| 1. |
- Wang, Gang, et al.
(författare)
-
US2Mask : Image-to-mask generation learning via a conditional GAN for cardiac ultrasound image segmentation
- 2024
-
Ingår i: Computers in Biology and Medicine. - Oxford : Elsevier. - 0010-4825 .- 1879-0534. ; 172, s. 1-13
-
Tidskriftsartikel (refereegranskat)abstract
- Cardiac ultrasound (US) image segmentation is vital for evaluating clinical indices, but it often demands a large dataset and expert annotations, resulting in high costs for deep learning algorithms. To address this, our study presents a framework utilizing artificial intelligence generation technology to produce multi-class RGB masks for cardiac US image segmentation. The proposed approach directly performs semantic segmentation of the heart's main structures in US images from various scanning modes. Additionally, we introduce a novel learning approach based on conditional generative adversarial networks (CGAN) for cardiac US image segmentation, incorporating a conditional input and paired RGB masks. Experimental results from three cardiac US image datasets with diverse scan modes demonstrate that our approach outperforms several state-of-the-art models, showcasing improvements in five commonly used segmentation metrics, with lower noise sensitivity. Source code is available at https://github.com/energy588/US2mask. © 2024 Elsevier Ltd
|
|
| 2. |
- Yao, Xingang, et al.
(författare)
-
Q63, a novel DENV2 RdRp non-nucleoside inhibitor, inhibited DENV2 replication and infection
- 2018
-
Ingår i: Journal of Pharmacological Sciences. - Amsterdam : Elsevier. - 1347-8613 .- 1347-8648. ; 138:4, s. 247-256
-
Tidskriftsartikel (refereegranskat)abstract
- Dengue virus (DENV) annually infects 400 million people worldwide. Unfortunately, there is lack ofwidely protective vaccine or drugs against DENV. The viral RNA-dependent RNA polymerase (RdRp) ofNS5 protein is highly conserved among different DENV subtypes, thus presenting itself as an attractivetarget for drug design. In the current research, SPRi was performed to screen compounds against DENV2RdRp and 5(1H)-Quinazolinone,2-(4-bromophenyl)-2,3,4,6,7,8-hexahydro-7,7-dimethyl-1,3-diphenyl(Q63) was successfully screened out with a KD of 0.9 mM. Then, ITC and molecular docking assay wasperformed to access the binding mechanism between Q63 and DENV2 RdRp. Meanwhile, Q63 alsodecreased the intermediate dsRNA production, which was the product of RdRp. Further the antiviraleffects of Q63 were evaluated on mosquito C6/36 cells and mammalian BHK-21 cells. Q63 reduced CPEand cell toxicity effect after DENV2 infection on C6/36 and BHK-21 cells, with an EC50 of 2.08 mM. Time ofaddition assay revealed that Q63 affected the early genome RNA replication stage, including genome RNAreplication. In addition, Q63 down-regulated STAT1 phosphorylation, ISG15 and ISG54 after DENV2infection. In summary, Q63 was found to be a novel RdRp non-nucleoside inhibitor and a potential leadcompound for coping with DENV infectious disease in the future. © 2018 The Authors.
|
|
