Phenotyping of xylem vessels for drought stress analysis in rice

Abstract: Quantification of physiological changes in plants can capture different drought mechanisms and assist in selection of tolerant varieties in a high throughput manner In this context, an accurate 3D model of plant canopy provides a reliable representation for drought stress characterization in contrast to using 2D images In this paper, we propose a novel end-to-end pipeline including 3D reconstruction, segmentation and feature extraction, leveraging deep neural networks at various stages, for drought stress study To overcome the high degree of self-similarities and self-occlusions in plant canopy, prior knowledge of leaf shape based on features from deep siamese network are used to construct an accurate 3D model using structure from motion on wheat plants The drought stress is characterized with a deep network based feature aggregation We compare the proposed methodology on several descriptors, and show that the network outperforms conventional methods

Abstract: Quantification of physiological changes in plants can capture different drought mechanisms and assist in selection of tolerant varieties in a high throughput manner. In this context, an accurate 3D model of plant canopy provides a reliable representation for drought stress characterization in contrast to using 2D images. In this paper, we propose a novel end-to-end pipeline including 3D reconstruction, segmentation and feature extraction, leveraging deep neural networks at various stages, for drought stress study. To overcome the high degree of self-similarities and self-occlusions in plant canopy, prior knowledge of leaf shape based on features from deep siamese network are used to construct an accurate 3D model using structure from motion on wheat plants. The drought stress is characterized with a deep network based feature aggregation. We compare the proposed methodology on several descriptors, and show that the network outperforms conventional methods.

Abstract: Rice is a global staple crop that has a large requirement of water at various growth and developmental stages. As a matter of fact, drought can substantially reduce rice yield. The traits responsible for drought tolerance can be selected and studied to improve rice growth and yield under stress conditions. In the present study, morphological, physiological, biochemical and molecular variations between drought tolerant (PB6 and Moroberakan) and drought sensitive (Way Rarem) varieties have been evaluated. Notable differences have been observed in root morphology, root xylem number and area, stomata number, relative water content, proline content, protein and gene expression. In addition, novel automated frameworks based on computer vision algorithms have been employed for high-throughput quantification of xylem using scanning electron microscopy images. Transcriptome analysis has revealed variation in expression of Med37c and RSOsPR10 genes among various rice varieties. The differential proteome analysis using 2-D followed by MALDI-based identification implied the role of chitinases in drought tolerance. The information generated from computational/digital image analysis as well as biochemical studies can contribute significantly towards the developing field of rice phenomics.

Abstract: High-throughput identification of digital traits encapsulating the changes in plant’s internal structure under drought stress, based on hyperspectral imaging (HSI) is a challenging task. This is due to the high spectral and spatial resolution of HSI data and lack of labelled data. Therefore, this work proposes a novel framework for phenotypic discovery based on autoencoders, which is trained using Simple Linear Iterative Clustering (SLIC) superpixels. The distinctive archetypes from the learnt digital traits are selected using simplex volume maximisation (SiVM). Their accumulation maps are employed to reveal differential drought responses of wheat cultivars based on t-distributed stochastic neighbour embedding (t-SNE) and the separability is quantified using cluster silhouette index. Unlike prior methods using raw pixels or feature vectors computed by fusing predefined indices as phenotypic traits, our proposed framework shows potential by separating the plant responses into three classes with a finer granularity. This capability shows the potential of our framework for the discovery of data-driven phenotypes to quantify drought stress responses.

Abstract: Wayne Rasband of NIH has created ImageJ, an open source Java-written program that is now at version 1.31 and is used for many imaging applications, including those that that span the gamut from skin analysis to neuroscience. ImageJ is in the public domain and runs on any operating system (OS). ImageJ is easy to use and can do many imaging manipulations. A very large and knowledgeable group makes up the user community for ImageJ. Topics covered are imaging abilities; cross platform; image formats support as of June 2004; extensions, including macros and plug-ins; and imaging library. NIH reports tens of thousands of downloads at a rate of about 24,000 per month currently. ImageJ can read most of the widely used and significant formats used in biomedical images. Manipulations supported are read/write of image files and operations on separate pixels, image regions, entire images, and volumes (stacks in ImageJ). Basic operations supported include convolution, edge detection, Fourier transform, histogram and particle analyses, editing and color manipulation, and more advanced operations, as well as visualization. For assistance in using ImageJ, users e-mail each other, and the user base is highly knowledgeable and will answer requests on the mailing list. A thorough manual with many examples and illustrations has been written by Tony Collins of the Wright Cell Imaging Facility at Toronto Western Research Institute and is available, along with other listed resources, via the Web.

Abstract: A new approach toward target representation and localization, the central component in visual tracking of nonrigid objects, is proposed. The feature histogram-based target representations are regularized by spatial masking with an isotropic kernel. The masking induces spatially-smooth similarity functions suitable for gradient-based optimization, hence, the target localization problem can be formulated using the basin of attraction of the local maxima. We employ a metric derived from the Bhattacharyya coefficient as similarity measure, and use the mean shift procedure to perform the optimization. In the presented tracking examples, the new method successfully coped with camera motion, partial occlusions, clutter, and target scale variations. Integration with motion filters and data association techniques is also discussed. We describe only a few of the potential applications: exploitation of background information, Kalman tracking using motion models, and face tracking.

Abstract: Two border following algorithms are proposed for the topological analysis of digitized binary images. The first one determines the surroundness relations among the borders of a binary image. Since the outer borders and the hole borders have a one-to-one correspondence to the connected components of 1-pixels and to the holes, respectively, the proposed algorithm yields a representation of a binary image, from which one can extract some sort of features without reconstructing the image. The second algorithm, which is a modified version of the first, follows only the outermost borders (i.e., the outer borders which are not surrounded by holes). These algorithms can be effectively used in component counting, shrinking, and topological structural analysis of binary images, when a sequential digital computer is used.

Abstract: Global agriculture is facing major challenges to ensure global food security, such as the need to breed high-yielding crops adapted to future climates and the identification of dedicated feedstock crops for biofuel production (biofuel feedstocks). Plant phenomics offers a suite of new technologies to accelerate progress in understanding gene function and environmental responses. This will enable breeders to develop new agricultural germplasm to support future agricultural production. In this review we present plant physiology in an 'omics' perspective, review some of the new high-throughput and high-resolution phenotyping tools and discuss their application to plant biology, functional genomics and crop breeding.