Peanut (Arachis hypogaea L.) is an important oilseed crop worldwide, and peanut height has been shown to be closely related to yield, therefore a better understanding of the genetic base of plant height-related traits may allow us to have better control of crop yield. Plant height-related traits are quantitative traits that are genetically controlled by many genes, and distinct quantitive trait loci (QTLs) may be identified for different peanut accessions/genotypes. In the present study, in order to gain a more complete picture of the genetic base for peanut height-related traits, we first make use of the high quality NGS sequence data for 159 peanut accessions that are available within our research groups, to carry out a GWAS study for searching plant height-related regions. We then perform a literature survey and collect QTLs for two plant height-related traits (Ph: peanut main stem height, and Fbl: the first branch length) from earlier related QTL/GWAS studies in peanut. In total, we find 74 and 21 genomic regions that are, associated with traits Ph and Fbl, respectively. Annotation of these regions found a total of 692 and 229 genes for, respectively, Ph and Fbl, and among those genes, 158 genes are shared. KEGG and GO enrichment analyses of those candidate genes reveal that Ph- and Fbl-associated genes are both enriched in the biosynthesis of secondary metabolites, some basic processes, pathways, or complexes that are supposed to be crucial for plant development and growth.
Image segmentation plays an essential role in medical imaging analysis such as tumor boundary extraction. Recently, deep learning techniques have dramatically improved performance for image segmentation. However, an important factor preventing deep neural networks from going further is the information loss during the information propagation process. In this article, we present AX-Unet, a deep learning framework incorporating a modified atrous spatial pyramid pooling module to learn the location information and to extract multi-level contextual information to reduce information loss during downsampling. We also introduce a special group convolution operation on the feature map at each level to achieve information decoupling between channels. In addition, we propose an explicit boundary-aware loss function to tackle the blurry boundary problem. We evaluate our model on two public Pancreas-CT datasets, NIH Pancreas-CT dataset, and the pancreas part in medical segmentation decathlon (MSD) medical dataset. The experimental results validate that our model can outperform the state-of-the-art methods in pancreas CT image segmentation. By comparing the extracted feature output of our model, we find that the pancreatic region of normal people and patients with pancreatic tumors shows significant differences. This could provide a promising and reliable way to assist physicians for the screening of pancreatic tumors.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.