2篇
您的检索式：作者名="Ruichao Mo"
|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Epidemiological characteristics and genetic alterations in adult diffuse glioma in East Asianpopulations显示文摘Understanding the racial specificities of diseases—such as adult diffuse glioma,the most common primary malignant tumor of the central nervous system—is a critical step toward precision medicine.Here,we comprehensively review studies of gliomas in East Asian populations and other ancestry groups to clarify the racial differences in terms of epidemiology and genomic characteristics.Overall,we observed a lower glioma incidence in East Asians than in Whites;notably,patients with glioblastoma had significantly younger ages of onset and longer overall survival than the Whites.Multiple genome-wide association studies of various cohorts have revealed single nucleotide polymorphisms associated with overall and subtype-specific glioma susceptibility.Notably,only 3 risk loci—5p15.33,11q23.3,and 20q13.33—were shared between patients with East Asian and White ancestry,whereas other loci predominated only in particular populations.For instance,risk loci 12p11.23,15q15-21.1,and 19p13.12 were reported in East Asians,whereas risk loci 8q24.21,1p31.3,and 1q32.1 were reported in studies in White patients.Although the somatic mutational profiles of gliomas between East Asians and non-East Asians were broadly consistent,a lower incidence of EGFR amplification in glioblastoma and a higher incidence of 1p19q-IDH-TERT triple-negative low-grade glioma were observed in East Asian cohorts.By summarizing large-scale disease surveillance,germline,and somatic genomic studies,this review reveals the unique characteristics of adult diffuse glioma among East Asians,to guide clinical management and policy design focused on patients with East Asian ancestry. | Zongchao Mo Junyi Xin Ruichao Chai Peter Y.M.Woo Danny T.M.Chan Jiguang Wang | 2022 | Cancer Biology & Medicine2022，19，10： | 1 |
| 2 | Pedestrian and Vehicle Detection Based on Pruning YOLOv4 with Cloud-Edge Collaboration显示文摘Nowadays,the rapid development of edge computing has driven an increasing number of deep learning applications deployed at the edge of the network,such as pedestrian and vehicle detection,to provide efficient intelligent services to mobile users.However,as the accuracy requirements continue to increase,the components of deep learning models for pedestrian and vehicle detection,such as YOLOv4,become more sophisticated and the computing resources required for model training are increasing dramatically,which in turn leads to significant challenges in achieving effective deployment on resource-constrained edge devices while ensuring the high accuracy performance.For addressing this challenge,a cloud-edge collaboration-based pedestrian and vehicle detection framework is proposed in this paper,which enables sufficient training of models by utilizing the abundant computing resources in the cloud,and then deploying the well-trained models on edge devices,thus reducing the computing resource requirements for model training on edge devices.Furthermore,to reduce the size of the model deployed on edge devices,an automatic pruning method combines the convolution layer and BN layer is proposed to compress the pedestrian and vehicle detection model size.Experimental results show that the framework proposed in this paper is able to deploy the pruned model on a real edge device,Jetson TX2,with 6.72 times higher FPS.Meanwhile,the channel pruning reduces the volume and the number of parameters to 96.77%for the model,and the computing amount is reduced to 81.37%. | Huabin Wang Ruichao Mo Yuping Chen Weiwei Lin Minxian Xu Bo Liu | 2023 | Computer Modeling in Engineering & Sciences2023，，11： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员