks are divided into three categories, organic-poor, organic-bearing,and organic-rich ones. The new scheme meets the requirement of unconventional oil and gas exploration and development today and solves the problem of conceptual confusion in fine-grained sedimentary rocks, providing a unified basic term system for the research of fine-grained sedimentology.

Multi-Branch Deepfake Detection Algorithm Based on Fine-Grained Features

With the rapid development of deepfake technology,the authenticity of various types of fake synthetic content is increasing rapidly,which brings potential security threats to people’s daily life and social stability.Currently,most algorithms define deepfake detection as a binary classification problem,i.e.,global features are first extracted using a backbone network and then fed into a binary classifier to discriminate true or false.However,the differences between real and fake samples are often subtle and local,and such global feature-based detection algorithms are not optimal in efficiency and accuracy.To this end,to enhance the extraction of forgery details in deep forgery samples,we propose a multi-branch deepfake detection algorithm based on fine-grained features from the perspective of fine-grained classification.First,to address the critical problem in locating discriminative feature regions in fine-grained classification tasks,we investigate a method for locating multiple different discriminative regions and design a lightweight feature localization module to obtain crucial feature representations by augmenting the most significant parts of the feature map.Second,using information complementation,we introduce a correlation-guided fusion module to enhance the discriminative feature information of different branches.Finally,we use the global attention module in the multi-branch model to improve the cross-dimensional interaction of spatial domain and channel domain information and increase the weights of crucial feature regions and feature channels.We conduct sufficient ablation experiments and comparative experiments.The experimental results show that the algorithm outperforms the detection accuracy and effectiveness on the FaceForensics++and Celeb-DF-v2 datasets compared with the representative detection algorithms in recent years,which can achieve better detection results.

Improving Targeted Multimodal Sentiment Classification with Semantic Description of Images

Targeted multimodal sentiment classification(TMSC)aims to identify the sentiment polarity of a target mentioned in a multimodal post.The majority of current studies on this task focus on mapping the image and the text to a high-dimensional space in order to obtain and fuse implicit representations,ignoring the rich semantic information contained in the images and not taking into account the contribution of the visual modality in the multimodal fusion representation,which can potentially influence the results of TMSC tasks.This paper proposes a general model for Improving Targeted Multimodal Sentiment Classification with Semantic Description of Images(ITMSC)as a way to tackle these issues and improve the accu-racy of multimodal sentiment analysis.Specifically,the ITMSC model can automatically adjust the contribution of images in the fusion representation through the exploitation of semantic descriptions of images and text similarity relations.Further,we propose a target-based attention module to capture the target-text relevance,an image-based attention module to capture the image-text relevance,and a target-image matching module based on the former two modules to properly align the target with the image so that fine-grained semantic information can be extracted.Our experimental results demonstrate that our model achieves comparable performance with several state-of-the-art approaches on two multimodal sentiment datasets.Our findings indicate that incorporating semantic descriptions of images can enhance our understanding of multimodal content and lead to improved sentiment analysis performance.

A New Classification for Retinitis Pigmentosa Including Multifocal Electroretinography to Evaluate the Disease Severity

Aim: To establish a useful and objective classification for retinitis pigmentosa (RP) to evaluate the disease severity. Methods: This is a retrospective cross-sectional study. Visual acuity (VA), visual field (VF) width, ellipsoid zone width on optic cohorence tomography (OCT) and multifocal electroretinography (mf ERG) values were obtained from medical records of patients with RP. A scoring criterion was developed wherein each variable was assigned a score from 0 to 5 depending on its distribution. The cumulative score (from 0 to 20) was used to classify disease severity from grade 0 to 5. The scores were correlated with each other and the final grade. Results: Data of 152 eyes of 92 patients who had the results of all tests were reviewed. The mean age was 41.2 years. The mean VA of the patients was 0.13 ± 0.16 Snellen lines. The majority of patients had a VA less than 20/40 (88.6%), a visual field smaller than 20˚ (78%), and an ellipsoid zone width smaller than 7˚ (84.4%). The majority of the patients (85.4%) were in advanced stage of the disease (Grade 4 and 5). Conclusions: We present a simple, objective and easy to use disease severity classification for RP which can be used to categorize patients and to evaluate and compare treatment results.

Natural Scene Classification Inspired by Visual Perception and Cognition Mechanisms

The process of human natural scene categorization consists of two correlated stages: visual perception and visual cognition of natural scenes.Inspired by this fact,we propose a biologically plausible approach for natural scene image classification.This approach consists of one visual perception model and two visual cognition models.The visual perception model,composed of two steps,is used to extract discriminative features from natural scene images.In the first step,we mimic the oriented and bandpass properties of human primary visual cortex by a special complex wavelets transform,which can decompose a natural scene image into a series of 2D spatial structure signals.In the second step,a hybrid statistical feature extraction method is used to generate gist features from those 2D spatial structure signals.Then we design a cognitive feedback model to realize adaptive optimization for the visual perception model.At last,we build a multiple semantics based cognition model to imitate human cognitive mode in rapid natural scene categorization.Experiments on natural scene datasets show that the proposed method achieves high efficiency and accuracy for natural scene classification.

Ransomware Classification Framework Using the Behavioral Performance Visualization of Execution Objects

A ransomware attack that interrupted the operation of Colonial Pipeline(a large U.S.oil pipeline company),showed that security threats by malware have become serious enough to affect industries and social infrastructure rather than individuals alone.The agents and characteristics of attacks should be identified,and appropriate strategies should be established accordingly in order to respond to such attacks.For this purpose,the first task that must be performed is malware classification.Malware creators are well aware of this and apply various concealment and avoidance techniques,making it difficult to classify malware.This study focuses on new features and classification techniques to overcome these difficulties.We propose a behavioral performance visualization method using utilization patterns of system resources,such as the central processing unit,memory,and input/output,that are commonly used in performance analysis or tuning of programs.We extracted the usage patterns of the system resources for ransomware to performbehavioral performance visualization.The results of the classification performance evaluation using the visualization results indicate an accuracy of at least 98.94%with a 3.69%loss rate.Furthermore,we designed and implemented a framework to perform the entire process—from data extraction to behavioral performance visualization and classification performance measurement—that is expected to contribute to related studies in the future.

Visual learning graph convolution for multi-grained orange quality grading

The quality of oranges is grounded on their appearance and diameter.Appearance refers to the skin’s smoothness and surface cleanliness;diameter refers to the transverse diameter size.They are visual attributes that visual perception technologies can automatically identify.Nonetheless,the current orange quality assessment needs to address two issues:1)There are no image datasets for orange quality grading;2)It is challenging to effectively learn the fine-grained and distinct visual semantics of oranges from diverse angles.This study collected 12522 images from 2087 oranges for multi-grained grading tasks.In addition,it presented a visual learning graph convolution approach for multi-grained orange quality grading,including a backbone network and a graph convolutional network(GCN).The backbone network’s object detection,data augmentation,and feature extraction can remove extraneous visual information.GCN was utilized to learn the topological semantics of orange feature maps.Finally,evaluation results proved that the recognition accuracy of diameter size,appearance,and fine-grained orange quality were 99.50,97.27,and 97.99%,respectively,indicating that the proposed approach is superior to others.

A New Childhood Pneumonia Diagnosis Method Based on Fine-Grained Convolutional Neural Network

Pneumonia is part of the main diseases causing the death of children.It is generally diagnosed through chest Xray images.With the development of Deep Learning(DL),the diagnosis of pneumonia based on DL has received extensive attention.However,due to the small difference between pneumonia and normal images,the performance of DL methods could be improved.This research proposes a new fine-grained Convolutional Neural Network(CNN)for children’s pneumonia diagnosis(FG-CPD).Firstly,the fine-grainedCNNclassificationwhich can handle the slight difference in images is investigated.To obtain the raw images from the real-world chest X-ray data,the YOLOv4 algorithm is trained to detect and position the chest part in the raw images.Secondly,a novel attention network is proposed,named SGNet,which integrates the spatial information and channel information of the images to locate the discriminative parts in the chest image for expanding the difference between pneumonia and normal images.Thirdly,the automatic data augmentation method is adopted to increase the diversity of the images and avoid the overfitting of FG-CPD.The FG-CPD has been tested on the public Chest X-ray 2017 dataset,and the results show that it has achieved great effect.Then,the FG-CPD is tested on the real chest X-ray images from children aged 3–12 years ago from Tongji Hospital.The results show that FG-CPD has achieved up to 96.91%accuracy,which can validate the potential of the FG-CPD.

Image Classification Based on Histogram Intersection Kernel

Histogram Intersection Kernel Support Vector Machines (SVM) was used for the image classification problem. Specifically, each image was split into blocks, and each block was represented by the Scale Invariant Feature Transform (SIFT) descriptors;secondly, k-means cluster method was applied to separate the SIFT descriptors into groups, each group represented a visual keywords;thirdly, count the number of the SIFT descriptors in each image, and histogram of each image should be constructed;finally, Histogram Intersection Kernel should be built based on these histograms. In our experimental study, we use Corel-low images to test our method. Compared with typical RBF kernel SVM, the Histogram Intersection kernel SVM performs better than RBF kernel SVM.

Does Stem Cell Implantation Have an Effect on Severity of Retinitis Pigmentosa: Evaluation with a Classification System?

Background: Cell replacement therapies have been evaluated in recent years as an alternative for various retinal pathologies to evaluate the therapeutic efficacy of cell therapy, it is important to measure the severity of the disease. The aim of this study was to evaluate the effect of umbilical cord derived Mesenchymal Stem Cell (UC-MSC) implantation on severity of Retinitis Pigmentosa (RP). Methods: This single-center, clinical study included data of 138 eyes of 92 patients who had a confirmed diagnosis of RP and received stem cell implantation to the suprachoroidal area with a surgical procedure. Patients were evaluated before and 1 year after the surgery regarding to the outcome measures of Best Corrected Visual Acuity (BCVA), Optical Coherence Tomography (OCT) and Visual Field (VF) tests. BCVA, VF width and ellipsoid zone (EZ) width on OCT were recorded for each patient and a scoring criterion was established for each variable varying from 0 to 5 depending on its distribution. The cumulative score (from 0 to 15) was used to classify disease severity from grade 0 to 5. Results: All of the patients completed 12-month follow-up period. The median age of the patients was 40.8 years, 46% were female, 77% had been diagnosed within 10 years and 41% had a family history. 79% of the patients with family history had autosomal recessive inheritance pattern. There were statistically significant improvements in the mean BCVA and VF scores during the study (p < 0.05). The mean score and the mean grade of the disease also improved after the treatment (p < 0.05). There was a negative correlation between BCVA improvement and scoring and grading of the disease. Conclusions: This study demonstrated beneficial effect of suprachoroidally applied UC-MSCs on BCVA, VF and the severity score and grade of the disease during 12-month follow-up period. Cell mediated therapy based on the secretion of Growth Factors (GFs) seems to be an effective and safe option for the treatment of degenerative retinal diseases. This classification is simple, produces objective measure of disease severity and gives opportunity to compare the results of different treatment modalities.

Deep Stacked Ensemble Learning Model for COVID-19 Classification

COVID-19 is a growing problem worldwide with a high mortality rate.As a result,the World Health Organization(WHO)declared it a pandemic.In order to limit the spread of the disease,a fast and accurate diagnosis is required.A reverse transcript polymerase chain reaction(RT-PCR)test is often used to detect the disease.However,since this test is time-consuming,a chest computed tomography(CT)or plain chest X-ray(CXR)is sometimes indicated.The value of automated diagnosis is that it saves time and money by minimizing human effort.Three significant contributions are made by our research.Its initial purpose is to use the essential finetuning methodology to test the action and efficiency of a variety of vision models,ranging from Inception to Neural Architecture Search(NAS)networks.Second,by plotting class activationmaps(CAMs)for individual networks and assessing classification efficiency with AUC-ROC curves,the behavior of these models is visually analyzed.Finally,stacked ensembles techniques were used to provide greater generalization by combining finetuned models with six ensemble neural networks.Using stacked ensembles,the generalization of the models improved.Furthermore,the ensemble model created by combining all of the finetuned networks obtained a state-of-the-art COVID-19 accuracy detection score of 99.17%.The precision and recall rates were 99.99%and 89.79%,respectively,highlighting the robustness of stacked ensembles.The proposed ensemble approach performed well in the classification of the COVID-19 lesions on CXR according to the experimental results.

基于Depth-wise卷积和视觉Transformer的图像分类模型

图像分类作为一种常见的视觉识别任务,有着广阔的应用场景。在处理图像分类问题时,传统的方法通常使用卷积神经网络,然而,卷积网络的感受野有限,难以建模图像的全局关系表示,导致分类精度低,难以处理复杂多样的图像数据。为了对全局关系进行建模,一些研究者将Transformer应用于图像分类任务,但为了满足Transformer的序列化和并行化要求,需要将图像分割成大小相等、互不重叠的图像块,破坏了相邻图像数据块之间的局部信息。此外,由于Transformer具有较少的先验知识,模型往往需要在大规模数据集上进行预训练,因此计算复杂度较高。为了同时建模图像相邻块之间的局部信息并充分利用图像的全局信息,提出了一种基于Depth-wise卷积的视觉Transformer(Efficient Pyramid Vision Transformer,EPVT)模型。EPVT模型可以实现以较低的计算成本提取相邻图像块之间的局部和全局信息。EPVT模型主要包含3个关键组件:局部感知模块(Local Perceptron Module,LPM)、空间信息融合模块(Spatial Information Fusion,SIF)和“+卷积前馈神经网络(Convolution Feed-forward Network,CFFN)。LPM模块用于捕获图像的局部相关性;SIF模块用于融合相邻图像块之间的局部信息,并利用不同图像块之间的远距离依赖关系,提升模型的特征表达能力,使模型学习到输出特征在不同维度下的语义信息;CFFN模块用于编码位置信息和重塑张量。在图像分类数据集ImageNet-1K上,所提模型优于现有的同等规模的视觉Transformer分类模型,取得了82.6%的分类准确度,证明了该模型在大规模数据集上具有竞争力。

面向工业缺陷分类的交互式易混淆缺陷分离方法研究

在工业生产中会根据严重程度对缺陷做不同处理,所以需要对缺陷进行分类。但是,实际生产中经常因为存在一些易混淆缺陷而导致分类精度不够,使得在生产实践中只能对所有缺陷进行保守处理,带来很大人力成本和经济代价。为解决该问题,提出一种交互式易混淆缺陷分离方法,将少量易混淆缺陷从其他缺陷中分离出来,从而保证剩下的绝大部分缺陷的分类结果能被直接使用。首先,将训练数据中的易混淆缺陷挑选出来作为一个或多个新缺陷类别,称之为虚缺陷,从而使得训练所得网络能区分虚缺陷和其它类缺陷。其中,还设计了一套可视化界面辅助用户交互地挑选易混淆缺陷以构建虚类别。使用实际工业现场的CMOS缺陷数据进行有效性验证,结果表明所提方法能快速分类出易混淆缺陷,并保证剩余缺陷的分类精度满足工业应用要求。

基于图像处理的视觉采摘机器人作业控制研究

为了实现自动化的番茄分类采摘,基于视觉识别技术设计了识别系统。首先,基于HSV视觉体系中的H分量,采用聚类分析的方法,依据成熟度将番茄分为不熟,半熟和全熟3类,并计算3类番茄成熟度对应的H分量分布范围;其次,根据半熟和全熟番茄H分量的分布范围进行番茄图像分割,并利用形态学的方法得到图像中番茄区域的轮廓曲线;再次,采用椭圆拟合方法实现对番茄轮廓拟合,计算得到图像中番茄区域的中心坐标;最后,采用双目视觉系统实现图像中番茄区域中心坐标向实际空间坐标转化。对番茄轮廓曲线拟合精度和视觉定位精度进行测试,表明系统具有良好的可靠性。

基于知识图谱的国内女性体型分类领域前沿研究

为揭示国内女性体型分类领域的研究现状、热点及未来的发展方向,基于Citespace软件,通过绘制知识图谱对2003—2023年CNKI知网数据库筛选的198篇文献进行分析,得出国内在女性体型分类的发展趋势。研究表明:当前女性体型分类研究的热点主要集中在体型数据获取与处理、体型分类算法以及数字化技术应用等方面。随着人工智能、数字化技术的迅猛发展,未来的研究趋势和方向应侧重于对分类方法的深入探索,借助先进的科学测量手段、机器学习技术以及创新的分类方法,实现对不同年龄段女性体型特征的更精准分类。这一方向的深入研究有望为女性体型领域的科学发展提供更为创新和前瞻性的贡献。

面向目视解译的全极化SAR船只精细化特征表征方法

随着卫星技术的发展,极化合成孔径雷达(PolSAR)数据的分辨率和数据质量得到大幅提升,为人造目标的精细化目视解译提供了良好的数据条件。目前主要采用多分量分解的方法,但是易造成像素错分问题,为此,该文结合Yamaguchi极化分解和极化熵提出了一种非固定阈值划分的方法用于实现全极化SAR图像船只结构精细化特征表征。Yamaguchi极化分解能够识别基本散射机制,其修正后的体散射模型更符合实测数据,可有效对人造目标进行表征。极化熵H在弱去极化状态下可以看成某一指定等效点的目标散射机制,能够有效突出船只主散射特征。因此,该文通过将Yamaguchi极化分解算法的非固定三分量与极化熵的低中高熵内嵌,将其分为非固定阈值的九分类成分,从而降低硬阈值处理在阈值边界处受噪声影响产生的类别随机性。并且将二次散射和单次散射均显著的区域称为混合散射(MSM),以更好匹配实验中船只典型结构的散射类型。在此基础上,利用广义相似性参数进一步缩短类内距离,采用改进后的GSP-Wishart分类器进行迭代聚类,旨在通过提高二次散射和混合散射机制以提高不同类型船只可区分度。最后,该文采用中国上海某港口的高分三号全极化SAR数据进行实验,为了验证每艘船只特征表征正确性,通过船舶自动识别系统(AIS)收集并筛选了该港口船只信息及光学数据,并与极化SAR数据中每艘船只进行匹配。实验结果表明该方法可有效区分散货船、集装箱船和油轮3种类型船只。

基于GHM可视化和深度学习的恶意代码检测与分类

恶意代码的复杂性和变异性在不断增加,致使恶意软件的检测变得越来越具有挑战性.大多数变异或未知的恶意程序是在现有恶意代码的逻辑基础上进行改进或混淆形成的,因此发现恶意代码家族并确定其恶意行为变得越来越重要.提出了一种基于GHM(Gray, HOG,Markov)的新型恶意软件可视化方法进行数据预处理.与传统的可视化方法不同,该方法在可视化过程中通过HOG和马尔科夫提取出更加有效的数据特征,并构建了3通道彩色图像.此外,构建了基于CNN和LSTM的VLMal分类模型,对可视化图像进行恶意软件检测分类.实验结果表明,该方法可以有效地检测和分类恶意代码,具有较好的准确性和稳定性.