TY - JOUR T1 - ChronoRoot: High-throughput phenotyping by deep segmentation networks reveals novel temporal parameters of plant root system architecture JF - bioRxiv DO - 10.1101/2020.10.27.350553 SP - 2020.10.27.350553 AU - Nicolás Gaggion AU - Federico Ariel AU - Vladimir Daric AU - Éric Lambert AU - Simon Legendre AU - Thomas Roulé AU - Alejandra Camoirano AU - Diego H. Milone AU - Martin Crespi AU - Thomas Blein AU - Enzo Ferrante Y1 - 2021/01/01 UR - http://biorxiv.org/content/early/2021/07/13/2020.10.27.350553.abstract N2 - Background Deep learning methods have outperformed previous techniques in most computer vision tasks, including image-based plant phenotyping. However, massive data collection of root traits and the development of associated artificial intelligence approaches have been hampered by the inaccessibility of the rhizosphere. Here we present ChronoRoot, a system which combines 3D printed open-hardware with deep segmentation networks for high temporal resolution phenotyping of plant roots in agarized medium.Results We developed a novel deep learning based root extraction method which leverages the latest advances in convolutional neural networks for image segmentation, and incorporates temporal consistency into the root system architecture reconstruction process. Automatic extraction of phenotypic parameters from sequences of images allowed a comprehensive characterization of the root system growth dynamics. Furthermore, novel time-associated parameters emerged from the analysis of spectral features derived from temporal signals.Conclusions Altogether, our work shows that the combination of machine intelligence methods and a 3D-printed device expands the possibilities of root high-throughput phenotyping for genetics and natural variation studies as well as the screening of clock-related mutants, revealing novel root traits.Competing Interest StatementThe authors have declared no competing interest.CLcontinuous lightCNNconvolutional neural networkCRFconditional random fieldDFSdepth first searchDSResUNetDeeply Supervised ResUNetELUexponential linear unitFCNfully convolutional networkFFTfast Fourier TransformGPUgraphical processing unitGWASgenome-wide association studiesGTground truthIRinfra-redLDlong dayLRlateral rootMRmain rootNIRnear infra-redRELUrectified linear unitROIregion of interestRSAroot system architectureRSMLRoot System Markup LanguageSDstandard deviationTRtotal root ER -