Search

Background: Alberta Stroke Program Early Computed Tomography Score (ASPECTS) is a standardized semi-quantitative method for early ischemic changes in acute ischemic stroke., Purpose: However, ASPECTS is still affected by expert experience and inconsistent results between readers in clinical. This study aims to propose an automatic ASPECTS scoring model based on diffusion-weighted imaging (DWI) mode to help clinicians make accurate treatment plans., Methods: Eighty-two patients with stroke were included in the study. First, we designed a new deep learning network for segmenting ASPECTS scoring brain regions. The network is improved based on U-net, which integrates multiple modules. Second, we proposed using hybrid classifiers to classify brain regions. For brain regions with larger areas, we used brain grayscale comparison algorithm to train machine learning classifiers, while using hybrid feature training for brain regions with smaller areas., Results: The average DICE coefficient of the segmented hindbrain area can reach 0.864. With the proposed hybrid classifier, our method performs significantly on both region-level ASPECTS and dichotomous ASPECTS. The sensitivity and accuracy on the test set are 95.51% and 93.43%, respectively. For dichotomous ASPECTS, the intraclass correlation coefficient (ICC) between our automated ASPECTS score and the expert reading was 0.87., Conclusions: This study proposed an automated model for ASPECTS scoring of patients with acute ischemic stroke based on DWI images. Experimental results show that the method of segmentation first and then classification is feasible. Our method has the potential to assist physicians in the Alberta Stroke Program with early CT scoring and clinical stroke diagnosis., (© 2024 American Association of Physicists in Medicine.)

Surface defect classification plays a very important role in industrial production and mechanical manufacturing. However, there are currently some challenges hindering its use. The first is the similarity of different defect samples makes classification a difficult task. Second, the lack of defect samples leads to poor accuracies when using deep learning methods. In this paper, we first design a novel backbone network, ResMSNet, which draws on the idea of multi-scale feature extraction for small discriminative regions in defect samples. Then, we introduce few-shot learning for defect classification and propose a Relation-Prototypical network (RPNet), which combines the characteristics of ProtoNet and RelationNet and provides classification by linking the prototypes distances and the nonlinear relation scores. Next, we consider a more realistic scenario where the base dataset for training the model and target defect dataset for applying the model are usually obtained from domains with large differences, called cross-domain few-shot learning. Hence, we further improve RPNet to KD-RPNet inspired by knowledge distillation methods. Through extensive comparative experiments and ablation experiments, we demonstrate that either our ResMSNet or RPNet proves its effectiveness and KD-RPNet outperforms other state-of-the-art approaches for few-shot defect classification. [ABSTRACT FROM AUTHOR]

Video Object Segmentation (VOS) methods have made many breakthroughs with the help of the continuous development and advancement of deep learning. However, the deep learning model is vulnerable to malicious adversarial attacks, which mislead the model to make wrong decisions by adding adversarial perturbation that humans cannot perceive to the input image. Threats to deep learning models remind us that video object segmentation methods are also vulnerable to attacks, thereby threatening their security. Therefore, we study adversarial attacks on the VOS task to better identify the vulnerabilities of the VOS method, which in turn provides an opportunity to improve its robustness. In this paper, we propose an attention-guided adversarial attack method, which uses spatial attention blocks to capture features with global dependencies to construct correlations between consecutive video frames, and performs multipath aggregation to effectively integrate spatial-temporal perturbation, thereby guiding the deconvolution network to generate adversarial examples with strong attack capability. Specifically, the class loss function is designed to enable the deconvolution network to better activate noise in other regions and suppress the activation related to the object class based on the enhanced feature map of the object class. At the same time, attentional feature loss is designed to enhance the transferability against attack. The experimental results on the DAVIS dataset show that the proposed attention-guided adversarial attack method can significantly reduce the segmentation accuracy of OSVOS, and the J&F mean on DAVIS 2016 can reach 73.6% drop rate. The generated adversarial examples are also highly transferable to other video object segmentation models. [ABSTRACT FROM AUTHOR]

Classifying mobile applications from encrypted network traffic is a common and basic requirement in network security and network management. Existing works classify mobile applications from flows, based on which application fingerprints and classifiers are created. However, mobile applications often generate concurrent flows with varying degrees of ties, such as low discriminative flows across applications and application-specific flows. So flow-based methods suffer from low accuracy. In this paper, a novel mobile application-classifying method is proposed, capturing relationships between flows and paying attention to their importance. To capture the inter-flow relationships, the proposed method slices raw mobile traffic into traffic chunks to represent flows as nodes, embeds statistical features into nodes, and adds edges according to cross-correlations between the nodes. To pay different attention to the various flows, the proposed method builds a deep learning model based on graph attention networks, implicitly assigning importance values to flows via graph attention layers. Compared to recently developed techniques on a large dataset with 101 popular apps using the Android platform, the proposed method improved by 4–20% for accuracy, precision, recall, and F1 score, and spent much less time training. [ABSTRACT FROM AUTHOR]

The neural network-based remote sensing image change detection method faces a large amount of imaging interference and severe class imbalance problems under high-resolution conditions, which bring new challenges to the accuracy of the detection network. In this work, to address the imaging interference caused by different imaging angles and times, the siamese strategy and multi-head self-attention mechanism are used to reduce the imaging differences between the dual-temporal images and fully exploit the inter-temporal information. Secondly, a learnable multi-part feature learning module is used to adaptively exploit features from different scales to obtain more comprehensive features. Finally, a mixed loss function strategy is used to ensure that the network converges effectively and excludes the adverse interference of a large number of negative samples to the network. Extensive experiments show that our method outperforms numerous methods on LEVIR-CD, WHU, and DSIFN datasets. [ABSTRACT FROM AUTHOR]

Over the past years, the increasingly severe data island problem has spawned an emerging distributed deep learning framework—federated learning, in which the global model can be constructed over multiple participants without directly sharing their raw data. Despite its promising prospect, there are still many security challenges in federated learning, such as privacy preservation and integrity verification. Furthermore, federated learning is usually performed with the assistance of a center, which is prone to cause trust worries and communicational bottlenecks. To tackle these challenges, in this paper, we propose a privacy-preserving and verifiable decentralized federated learning framework, named PVD-FL, which can achieve secure deep learning model training under a decentralized architecture. Specifically, we first design an efficient and verifiable cipher-based matrix multiplication (EVCM) algorithm to execute the most basic calculation in deep learning. Then, by employing EVCM, we design a suite of decentralized algorithms to construct the PVD-FL framework, which ensures the confidentiality of both global model and local update and the verification of every training step. Detailed security analysis shows that PVD-FL can well protect privacy against various inference attacks and guarantee training integrity. In addition, the extensive experiments on real-world datasets also demonstrate that PVD-FL can achieve lossless accuracy and practical performance. [ABSTRACT FROM AUTHOR]

The appropriate setting of hyperparameter is a key factor to determine the performance of the deep learning model. Efficient hyperparametric optimization algorithm can not only improve the efficiency and speed of model hyperparametric optimization, but also reduce the application threshold of deep learning model. Therefore, we propose a parameter learning algorithm-based co-evolutionary for remote sensing scene classification. First, a co-evolution framework is proposed to optimize the optimizer's hyperparameters and weight parameters of the convolutional neural networks (CNNs) simultaneously. Second, with the strategy of co-evolution with two populations, the hyperparameters can learn within the population and the weights of CNN can be updated by utilizing information between the populations. Finally, the parallel computing mechanism is adapted to speed up the learning process, as the two populations can evolve simultaneously. Extensive experiments on three public datasets demonstrate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Visible-infrared person re-identification (VI-ReID) aims at matching people across images from RGB and infrared modality. Existing methods tend to utilize the readily available models to extract features, ignoring mining spatial and channel information of features. In this paper, we propose an attentive modality-consistent network (AMC-Net) for VI-ReID. Firstly, to avoid the damage to discriminability of features caused by overfitting of local regions in the network, a context-aware attention block (CAB) is designed to mine the spatial information of the whole person region by magnifying the perception scope of convolution layers. Secondly, the attentive channel aggregation block (ACB) is adopted to mine the channel information with richer semantic cues by considering local cross-channel interactive information. Thirdly, we propose a modality-consistent regularizer to narrow down the discrepancy of high order features between heterogeneous images. Extensive experiments on two datasets indicate that the proposed method outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Image semantic segmentation is one of the most important tasks in the field of computer vision, and it has made great progress in many applications. Many fully supervised deep learning models are designed to implement complex semantic segmentation tasks and the experimental results are remarkable. However, the acquisition of pixel-level labels in fully supervised learning is time consuming and laborious, semi-supervised and weakly supervised learning is gradually replacing fully supervised learning, thus achieving good results at a lower cost. Based on the commonly used models such as convolutional neural networks, fully convolutional networks, generative adversarial networks, this paper focuses on the core methods and reviews the semi- and weakly supervised semantic segmentation models in recent years. In the following chapters, existing evaluations and data sets are summarized in details and the experimental results are analyzed according to the data set. The last part of the paper is an objective summary. In addition, it points out the possible direction of research and inspiring suggestions for future work. [ABSTRACT FROM AUTHOR]

The convolutional neural networks (CNNs) have shown powerful feature representation capability, which provides novel avenues to improve scene classification of remote sensing imagery. Although we can acquire large collections of satellite images, the lack of rich label information is still a major concern in the remote sensing field. In addition, remote sensing data sets have their own limitations, such as the small scale of scene classes and lack of image diversity. To mitigate the impact of the existing problems, a Siamese CNN, which combines the identification and verification models of CNNs, is proposed in this letter. A metric learning regularization term is explicitly imposed on the features learned through CNNs, which enforce the Siamese networks to be more robust. We carried out experiments on three widely used remote sensing data sets for performance evaluation. Experimental results show that our proposed method outperforms the existing methods. [ABSTRACT FROM AUTHOR]

Feature pyramid networks are widely applied in remote sensing images for object detection to deal with the challenge of large scale variation in objects. However, the feature pyramid-based object detector for remote sensing images ignores the channel information loss, feature misalignment, and additional computational overhead to eliminate the aliasing effect, leading to inadequate feature extraction for multi-scale objects in remote sensing images. To address these challenges, an Informative Feature Pyramid Network (Info-FPN) is proposed. Specifically, we propose a Pixel Shuffle-based lateral connection Module (PSM) for the complete preservation of channel information in the feature pyramid. Then, to alleviate the problem of confusion caused by feature misalignment, a Feature Alignment Module (FAM) is proposed to achieve aligned feature fusion by template matching and learning feature offsets in the feature fusion stage. To eliminate the aliasing effect, we design a Semantic Encoder Module (SEM), which reduces the parameters and computation of model with the desirable detection accuracy. Extensive experiments on two challenging remote sensing datasets, namely DOTA and HRSC2016, prove the effectiveness of the proposed method which achieves comparable detection performance with the state-of-the-art FPN-based method. • A new feature pyramid network is proposed for remote sensing images detection. • Reducing the channel information loss for remote sensing images using Pixel Shuffle. • Offset learning and template matching align multi-scale features. • Simple encoder can replace redundant calculations that eliminate aliasing effects. • Our model achieves state-of-the-art performance for remote sensing images detection. [ABSTRACT FROM AUTHOR]

The remote sensing data is difficult to collect and lack of diversity, which extremely limits the performance of object detection on remote sensing images. In this paper, a multi-branch conditional generative adversarial network (MCGAN) is proposed to augment data for object detection in optical remote sensing images, which is the first GANs-based data augmentation framework proposed for this topic. We use MCGAN to generate the diverse objects based on the existing remote sensing datasets. The multi-branch dilated convolution and the classification branch are adopted into MCGAN to help the generator to generate the diverse and high-quality images. Meanwhile, an adaptive samples selection strategy based on the Faster R-CNN is proposed to select the samples for data augmentation from the objects generated by MCGAN, which can ensure the quality of new augmented training sets and improve the diversity of samples. Experiments based on NWPU VHR-10 and DOTA show that the objects generated by MCGAN have the higher quality compared with the objects generated by WGAN and LSGAN. And the mean average precision detected by the state-of-the-art object detection models used in the experiments has the satisfactory improvement after the MCGAN based data augmentation, which indicates that data augmentation by MCGAN can effectively improve the accuracy of remote sensing images object detection. [ABSTRACT FROM AUTHOR]