Semantic Constraint Based Unsupervised Domain Adaptation for Cardiac Segmentation

The segmentation of unlabeled medical images is troublesome due to the high cost of annotation, and unsupervised domain adaptation is one solution to this. In this paper, an improved unsupervised domain adaptation method was proposed. The proposed method considered both global alignment and category-wise alignment. First, we aligned the appearance of two domains by image transformation. Second, we aligned the output maps of two domains in a global way. Then, we decomposed the semantic prediction map by category, aligning the prediction maps in a category-wise manner. Finally, we evaluated the proposed method on the 2017 Multi-Modality Whole Heart Segmentation Challenge dataset, and obtained 82.1 on the dice similarity coefficient and 4.6 on the average symmetric surface distance, demonstrating the effectiveness of the combination of global alignment and category-wise alignment.

WADE-Net: Weighted Aggregation with Density Estimation for Point Cloud Place Recognition

Point cloud based place recognition plays an important role in mobile robotics. In this paper, we propose a weighted aggregation method from structure information adaptively for point cloud place recognition. Firstly, to preserve the prior distributions and local geometric structures, we fuse learned hidden features with handcrafted features in the beginning. Secondly, we further extract and aggregate adaptively weighted features concerning density and relative spatial information from these fused features, named Weighted Aggregation with Density Estimation (WADE) module. Then, we conduct the WADE block iteratively to group the latent manifold structures. Finally, comparison results on two public datasets Oxford Robotcar and KITTI show that the proposed approach exceeds the comparison approaches on recall rate averagely 7% - 8%.

Lipidomic analyses reveal enhanced lipolysis in planthoppers feeding on resistant host plants

The brown planthopper(BPH)(Nilaparvata lugens St?l)is a highly destructive pest that seriously damages rice(Oryza sativa L.)and causes severe yield losses.To better understand the physiological and metabolic mechanisms through which BPHs respond to resistant rice,we combined mass-spectrometry-based lipidomics with transcriptomic analysis and gene knockdown techniques to compare the lipidomes of BPHs feeding on either of the two resistant(NIL-Bph6 and NIL-Bph9)plants or a wild-type,BPH susceptible(9311)plant.Insects that were fed on resistant rice transformed triglyceride(TG)to phosphatidylcholine(PC)and digalactosyldiacylglycerol(DGDG),with these lipid classes showing significant alterations in fatty acid composition.Moreover,the insects that were fed on resistant rice were characterized by prominent expression changes in genes involved in lipid metabolism processes.Knockdown of the NlBmm gene,which encodes a lipase that regulates the mobilization of lipid reserves,significantly increased TG content and feeding performance of BPHs on resistant plants relative to dsGFP-injected BPHs.Our study provides the first detailed description of lipid changes in BPHs fed on resistant and susceptible rice genotypes.Results from BPHs fed on resistant rice plants reveal that these insects can accelerate TG mobilization to provide energy for cell proliferation,body maintenance,growth and oviposition.