Aerial imagery is regularly used by crop researchers, growers and farmers to monitor crops during the growing season. To extract meaningful information from large-scale aerial images collected from the field, high-throughput phenotypic analysis solutions are required, which not only produce high-quality measures of key crop traits, but also support professionals to make prompt and reliable crop management decisions. Here, we report AirSurf, an automated and open-source analytic platform that combines modern computer vision, up-to-date machine learning, and modular software engineering in order to measure yield-related phenotypes from ultra-large aerial imagery. To quantify millions of in-field lettuces acquired by fixed-wing light aircrafts equipped with normalised difference vegetation index (NDVI) sensors, we customised AirSurf by combining computer vision algorithms and a deep-learning classifier trained with over 100,000 labelled lettuce signals. The tailored platform, AirSurf- Lettuce , is capable of scoring and categorising iceberg lettuces with high accuracy (>98%). Furthermore, novel analysis functions have been developed to map lettuce size distribution across the field, based on which associated global positioning system (GPS) tagged harvest regions have been identified to enable growers and farmers to conduct precision agricultural practises in order to improve the actual yield as well as crop marketability before the harvest.

Recently, high-throughput sequencing (HTS) has revealed compelling details about the small RNA (sRNA) population in eukaryotes. These 20 to 25 nt noncoding RNAs can influence gene expression by acting as guides for the sequence-specific regulatory mechanism known as RNA silencing. The increase in sequencing depth and number of samples per project enables a better understanding of the role sRNAs play by facilitating the study of expression patterns. However, the intricacy of the biological hypotheses coupled with a lack of appropriate tools often leads to inadequate mining of the available data and thus, an incomplete description of the biological mechanisms involved. To enable a comprehensive study of differential expression in sRNA data sets, we present a new interactive pipeline that guides researchers through the various stages of data preprocessing and analysis. This includes various tools, some of which we specifically developed for sRNA analysis, for quality checking and normalization of sRNA samples as well as tools for the detection of differentially expressed sRNAs and identification of the resulting expression patterns. The pipeline is available within the UEA sRNA Workbench, a user-friendly software package for the processing of sRNA data sets. We demonstrate the use of the pipeline on a H. sapiens data set; additional examples on a B. terrestris data set and on an A. thaliana data set are described in the Supplemental Information. A comparison with existing approaches is also included, which exemplifies some of the issues that need to be addressed for sRNA analysis and how the new pipeline may be used to do this.

BackgroundPlants demonstrate dynamic growth phenotypes that are determined by genetic and environmental factors. Phenotypic analysis of growth features over time is a key approach to understand how plants interact with environmental change as well as respond to different treatments. Although the importance of measuring dynamic growth traits is widely recognised, available open software tools are limited in terms of batch image processing, multiple traits analyses, software usability and cross-referencing results between experiments, making automated phenotypic analysis problematic.ResultsHere, we present Leaf-GP (Growth Phenotypes), an easy-to-use and open software application that can be executed on different computing platforms. To facilitate diverse scientific communities, we provide three software versions, including a graphic user interface (GUI) for personal computer (PC) users, a command-line interface for high-performance computer (HPC) users, and a well-commented interactive Jupyter Notebook (also known as the iPython Notebook) for computational biologists and computer scientists. The software is capable of extracting multiple growth traits automatically from large image datasets. We have utilised it in Arabidopsis thaliana and wheat (Triticum aestivum) growth studies at the Norwich Research Park (NRP, UK). By quantifying a number of growth phenotypes over time, we have identified diverse plant growth patterns between different genotypes under several experimental conditions. As Leaf-GP has been evaluated with noisy image series acquired by different imaging devices (e.g. smartphones and digital cameras) and still produced reliable biological outputs, we therefore believe that our automated analysis workflow and customised computer vision based feature extraction software implementation can facilitate a broader plant research community for their growth and development studies. Furthermore, because we implemented Leaf-GP based on open Python-based computer vision, image analysis and machine learning libraries, we believe that our software not only can contribute to biological research, but also demonstrates how to utilise existing open numeric and scientific libraries (e.g. Scikit-image, OpenCV, SciPy and Scikit-learn) to build sound plant phenomics analytic solutions, in a efficient and effective way.ConclusionsLeaf-GP is a sophisticated software application that provides three approaches to quantify growth phenotypes from large image series. We demonstrate its usefulness and high accuracy based on two biological applications: (1) the quantification of growth traits for Arabidopsis genotypes under two temperature conditions; and (2) measuring wheat growth in the glasshouse over time. The software is easy-to-use and cross-platform, which can be executed on Mac OS, Windows and HPC, with open Python-based scientific libraries preinstalled. Our work presents the advancement of how to integrate computer vision, image analysis, machine learning and software engineering in plant phenomics software implementatio...

This paper presents the preclinical evaluation of a novel immobilization system for patients undergoing external beam radiation treatment of head and neck tumors. An immobilization mask is manufactured directly from a 3-D model, built using the CT data routinely acquired for treatment planning so there is no need to take plaster of Paris moulds. Research suggests that many patients find the mould room visit distressing and so rapid prototyping could potentially improve the overall patient experience. Evaluation of a computer model of the immobilization system using an anthropomorphic phantom shows that >99% of vertices are within a tolerance of ±0.2 mm. Hausdorff distance was used to analyze CT slices obtained by rescanning the phantom with a printed mask in position. These results show that for >80% of the slices the median "worse-case" tolerance is approximately 4 mm. These measurements suggest that printed masks can achieve similar levels of immobilization to those of systems currently in clinical use.

RNA silencing (RNA interference, RNAi) is a complex, highly conserved mechanism mediated by short, typically 20-24 nt in length, noncoding RNAs known as small RNAs (sRNAs). They act as guides for the sequence-specific transcriptional and posttranscriptional regulation of target mRNAs and play a key role in the fine-tuning of biological processes such as growth, response to stresses, or defense mechanism.High-throughput sequencing (HTS) technologies are employed to capture the expression levels of sRNA populations. The processing of the resulting big data sets facilitated the computational analysis of the sRNA patterns of variation within biological samples such as time point experiments, tissue series or various treatments. Rapid technological advances enable larger experiments, often with biological replicates leading to a vast amount of raw data. As a result, in this fast-evolving field, the existing methods for sequence characterization and prediction of interaction (regulatory) networks periodically require adapting or in extreme cases, a complete redesign to cope with the data deluge. In addition, the presence of numerous tools focused only on particular steps of HTS analysis hinders the systematic parsing of the results and their interpretation.The UEA small RNA Workbench (v1-4), described in this chapter, provides a user-friendly, modular, interactive analysis in the form of a suite of computational tools designed to process and mine sRNA datasets for interesting characteristics that can be linked back to the observed phenotypes. First, we show how to preprocess the raw sequencing output and prepare it for downstream analysis. Then we review some quality checks that can be used as a first indication of sources of variability between samples. Next we show how the Workbench can provide a comparison of the effects of different normalization approaches on the distributions of expression, enhanced methods for the identification of differentially expressed transcripts and a summary of their corresponding patterns. Finally we describe individual analysis tools such as PAREsnip, for the analysis of PARE (degradome) data or CoLIde for the identification of sRNA loci based on their expression patterns and the visualization of the results using the software. We illustrate the features of the UEA sRNA Workbench on Arabidopsis thaliana and Homo sapiens datasets.

No abstract

No abstract

To create traffic simulations of high visual-fidelity, each road needs to be designed and modelled in great detail to conform with the governing rules and regulations of highway design. Roads could be created manually, but this can become a time-consuming and laborious process when modelling large-scale networks. Therefore, automated techniques for generating road networks efficiently and effectively, without any prior user knowledge of road design principles and practices, is highly desirable in both urban-planning and entertainment industries. In this paper, we present a novel sketch-based tool to semi-automate the design, creation and visualisation of realistic road networks across both flat and undulating terrains. Our tool is guided by input sketches and a combination of prioritised constraints, including the curvature of roads, their inclination, and the volume of ground that would be displaced during construction. Furthermore, we present an extension to a cellular automata traffic behaviour model that utilises more accurate car-following rules to simulate large-scale networks with high visual-fidelity.