Gaussian-guided feature alignment for unsupervised cross-subject adaptation

2022 ◽  
Vol 122 ◽  
pp. 108332
Author(s):  
Kuangen Zhang ◽  
Jiahong Chen ◽  
Jing Wang ◽  
Yuquan Leng ◽  
Clarence W. de Silva ◽  
...  
Keyword(s):  
2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Bagrat Grigoryan ◽  
Daniel W. Sazer ◽  
Amanda Avila ◽  
Jacob L. Albritton ◽  
Aparna Padhye ◽  
...  

AbstractAs a 3D bioprinting technique, hydrogel stereolithography has historically been limited in its ability to capture the spatial heterogeneity that permeates mammalian tissues and dictates structure–function relationships. This limitation stems directly from the difficulty of preventing unwanted material mixing when switching between different liquid bioinks. Accordingly, we present the development, characterization, and application of a multi-material stereolithography bioprinter that provides controlled material selection, yields precise regional feature alignment, and minimizes bioink mixing. Fluorescent tracers were first used to highlight the broad design freedoms afforded by this fabrication strategy, complemented by morphometric image analysis to validate architectural fidelity. To evaluate the bioactivity of printed gels, 344SQ lung adenocarcinoma cells were printed in a 3D core/shell architecture. These cells exhibited native phenotypic behavior as evidenced by apparent proliferation and formation of spherical multicellular aggregates. Cells were also printed as pre-formed multicellular aggregates, which appropriately developed invasive protrusions in response to hTGF-β1. Finally, we constructed a simplified model of intratumoral heterogeneity with two separate sub-populations of 344SQ cells, which together grew over 14 days to form a dense regional interface. Together, these studies highlight the potential of multi-material stereolithography to probe heterotypic interactions between distinct cell types in tissue-specific microenvironments.


Author(s):  
Xiaoqin Zhang ◽  
Jinxin Wang ◽  
Tao Wang ◽  
Runhua Jiang ◽  
Jiawei Xu ◽  
...  

Electronics ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 1205
Author(s):  
Zhiyu Wang ◽  
Li Wang ◽  
Bin Dai

Object detection in 3D point clouds is still a challenging task in autonomous driving. Due to the inherent occlusion and density changes of the point cloud, the data distribution of the same object will change dramatically. Especially, the incomplete data with sparsity or occlusion can not represent the complete characteristics of the object. In this paper, we proposed a novel strong–weak feature alignment algorithm between complete and incomplete objects for 3D object detection, which explores the correlations within the data. It is an end-to-end adaptive network that does not require additional data and can be easily applied to other object detection networks. Through a complete object feature extractor, we achieve a robust feature representation of the object. It serves as a guarding feature to help the incomplete object feature generator to generate effective features. The strong–weak feature alignment algorithm reduces the gap between different states of the same object and enhances the ability to represent the incomplete object. The proposed adaptation framework is validated on the KITTI object benchmark and gets about 6% improvement in detection average precision on 3D moderate difficulty compared to the basic model. The results show that our adaptation method improves the detection performance of incomplete 3D objects.


Author(s):  
Shuang Liu ◽  
Yuping Wu ◽  
Wenjun Lv ◽  
Ji Chang ◽  
Zerui Li ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document