Latent Space Phenotyping:Automatic Image-Based Phenotyping for Treatment Studies

作     者：Jordan Ubbens Mikolaj Cieslak Przemyslaw Prusinkiewicz Isobel Parkin Jana Ebersbach Ian Stavness 

作者机构：Department of Computer ScienceUniversity of SaskatchewanCanada Department of Computer ScienceUniversity of CalgaryCanada Agriculture and Agri-Food CanadaSaskatoonSKCanada 

出 版 物：《Plant Phenomics》 (植物表型组学（英文）)

年 卷 期：2020年第2卷第1期

页      面：1-13页

核心收录：

学科分类：082804[工学-农业电气化与自动化] 081203[工学-计算机应用技术] 08[工学] 0828[工学-农业工程] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Natural Sciences and Engineering Research Council of Canada  NSERC 

主　　题：typically traits mapping 

摘      要：Association mapping studies have enabled researchers to identify candidate loci for many important environmental tolerance factors,including agronomically relevant tolerance traits in ***,traditional genome-by-environment studies such as these require a phenotyping pipeline which is capable of accurately measuring stress responses,typically in an automated highthroughput context using image *** this work,we present Latent Space Phenotyping(LSP),a novel phenotyping method which is able to automatically detect and quantify response-to-treatment directly from *** demonstrate example applications using data from an interspecific cross of the model C_(4) grass Setaria,a diversity panel of sorghum(***),and the founder panel for a nested association mapping population of canola(Brassica napus L.).Using two synthetically generated image datasets,we then show that LSP is able to successfully recover the simulated QTL in both simple and complex synthetic *** propose LSP as an alternative to traditional image analysis methods for phenotyping,enabling the phenotyping of arbitrary and potentially complex response traits without the need for engineering-complicated image-processing pipelines.