Universal lesion detection(ULD)methods for computed tomography(CT)images play a vital role in the modern clinical medicine and intelligent automation.It is well known that single 2D CT slices lack spatial-temporal cha...Universal lesion detection(ULD)methods for computed tomography(CT)images play a vital role in the modern clinical medicine and intelligent automation.It is well known that single 2D CT slices lack spatial-temporal characteristics and contextual information compared to 3D CT blocks.However,3D CT blocks necessitate significantly higher hardware resources during the learning phase.Therefore,efficiently exploiting temporal correlation and spatial-temporal features of 2D CT slices is crucial for ULD tasks.In this paper,we propose a ULD network with the enhanced temporal correlation for this purpose,named TCE-Net.The designed TCE module is applied to enrich the discriminate feature representation of multiple sequential CT slices.Besides,we employ multi-scale feature maps to facilitate the localization and detection of lesions in various sizes.Extensive experiments are conducted on the DeepLesion benchmark demonstrate that thismethod achieves 66.84%and 78.18%for FS@0.5 and FS@1.0,respectively,outperforming compared state-of-the-art methods.展开更多
Twenty five serotypes of Bluetongue virus (BTV) have been identified worldwide. Rapid and reliable methods of virus universal detection are essential for fighting against bluetongue (BT). We have therefore developed a...Twenty five serotypes of Bluetongue virus (BTV) have been identified worldwide. Rapid and reliable methods of virus universal detection are essential for fighting against bluetongue (BT). We have therefore developed and evaluated a pair of primers which can detect various serotypes of BTV by RT-PCR. Analysis of the viral protein 7 (VP7) and the non-structural protein (NS1) gene from different serotypes of BTV by DNAstar showed that the 5' end of the NS1 gene is the most conserved region. The primer pairs (P1 and P2) were designed based on the highly conserved region of NS1. The novel primers were evaluated by detecting BTV serotypes 1, 3, 5, 8, 10, 11, 21 and 22. The specificity of the primers was estimated by comparing to gene sequences of viruses published in GenBank, and further assessed by detecting BTV serotype 1-12 and Epizootic hemorrhagic disease virus (EHDV) serotype 1-4. The sensitivity and repeatability of PCR with the novel primers were evaluated by successfully detecting the recombinant plasmid pGEM-T121 containing the diagnosed nucleotide sequence. Our results suggest that these unique primers can be used in high throughout and universal detection of the NS1 gene from various BTV serotypes.展开更多
基金Taishan Young Scholars Program of Shandong Province,Key Development Program for Basic Research of Shandong Province(ZR2020ZD44).
文摘Universal lesion detection(ULD)methods for computed tomography(CT)images play a vital role in the modern clinical medicine and intelligent automation.It is well known that single 2D CT slices lack spatial-temporal characteristics and contextual information compared to 3D CT blocks.However,3D CT blocks necessitate significantly higher hardware resources during the learning phase.Therefore,efficiently exploiting temporal correlation and spatial-temporal features of 2D CT slices is crucial for ULD tasks.In this paper,we propose a ULD network with the enhanced temporal correlation for this purpose,named TCE-Net.The designed TCE module is applied to enrich the discriminate feature representation of multiple sequential CT slices.Besides,we employ multi-scale feature maps to facilitate the localization and detection of lesions in various sizes.Extensive experiments are conducted on the DeepLesion benchmark demonstrate that thismethod achieves 66.84%and 78.18%for FS@0.5 and FS@1.0,respectively,outperforming compared state-of-the-art methods.
基金Hi-Tech Research and Development Program of China (2006AA10Z446)
文摘Twenty five serotypes of Bluetongue virus (BTV) have been identified worldwide. Rapid and reliable methods of virus universal detection are essential for fighting against bluetongue (BT). We have therefore developed and evaluated a pair of primers which can detect various serotypes of BTV by RT-PCR. Analysis of the viral protein 7 (VP7) and the non-structural protein (NS1) gene from different serotypes of BTV by DNAstar showed that the 5' end of the NS1 gene is the most conserved region. The primer pairs (P1 and P2) were designed based on the highly conserved region of NS1. The novel primers were evaluated by detecting BTV serotypes 1, 3, 5, 8, 10, 11, 21 and 22. The specificity of the primers was estimated by comparing to gene sequences of viruses published in GenBank, and further assessed by detecting BTV serotype 1-12 and Epizootic hemorrhagic disease virus (EHDV) serotype 1-4. The sensitivity and repeatability of PCR with the novel primers were evaluated by successfully detecting the recombinant plasmid pGEM-T121 containing the diagnosed nucleotide sequence. Our results suggest that these unique primers can be used in high throughout and universal detection of the NS1 gene from various BTV serotypes.
