- 著者
- Jianbo WANG Haozhi HUANG Li SHEN Xuan WANG Toshihiko YAMASAKI
- 出版者
- The Institute of Electronics, Information and Communication Engineers
- 雑誌
- IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)
- 巻号頁・発行日
- vol.E106-D, no.12, pp.2085-2096, 2023-12-01
The image-to-image translation aims to learn a mapping between the source and target domains. For improving visual quality, the majority of previous works adopt multi-stage techniques to refine coarse results in a progressive manner. In this work, we present a novel approach for generating plausible details by only introducing a group of intermediate supervisions without cascading multiple stages. Specifically, we propose a Laplacian Pyramid Transformation Generative Adversarial Network (LapTransGAN) to simultaneously transform components in different frequencies from the source domain to the target domain within only one stage. Hierarchical perceptual and gradient penalization are utilized for learning consistent semantic structures and details at each pyramid level. The proposed model is evaluated based on various metrics, including the similarity in feature maps, reconstruction quality, segmentation accuracy, similarity in details, and qualitative appearances. Our experiments show that LapTransGAN can achieve a much better quantitative performance than both the supervised pix2pix model and the unsupervised CycleGAN model. Comprehensive ablation experiments are conducted to study the contribution of each component.
- 著者
- Ping Zhang Jianfang Luo Tianlong Wu Xuan Wang Fan Yang Yanhong Yu Lihe Lu Huimin Yu
- 出版者
- International Heart Journal Association
- 雑誌
- International Heart Journal (ISSN:13492365)
- 巻号頁・発行日
- vol.63, no.5, pp.928-938, 2022-09-30 (Released:2022-09-30)
- 参考文献数
- 39
- 被引用文献数
- 4
The role of endothelial injury and inflammation in atherosclerosis has been well established. miRNAs have been found to be key regulators in the development of atherosclerosis. Here we investigated whether miR-32-5p and its predicted target gene axin interactor, dorsalization associated (AIDA) are involved in endothelial injury and inflammation. Human umbilical vein endothelial cells (HUVECs) were treated with oxidized low-density lipoprotein (oxLDL) to induce endothelial injury and inflammation. AIDA was predicted to be a target gene of miR-32-5p using TargetScan software. Cell viability, migration, and angiogenesis were evaluated using Cell Counting Kit-8, wound-healing, and tube formation assays, respectively. The expression of inflammatory factors was detected using quantitative PCR, enzyme-linked immunosorbent assay, and western blot. We found that miR-32-5p expression was significantly decreased, whereas AIDA expression was significantly increased in oxLDL-treated HUVECs and the increased AIDA expression was reversed by the up-regulation of miR-32-5p. Moreover, both miR-32-5p mimic and knockdown of AIDA enhanced cell viability, promoted cell migration and angiogenesis and suppressed the expression of inflammatory factors including IL-1β, IL-6, TNF-α, ICAM-1, and VCAM-1 in oxLDL-induced HUVECs. Furthermore, miR-32-5p was verified to directly target AIDA using dual-luciferase reporter assay. Overall, these findings suggest that miR-32-5p/AIDA signal plays an important role in oxLDL-induced endothelial injury and inflammation. This study provides new insights into novel molecular mechanisms of endothelial dysfunction and atherosclerosis.