Over the past decade,large-scale pre-trained autoregressive and diffusion models rejuvenated the field of text-guided image generation.However,these models require enormous datasets and parameters,and their multi-step...Over the past decade,large-scale pre-trained autoregressive and diffusion models rejuvenated the field of text-guided image generation.However,these models require enormous datasets and parameters,and their multi-step generation processes are often inefficient and difficult to control.To address these challenges,we propose CAFE-GAN,a CLIP-Projected GAN with Attention-Aware Generation and Multi-Scale Discrimination,which incorporates a pretrained CLIP model along with several key architectural innovations.First,we embed a coordinate attention mechanism into the generator to capture long-range dependencies and enhance feature representation.Second,we introduce a trainable linear projection layer after the CLIP text encoder,which aligns textual embeddings with the generator’s semantic space.Third,we design a multi-scale discriminator that leverages pre-trained visual features and integrates a feature regularization strategy,thereby improving training stability and discrimination performance.Experiments on the CUB and COCO datasets demonstrate that CAFE-GAN outperforms existing text-to-image generation methods,achieving lower Fréchet Inception Distance(FID)scores and generating images with superior visual quality and semantic fidelity,with FID scores of 9.84 and 5.62 on the CUB and COCO datasets,respectively,surpassing current state-of-the-art text-to-image models by varying degrees.These findings offer valuable insights for future research on efficient,controllable text-to-image synthesis.展开更多
Glycolytic metabolism enzymes have been implicated in the immunometabolism field through changes in metabolic status. PGK1 is a catalytic enzyme in the glycolytic pathway. Here, we set up a high-throughput screen plat...Glycolytic metabolism enzymes have been implicated in the immunometabolism field through changes in metabolic status. PGK1 is a catalytic enzyme in the glycolytic pathway. Here, we set up a high-throughput screen platform to identify PGK1 inhibitors. DC-PGKI is an ATPcompetitive inhibitor of PGK1 with an affinity of Kd= 99.08 nmol/L. DC-PGKI stabilizes PGK1in vitro and in vivo, and suppresses both glycolytic activity and the kinase function of PGK1. In addition,DC-PGKI unveils that PGK1 regulates production of IL-1β and IL-6 in LPS-stimulated macrophages.Mechanistically, inhibition of PGK1 with DC-PGKI results in NRF2(nuclear factor-erythroid factor 2-related factor 2, NFE2L2) accumulation, then NRF2 translocates to the nucleus and binds to the proximity region of Il-1β and Il-6 genes, and inhibits LPS-induced expression of these genes. DC-PGKI ameliorates colitis in the dextran sulfate sodium(DSS)-induced colitis mouse model. These data support PGK1 as a regulator of macrophages and suggest potential utility of PGK1 inhibitors in the treatment of inflammatory bowel disease.展开更多
Purpose We developed a low-complexity,high-resolution depth-of-interaction(DOI)capable positron emission tomography(PET)detector and tested its performance to prove that it can be applied to practical PET instruments....Purpose We developed a low-complexity,high-resolution depth-of-interaction(DOI)capable positron emission tomography(PET)detector and tested its performance to prove that it can be applied to practical PET instruments.Methods The detector module consists of a 24×24 LYSO crystal matrix,each with dimension of 1.04×1.04×15mm^(3),optically coupled to an 8×8 SiPM photo-sensor array with TOFPET2 ASIC single-ended readout.By only adding a light guide at the top of the crystal to reflect scintillation light back to the SiPM array,the continuous DOI information is extracted using a light sharing and redirection encoding method without adding system complexity.Results The crystal array with 9-to-1 coupling between scintillators and photo-sensors can be clearly separated in the flood image.The other detector performance in terms of DOI resolution,energy resolution and coincidence time resolution are measured on average as 4.1 mm,15.0%and 432 ps,respectively.Conclusion The test results confirm that the light sharing and redirection DOI encoding method can provide reasonably high DOI resolution without deteriorating other performance,even for highly pixelated PET detectors readout with commercially available ASIC chip.It has great potential for applications in future pre-clinical and organ-dedicated PET scanners.展开更多
文摘Over the past decade,large-scale pre-trained autoregressive and diffusion models rejuvenated the field of text-guided image generation.However,these models require enormous datasets and parameters,and their multi-step generation processes are often inefficient and difficult to control.To address these challenges,we propose CAFE-GAN,a CLIP-Projected GAN with Attention-Aware Generation and Multi-Scale Discrimination,which incorporates a pretrained CLIP model along with several key architectural innovations.First,we embed a coordinate attention mechanism into the generator to capture long-range dependencies and enhance feature representation.Second,we introduce a trainable linear projection layer after the CLIP text encoder,which aligns textual embeddings with the generator’s semantic space.Third,we design a multi-scale discriminator that leverages pre-trained visual features and integrates a feature regularization strategy,thereby improving training stability and discrimination performance.Experiments on the CUB and COCO datasets demonstrate that CAFE-GAN outperforms existing text-to-image generation methods,achieving lower Fréchet Inception Distance(FID)scores and generating images with superior visual quality and semantic fidelity,with FID scores of 9.84 and 5.62 on the CUB and COCO datasets,respectively,surpassing current state-of-the-art text-to-image models by varying degrees.These findings offer valuable insights for future research on efficient,controllable text-to-image synthesis.
基金the National Key Research and Development Program of China (2021ZD0203900 to Cheng Luo)the National Natural Science Foundation of China (91853205, 81821005 to Cheng Luo)+1 种基金the Science and Technology Commission of Shanghai Municipality (19XD1404700 to Cheng Luo, China)the project of National Multidisciplinary Innovation Team of Traditional Chinese Medicine supported by National Administration of Traditional Chinese Medicine to Cheng Luo, the Lingang Laboratory, Grant No. LG-QS-202206-01.
文摘Glycolytic metabolism enzymes have been implicated in the immunometabolism field through changes in metabolic status. PGK1 is a catalytic enzyme in the glycolytic pathway. Here, we set up a high-throughput screen platform to identify PGK1 inhibitors. DC-PGKI is an ATPcompetitive inhibitor of PGK1 with an affinity of Kd= 99.08 nmol/L. DC-PGKI stabilizes PGK1in vitro and in vivo, and suppresses both glycolytic activity and the kinase function of PGK1. In addition,DC-PGKI unveils that PGK1 regulates production of IL-1β and IL-6 in LPS-stimulated macrophages.Mechanistically, inhibition of PGK1 with DC-PGKI results in NRF2(nuclear factor-erythroid factor 2-related factor 2, NFE2L2) accumulation, then NRF2 translocates to the nucleus and binds to the proximity region of Il-1β and Il-6 genes, and inhibits LPS-induced expression of these genes. DC-PGKI ameliorates colitis in the dextran sulfate sodium(DSS)-induced colitis mouse model. These data support PGK1 as a regulator of macrophages and suggest potential utility of PGK1 inhibitors in the treatment of inflammatory bowel disease.
基金This work was supported by the National Natural Science Foundation of China[Grant Number 11735013].
文摘Purpose We developed a low-complexity,high-resolution depth-of-interaction(DOI)capable positron emission tomography(PET)detector and tested its performance to prove that it can be applied to practical PET instruments.Methods The detector module consists of a 24×24 LYSO crystal matrix,each with dimension of 1.04×1.04×15mm^(3),optically coupled to an 8×8 SiPM photo-sensor array with TOFPET2 ASIC single-ended readout.By only adding a light guide at the top of the crystal to reflect scintillation light back to the SiPM array,the continuous DOI information is extracted using a light sharing and redirection encoding method without adding system complexity.Results The crystal array with 9-to-1 coupling between scintillators and photo-sensors can be clearly separated in the flood image.The other detector performance in terms of DOI resolution,energy resolution and coincidence time resolution are measured on average as 4.1 mm,15.0%and 432 ps,respectively.Conclusion The test results confirm that the light sharing and redirection DOI encoding method can provide reasonably high DOI resolution without deteriorating other performance,even for highly pixelated PET detectors readout with commercially available ASIC chip.It has great potential for applications in future pre-clinical and organ-dedicated PET scanners.
