The current method for inspecting microholes in printed circuit boards(PCBs)involves preparing slices followed by optical microscope measurements.However,this approach suffers from low detection efficiency,poor reliab...The current method for inspecting microholes in printed circuit boards(PCBs)involves preparing slices followed by optical microscope measurements.However,this approach suffers from low detection efficiency,poor reliability,and insufficient measurement stability.Micro-CT enables the observation of the internal structures of the sample without the need for slicing,thereby presenting a promising new method for assessing the quality of microholes in PCBs.This study integrates computer vision technology with computed tomography(CT)to propose a method for detecting microhole wall roughness using a U-Net model and image processing algorithms.This study established an unplated copper PCB CT image dataset and trained an improved U-Net model.Validation of the test set demonstrated that the improved model effectively segmented microholes in the PCB CT images.Subsequently,the roughness of the holes’walls was assessed using a customized image-processing algorithm.Comparative analysis between CT detection based on various edge detection algorithms and slice detection revealed that CT detection employing the Canny algorithm closely approximates slice detection,yielding range and average errors of 2.92 and 1.64μm,respectively.Hence,the detection method proposed in this paper offers a novel approach for nondestructive testing of hole wall roughness in the PCB industry.展开更多
With the intensification of global warming,marine heatwaves(MHWs)have emerged as a significant extreme hazard,garnering widespread attention and creating a pressing need for accurate prediction.The development of arti...With the intensification of global warming,marine heatwaves(MHWs)have emerged as a significant extreme hazard,garnering widespread attention and creating a pressing need for accurate prediction.The development of artificial intelligence,particularly the application of deep learning to sea surface temperature(SST),has significantly improved the feasibility of predictions.This study utilizes SST and Outgoing Longwave Radiation(OLR)data to train a 3D U-Net model for predicting MHWs in the South China Sea(SCS)with lead times ranging from 1 to 7 days,based on the characteristics of intraseasonal weather processes.Analysis of MHWs occurrences from 1982 to 2023 reveals distinct seasonal patterns,with summer MHWs primarily concentrated in the northern and central SCS,and the highest temperature centers located in the Gulf of Tonkin and west of the Philippines.The 2023 MHW forecast results demonstrate that the 3D U-Net model achieves low error rates and high correlation coefficients with observational data.Incorporating OLR data enhances forecast accuracy compared to SST-only inputs,and training the model exclusively with summer data further improves prediction accuracy.These findings indicate that the proposed method can significantly enhance the accuracy of MHW forecasts.展开更多
El Niño-Southern Oscillation(ENSO)is the strongest interannual climate mode influencing the coupled ocean-atmosphere system in the tropical Pacific,and numerous dynamical and statistical models have been develope...El Niño-Southern Oscillation(ENSO)is the strongest interannual climate mode influencing the coupled ocean-atmosphere system in the tropical Pacific,and numerous dynamical and statistical models have been developed to simulate and predict it.In some simplified coupled ocean-atmosphere models,the relationship between sea surface temperature(SST)anomalies and wind stress(τ)anomalies can be constructed by statistical methods,such as singular value decomposition(SVD).In recent years,the applications of artificial intelligence(AI)to climate modeling have shown promising prospects,and the integrations of AI-based models with dynamical models are active areas of research.This study constructs U-Net models for representing the relationship between SSTAs andτanomalies in the tropical Pacific;the UNet-derivedτmodel,denoted asτUNet,is then used to replace the original SVD-basedτmodel of an intermediate coupled model(ICM),forming a newly AI-integrated ICM,referred to as ICM-UNet.The simulation results obtained from ICM-UNet demonstrate their ability to represent the spatiotemporal variability of oceanic and atmospheric anomaly fields in the equatorial Pacific.In the ocean-only case study,theτUNet-derived wind stress anomaly fields are used to force the ocean component of the ICM,the results of which also indicate reasonable simulations of typical ENSO events.These results demonstrate the feasibility of integrating an AI-derived model with a physics-based dynamical model for ENSO modeling studies.Furthermore,the successful integration of the dynamical ocean models with the AI-based atmospheric wind model provides a novel approach to ocean-atmosphere interaction modeling studies.展开更多
Deep learning-based systems have succeeded in many computer vision tasks.However,it is found that the latest study indicates that these systems are in danger in the presence of adversarial attacks.These attacks can qu...Deep learning-based systems have succeeded in many computer vision tasks.However,it is found that the latest study indicates that these systems are in danger in the presence of adversarial attacks.These attacks can quickly spoil deep learning models,e.g.,different convolutional neural networks(CNNs),used in various computer vision tasks from image classification to object detection.The adversarial examples are carefully designed by injecting a slight perturbation into the clean images.The proposed CRU-Net defense model is inspired by state-of-the-art defense mechanisms such as MagNet defense,Generative Adversarial Net-work Defense,Deep Regret Analytic Generative Adversarial Networks Defense,Deep Denoising Sparse Autoencoder Defense,and Condtional Generattive Adversarial Network Defense.We have experimentally proved that our approach is better than previous defensive techniques.Our proposed CRU-Net model maps the adversarial image examples into clean images by eliminating the adversarial perturbation.The proposed defensive approach is based on residual and U-Net learning.Many experiments are done on the datasets MNIST and CIFAR10 to prove that our proposed CRU-Net defense model prevents adversarial example attacks in WhiteBox and BlackBox settings and improves the robustness of the deep learning algorithms especially in the computer visionfield.We have also reported similarity(SSIM and PSNR)between the original and restored clean image examples by the proposed CRU-Net defense model.展开更多
Brain tumor segmentation from Magnetic Resonance Imaging(MRI)supports neurologists and radiologists in analyzing tumors and developing personalized treatment plans,making it a crucial yet challenging task.Supervised m...Brain tumor segmentation from Magnetic Resonance Imaging(MRI)supports neurologists and radiologists in analyzing tumors and developing personalized treatment plans,making it a crucial yet challenging task.Supervised models such as 3D U-Net perform well in this domain,but their accuracy significantly improves with appropriate preprocessing.This paper demonstrates the effectiveness of preprocessing in brain tumor segmentation by applying a pre-segmentation step based on the Generalized Gaussian Mixture Model(GGMM)to T1 contrastenhanced MRI scans from the BraTS 2020 dataset.The Expectation-Maximization(EM)algorithm is employed to estimate parameters for four tissue classes,generating a new pre-segmented channel that enhances the training and performance of the 3DU-Net model.The proposed GGMM+3D U-Net framework achieved a Dice coefficient of 0.88 for whole tumor segmentation,outperforming both the standard multiscale 3D U-Net(0.84)and MMU-Net(0.85).It also delivered higher Intersection over Union(IoU)scores compared to models trained without preprocessing or with simpler GMM-based segmentation.These results,supported by qualitative visualizations,suggest that GGMM-based preprocessing should be integrated into brain tumor segmentation pipelines to optimize performance.展开更多
Lower back pain is one of the most common medical problems in the world and it is experienced by a huge percentage of people everywhere.Due to its ability to produce a detailed view of the soft tissues,including the s...Lower back pain is one of the most common medical problems in the world and it is experienced by a huge percentage of people everywhere.Due to its ability to produce a detailed view of the soft tissues,including the spinal cord,nerves,intervertebral discs,and vertebrae,Magnetic Resonance Imaging is thought to be the most effective method for imaging the spine.The semantic segmentation of vertebrae plays a major role in the diagnostic process of lumbar diseases.It is difficult to semantically partition the vertebrae in Magnetic Resonance Images from the surrounding variety of tissues,including muscles,ligaments,and intervertebral discs.U-Net is a powerful deep-learning architecture to handle the challenges of medical image analysis tasks and achieves high segmentation accuracy.This work proposes a modified U-Net architecture namely MU-Net,consisting of the Meijering convolutional layer that incorporates the Meijering filter to perform the semantic segmentation of lumbar vertebrae L1 to L5 and sacral vertebra S1.Pseudo-colour mask images were generated and used as ground truth for training the model.The work has been carried out on 1312 images expanded from T1-weighted mid-sagittal MRI images of 515 patients in the Lumbar Spine MRI Dataset publicly available from Mendeley Data.The proposed MU-Net model for the semantic segmentation of the lumbar vertebrae gives better performance with 98.79%of pixel accuracy(PA),98.66%of dice similarity coefficient(DSC),97.36%of Jaccard coefficient,and 92.55%mean Intersection over Union(mean IoU)metrics using the mentioned dataset.展开更多
由于患者个体差异、采集协议多样性和数据损坏等因素,现有基于磁共振成像(Magnetic resonance imaging,MRI)的脑肿瘤分割方法存在模态数据丢失问题,导致分割精度不高。为此,本文提出了一种基于U-Net和Transformer结合的不完整多模态脑...由于患者个体差异、采集协议多样性和数据损坏等因素,现有基于磁共振成像(Magnetic resonance imaging,MRI)的脑肿瘤分割方法存在模态数据丢失问题,导致分割精度不高。为此,本文提出了一种基于U-Net和Transformer结合的不完整多模态脑肿瘤分割(Incomplete multimodal brain tumor segmentation based on the combination of U-Net and Transformer,IM TransNet)方法。首先,针对脑肿瘤MRI的4个不同模态设计了单模态特定编码器,提升模型对各模态数据的表征能力。其次,在U-Net中嵌入双重注意力的Transformer模块,克服模态缺失引起的信息不完整问题,减少U-Net的长距离上下文交互和空间依赖性局限。在U-Net的跳跃连接中加入跳跃交叉注意力机制,动态关注不同层级和模态的特征,即使在模态缺失时,也能有效融合特征并进行重建。此外,针对模态缺失引起的训练不平衡问题,设计了辅助解码模块,确保模型在各种不完整模态子集上均能稳定高效地分割脑肿瘤。最后,基于公开数据集BRATS验证模型的性能。实验结果表明,本文提出的模型在增强型肿瘤、肿瘤核心和全肿瘤上的平均Dice评分分别为63.19%、76.42%和86.16%,证明了其在处理不完整多模态数据时的优越性和稳定性,为临床实践中脑肿瘤的准确、高效和可靠分割提供了一种可行的技术手段。展开更多
基金Supported by National Natural Science Foundation of China(Grant Nos.52122510 and 52375415).
文摘The current method for inspecting microholes in printed circuit boards(PCBs)involves preparing slices followed by optical microscope measurements.However,this approach suffers from low detection efficiency,poor reliability,and insufficient measurement stability.Micro-CT enables the observation of the internal structures of the sample without the need for slicing,thereby presenting a promising new method for assessing the quality of microholes in PCBs.This study integrates computer vision technology with computed tomography(CT)to propose a method for detecting microhole wall roughness using a U-Net model and image processing algorithms.This study established an unplated copper PCB CT image dataset and trained an improved U-Net model.Validation of the test set demonstrated that the improved model effectively segmented microholes in the PCB CT images.Subsequently,the roughness of the holes’walls was assessed using a customized image-processing algorithm.Comparative analysis between CT detection based on various edge detection algorithms and slice detection revealed that CT detection employing the Canny algorithm closely approximates slice detection,yielding range and average errors of 2.92 and 1.64μm,respectively.Hence,the detection method proposed in this paper offers a novel approach for nondestructive testing of hole wall roughness in the PCB industry.
基金Guangdong Major Project of Basic and Applied Basic Research(2020B0301030004)。
文摘With the intensification of global warming,marine heatwaves(MHWs)have emerged as a significant extreme hazard,garnering widespread attention and creating a pressing need for accurate prediction.The development of artificial intelligence,particularly the application of deep learning to sea surface temperature(SST),has significantly improved the feasibility of predictions.This study utilizes SST and Outgoing Longwave Radiation(OLR)data to train a 3D U-Net model for predicting MHWs in the South China Sea(SCS)with lead times ranging from 1 to 7 days,based on the characteristics of intraseasonal weather processes.Analysis of MHWs occurrences from 1982 to 2023 reveals distinct seasonal patterns,with summer MHWs primarily concentrated in the northern and central SCS,and the highest temperature centers located in the Gulf of Tonkin and west of the Philippines.The 2023 MHW forecast results demonstrate that the 3D U-Net model achieves low error rates and high correlation coefficients with observational data.Incorporating OLR data enhances forecast accuracy compared to SST-only inputs,and training the model exclusively with summer data further improves prediction accuracy.These findings indicate that the proposed method can significantly enhance the accuracy of MHW forecasts.
基金supported by the National Natural Science Foundation of China(NFSCGrant No.42030410)+2 种基金Laoshan Laboratory(No.LSKJ202202402)the Strategic Priority Research Program of the Chinese Academy of Sciences(Grant No.XDB40000000)the Startup Foundation for Introducing Talent of NUIST.
文摘El Niño-Southern Oscillation(ENSO)is the strongest interannual climate mode influencing the coupled ocean-atmosphere system in the tropical Pacific,and numerous dynamical and statistical models have been developed to simulate and predict it.In some simplified coupled ocean-atmosphere models,the relationship between sea surface temperature(SST)anomalies and wind stress(τ)anomalies can be constructed by statistical methods,such as singular value decomposition(SVD).In recent years,the applications of artificial intelligence(AI)to climate modeling have shown promising prospects,and the integrations of AI-based models with dynamical models are active areas of research.This study constructs U-Net models for representing the relationship between SSTAs andτanomalies in the tropical Pacific;the UNet-derivedτmodel,denoted asτUNet,is then used to replace the original SVD-basedτmodel of an intermediate coupled model(ICM),forming a newly AI-integrated ICM,referred to as ICM-UNet.The simulation results obtained from ICM-UNet demonstrate their ability to represent the spatiotemporal variability of oceanic and atmospheric anomaly fields in the equatorial Pacific.In the ocean-only case study,theτUNet-derived wind stress anomaly fields are used to force the ocean component of the ICM,the results of which also indicate reasonable simulations of typical ENSO events.These results demonstrate the feasibility of integrating an AI-derived model with a physics-based dynamical model for ENSO modeling studies.Furthermore,the successful integration of the dynamical ocean models with the AI-based atmospheric wind model provides a novel approach to ocean-atmosphere interaction modeling studies.
基金supported by the National Natural Science Foundation of China [grant number 42276008]the Laoshan Laboratory[grant number LSKJ202202403-2]+2 种基金supported by the National Natural Science Foundation of China [grant number 42030410]the Strategic Priority Research Program of the Chinese Academy of Sciences [grant number XDB40000000]the Startup Foundation for Introducing Talent of NUIST
文摘Deep learning-based systems have succeeded in many computer vision tasks.However,it is found that the latest study indicates that these systems are in danger in the presence of adversarial attacks.These attacks can quickly spoil deep learning models,e.g.,different convolutional neural networks(CNNs),used in various computer vision tasks from image classification to object detection.The adversarial examples are carefully designed by injecting a slight perturbation into the clean images.The proposed CRU-Net defense model is inspired by state-of-the-art defense mechanisms such as MagNet defense,Generative Adversarial Net-work Defense,Deep Regret Analytic Generative Adversarial Networks Defense,Deep Denoising Sparse Autoencoder Defense,and Condtional Generattive Adversarial Network Defense.We have experimentally proved that our approach is better than previous defensive techniques.Our proposed CRU-Net model maps the adversarial image examples into clean images by eliminating the adversarial perturbation.The proposed defensive approach is based on residual and U-Net learning.Many experiments are done on the datasets MNIST and CIFAR10 to prove that our proposed CRU-Net defense model prevents adversarial example attacks in WhiteBox and BlackBox settings and improves the robustness of the deep learning algorithms especially in the computer visionfield.We have also reported similarity(SSIM and PSNR)between the original and restored clean image examples by the proposed CRU-Net defense model.
基金Princess Nourah Bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R826),Princess Nourah Bint Abdulrahman University,Riyadh,Saudi ArabiaNorthern Border University,Saudi Arabia,for supporting this work through project number(NBU-CRP-2025-2933).
文摘Brain tumor segmentation from Magnetic Resonance Imaging(MRI)supports neurologists and radiologists in analyzing tumors and developing personalized treatment plans,making it a crucial yet challenging task.Supervised models such as 3D U-Net perform well in this domain,but their accuracy significantly improves with appropriate preprocessing.This paper demonstrates the effectiveness of preprocessing in brain tumor segmentation by applying a pre-segmentation step based on the Generalized Gaussian Mixture Model(GGMM)to T1 contrastenhanced MRI scans from the BraTS 2020 dataset.The Expectation-Maximization(EM)algorithm is employed to estimate parameters for four tissue classes,generating a new pre-segmented channel that enhances the training and performance of the 3DU-Net model.The proposed GGMM+3D U-Net framework achieved a Dice coefficient of 0.88 for whole tumor segmentation,outperforming both the standard multiscale 3D U-Net(0.84)and MMU-Net(0.85).It also delivered higher Intersection over Union(IoU)scores compared to models trained without preprocessing or with simpler GMM-based segmentation.These results,supported by qualitative visualizations,suggest that GGMM-based preprocessing should be integrated into brain tumor segmentation pipelines to optimize performance.
文摘Lower back pain is one of the most common medical problems in the world and it is experienced by a huge percentage of people everywhere.Due to its ability to produce a detailed view of the soft tissues,including the spinal cord,nerves,intervertebral discs,and vertebrae,Magnetic Resonance Imaging is thought to be the most effective method for imaging the spine.The semantic segmentation of vertebrae plays a major role in the diagnostic process of lumbar diseases.It is difficult to semantically partition the vertebrae in Magnetic Resonance Images from the surrounding variety of tissues,including muscles,ligaments,and intervertebral discs.U-Net is a powerful deep-learning architecture to handle the challenges of medical image analysis tasks and achieves high segmentation accuracy.This work proposes a modified U-Net architecture namely MU-Net,consisting of the Meijering convolutional layer that incorporates the Meijering filter to perform the semantic segmentation of lumbar vertebrae L1 to L5 and sacral vertebra S1.Pseudo-colour mask images were generated and used as ground truth for training the model.The work has been carried out on 1312 images expanded from T1-weighted mid-sagittal MRI images of 515 patients in the Lumbar Spine MRI Dataset publicly available from Mendeley Data.The proposed MU-Net model for the semantic segmentation of the lumbar vertebrae gives better performance with 98.79%of pixel accuracy(PA),98.66%of dice similarity coefficient(DSC),97.36%of Jaccard coefficient,and 92.55%mean Intersection over Union(mean IoU)metrics using the mentioned dataset.
文摘由于患者个体差异、采集协议多样性和数据损坏等因素,现有基于磁共振成像(Magnetic resonance imaging,MRI)的脑肿瘤分割方法存在模态数据丢失问题,导致分割精度不高。为此,本文提出了一种基于U-Net和Transformer结合的不完整多模态脑肿瘤分割(Incomplete multimodal brain tumor segmentation based on the combination of U-Net and Transformer,IM TransNet)方法。首先,针对脑肿瘤MRI的4个不同模态设计了单模态特定编码器,提升模型对各模态数据的表征能力。其次,在U-Net中嵌入双重注意力的Transformer模块,克服模态缺失引起的信息不完整问题,减少U-Net的长距离上下文交互和空间依赖性局限。在U-Net的跳跃连接中加入跳跃交叉注意力机制,动态关注不同层级和模态的特征,即使在模态缺失时,也能有效融合特征并进行重建。此外,针对模态缺失引起的训练不平衡问题,设计了辅助解码模块,确保模型在各种不完整模态子集上均能稳定高效地分割脑肿瘤。最后,基于公开数据集BRATS验证模型的性能。实验结果表明,本文提出的模型在增强型肿瘤、肿瘤核心和全肿瘤上的平均Dice评分分别为63.19%、76.42%和86.16%,证明了其在处理不完整多模态数据时的优越性和稳定性,为临床实践中脑肿瘤的准确、高效和可靠分割提供了一种可行的技术手段。
