Purpose: The present study aimed to assess the associations of expansive remodeling of carotid arteries with ischemic symptoms and the degree of stenosis. Materials and Methods: A total of 41 symptomatic patients with...Purpose: The present study aimed to assess the associations of expansive remodeling of carotid arteries with ischemic symptoms and the degree of stenosis. Materials and Methods: A total of 41 symptomatic patients with vulnerable plaques and 25 asymptomatic individuals with stable plaques were included. All patients underwent 3.0T high-resolution MRI of the carotid artery(CA) for measuring the expansive remodeling(ER) ratio and assessing plaque stability. The ER ratio was calculated by dividing the maximum distance between the lumen and the outer border of the plaque in the internal CA by the lumen diameter within 1 centimeter of the plaque at the distal ipsilateral internal CA. ER ratios were compared between the symptomatic and asymptomatic groups. The 41 symptomatic patients were further divided into 4 groups according to stenosis rate(CA stenosis <50%, 50%–74%, 75–89%, and > 90%), and the correlation between the ER ratio and the rate of stenosis was evaluated. Results: There was a significant difference in ER ratio between the symptomatic and asymptomatic groups(p<0.001). When symptomatic patients were divided into 4 subgroups based on degree of stenosis, ER ratios among groups showed statistically significant differences(p=0.014). Conclusion: There were significant associations of the ER ratio with ischemic symptoms. Furthermore, the ER ratio in symptomatic patients continued to increase with stenosis severity. These findings suggested that the ER ratio might be a practical marker of plaque vulnerability in the CA and further prospective studies for asymptomatic patients are warranted.展开更多
The advancement of the Internet of Things(IoT)brings new opportunities for collecting real-time data and deploying machine learning models.Nonetheless,an individual IoT device may not have adequate computing resources...The advancement of the Internet of Things(IoT)brings new opportunities for collecting real-time data and deploying machine learning models.Nonetheless,an individual IoT device may not have adequate computing resources to train and deploy an entire learning model.At the same time,transmitting continuous real-time data to a central server with high computing resource incurs enormous communication costs and raises issues in data security and privacy.Federated learning,a distributed machine learning framework,is a promising solution to train machine learning models with resource-limited devices and edge servers.Yet,the majority of existing works assume an impractically synchronous parameter update manner with homogeneous IoT nodes under stable communication connections.In this paper,we develop an asynchronous federated learning scheme to improve training efficiency for heterogeneous IoT devices under unstable communication network.Particularly,we formulate an asynchronous federated learning model and develop a lightweight node selection algorithm to carry out learning tasks effectively.The proposed algorithm iteratively selects heterogeneous IoT nodes to participate in the global learning aggregation while considering their local computing resource and communication condition.Extensive experimental results demonstrate that our proposed asynchronous federated learning scheme outperforms the state-of-the-art schemes in various settings on independent and identically distributed(i.i.d.)and non-i.i.d.data distribution.展开更多
The federated learning framework builds a deep learning model collaboratively by a group of connected devices via only sharing local parameter updates to the central parameter server.Nonetheless,the lack of transparen...The federated learning framework builds a deep learning model collaboratively by a group of connected devices via only sharing local parameter updates to the central parameter server.Nonetheless,the lack of transparency in the local data resource makes it prone to adversarial federated attacks,which have shown increasing ability to reduce learning performance.Existing research efforts either focus on the single-party attack with impractical perfect knowledge setting and limited stealthy ability or the random attack that has no control on attack effects.In this paper,we investigate a new multi-party adversarial attack with the imperfect knowledge of the target system.Controlled by an adversary,a number of compromised devices collaboratively launch targeted model poisoning attacks,intending to misclassify the targeted samples while maintaining stealthy under different de-tection strategies.Specifically,the compromised devices jointly minimize the loss function of model training in different scenarios.To overcome the update scaling problem,we develop a new boosting strategy by introducing two stealthy metrics.Via experimental results,we show that under both perfect knowledge and limited knowl-edge settings,the multi-party attack is capable of successfully evading detection strategies while guaranteeing the convergence.We also demonstrate that the learned model achieves the high accuracy on the targeted samples,which confirms the significant impact of the multi-party attack on federated learning systems.展开更多
基金Grants from the Shanghai Municipal Education Commission-Gaofeng Clinical Medicine Grant Support(No.20152528)Shanghai Pujiang Program(16PJD036)+3 种基金Three-year plan program by Shanghai Shen Kang Hospital Development Center(16CR3043A)Shanghai Science and Technology Commission of Shanghai Municipality Program(14DZ1941206)the Cross Project of Medicine and Engineering from Shanghai Jiao Tong University(YG2015MS21)Shanghai key discipline of medical imaging(No.2017ZZ02005)
文摘Purpose: The present study aimed to assess the associations of expansive remodeling of carotid arteries with ischemic symptoms and the degree of stenosis. Materials and Methods: A total of 41 symptomatic patients with vulnerable plaques and 25 asymptomatic individuals with stable plaques were included. All patients underwent 3.0T high-resolution MRI of the carotid artery(CA) for measuring the expansive remodeling(ER) ratio and assessing plaque stability. The ER ratio was calculated by dividing the maximum distance between the lumen and the outer border of the plaque in the internal CA by the lumen diameter within 1 centimeter of the plaque at the distal ipsilateral internal CA. ER ratios were compared between the symptomatic and asymptomatic groups. The 41 symptomatic patients were further divided into 4 groups according to stenosis rate(CA stenosis <50%, 50%–74%, 75–89%, and > 90%), and the correlation between the ER ratio and the rate of stenosis was evaluated. Results: There was a significant difference in ER ratio between the symptomatic and asymptomatic groups(p<0.001). When symptomatic patients were divided into 4 subgroups based on degree of stenosis, ER ratios among groups showed statistically significant differences(p=0.014). Conclusion: There were significant associations of the ER ratio with ischemic symptoms. Furthermore, the ER ratio in symptomatic patients continued to increase with stenosis severity. These findings suggested that the ER ratio might be a practical marker of plaque vulnerability in the CA and further prospective studies for asymptomatic patients are warranted.
文摘The advancement of the Internet of Things(IoT)brings new opportunities for collecting real-time data and deploying machine learning models.Nonetheless,an individual IoT device may not have adequate computing resources to train and deploy an entire learning model.At the same time,transmitting continuous real-time data to a central server with high computing resource incurs enormous communication costs and raises issues in data security and privacy.Federated learning,a distributed machine learning framework,is a promising solution to train machine learning models with resource-limited devices and edge servers.Yet,the majority of existing works assume an impractically synchronous parameter update manner with homogeneous IoT nodes under stable communication connections.In this paper,we develop an asynchronous federated learning scheme to improve training efficiency for heterogeneous IoT devices under unstable communication network.Particularly,we formulate an asynchronous federated learning model and develop a lightweight node selection algorithm to carry out learning tasks effectively.The proposed algorithm iteratively selects heterogeneous IoT nodes to participate in the global learning aggregation while considering their local computing resource and communication condition.Extensive experimental results demonstrate that our proposed asynchronous federated learning scheme outperforms the state-of-the-art schemes in various settings on independent and identically distributed(i.i.d.)and non-i.i.d.data distribution.
文摘The federated learning framework builds a deep learning model collaboratively by a group of connected devices via only sharing local parameter updates to the central parameter server.Nonetheless,the lack of transparency in the local data resource makes it prone to adversarial federated attacks,which have shown increasing ability to reduce learning performance.Existing research efforts either focus on the single-party attack with impractical perfect knowledge setting and limited stealthy ability or the random attack that has no control on attack effects.In this paper,we investigate a new multi-party adversarial attack with the imperfect knowledge of the target system.Controlled by an adversary,a number of compromised devices collaboratively launch targeted model poisoning attacks,intending to misclassify the targeted samples while maintaining stealthy under different de-tection strategies.Specifically,the compromised devices jointly minimize the loss function of model training in different scenarios.To overcome the update scaling problem,we develop a new boosting strategy by introducing two stealthy metrics.Via experimental results,we show that under both perfect knowledge and limited knowl-edge settings,the multi-party attack is capable of successfully evading detection strategies while guaranteeing the convergence.We also demonstrate that the learned model achieves the high accuracy on the targeted samples,which confirms the significant impact of the multi-party attack on federated learning systems.