Automated Processing of Imaging Data through Multi-tiered Classification of Biological Structures Illustrated Using Caenorhabditis elegans

Quantitative imaging has become a vital technique in biological discovery and clinical diagnostics; a plethora of tools have recently been developed to enable new and accelerated forms of biological investigation. Increasingly, the capacity for high-throughput experimentation provided by new imaging modalities, contrast techniques, microscopy tools, microfluidics and computer controlled systems shifts the experimental bottleneck from the level of physical manipulation and raw data collection to automated recognition and data processing. Yet, despite their broad importance, image analysis solutions to address these needs have been narrowly tailored. Here, we present a generalizable formulation for autonomous identification of specific biological structures that is applicable for many problems. The process flow architecture we present here utilizes standard image processing techniques and the multi-tiered application of classification models such as support vector machines (SVM). These low-level functions are readily available in a large array of image processing software packages and programming languages. Our framework is thus both easy to implement at the modular level and provides specific high-level architecture to guide the solution of more complicated image-processing problems. We demonstrate the utility of the classification routine by developing two specific classifiers as a toolset for automation and cell identification in the model organism Caenorhabditis elegans. To serve a common need for automated high-resolution imaging and behavior applications in the C. elegans research community, we contribute a ready-to-use classifier for the identification of the head of the animal under bright field imaging. Furthermore, we extend our framework to address the pervasive problem of cell-specific identification under fluorescent imaging, which is critical for biological investigation in multicellular organisms or tissues. Using these examples as a guide, we envision the broad utility of the framework for diverse problems across different length scales and imaging methods.     

Natsumushi: Image measuring software for entomological studies

Natsumushi is a free image analysis software that offers easy handling and quick measurement, designed especially for entomologists as the main users. The software enables measurement of: (i) color features of a specific region; (ii) area size; (iii) length of simple lines or polylines; and (iv) number of points or their x–y coordinates. Users can specify the region for measurement either manually or automatically by using image thresholding operations. The software is freely available at the website https://staff.aist.go.jp/t-fukatsu/Natsumushi.html .     

2dx_merge: data management and merging for 2D crystal images

Electron crystallography of membrane proteins determines the structure of membrane-reconstituted and two-dimensionally (2D) crystallized membrane proteins by low-dose imaging with the transmission electron microscope, and computer image processing. We have previously presented the software system 2dx, for user-friendly image processing of 2D crystal images. Its central component 2dx_image is based on the MRC program suite, and allows the optionally fully automatic processing of one 2D crystal image. We present here the program 2dx_merge, which assists the user in the management of a 2D crystal image processing project, and facilitates the merging of the data from multiple images. The merged dataset can be used as a reference to re-process all images, which usually improves the resolution of the final reconstruction. Image processing and merging can be applied iteratively, until convergence is reached. 2dx is available under the GNU General Public License at http://2dx.org.     

Quantitative Assessment of Lesion Characteristics and Disease Severity Using Digital Image Processing

This work describes a dedicated software which detects and characterizes disease lesions on leaves to provide data on the number and type of lesions and the percentage of leaf area diseased (severity). The software, written in C²⁺, can be used with a standard computer in combination with a colour CCD camera and a frame grabber for image acquisition. The usefulness and adaptability of the software was evaluated using two foliar diseases, Alternaria blight of sunflower and oat leaf rust (Puccinia coronata f.sp. avenae), which differ in symptoms. Using image segmentation and classification techniques, the software discriminated disease symptoms from the healthy leaf area. The number and size of lesions and severity, obtained using the image processing software, were compared with those calculated using a software planimeter or visual assessment. Significant linear relationships between planimeter and the imaging software were obtained for lesion number and severity in oat leaf rust and for severity in sunflower blight. Artefacts, mistakenly classified as blight lesions by the imaging software resulted in an over-estimation of the number of lesions. Future research is aimed at improving accuracy through better illumination during image capture. A dedicated, compact and portable hardware is currently being developed for field use as a self-contained device for disease assessment.     

Automated Detection and Analysis of Ca2+ Sparks in x-y Image Stacks Using a Thresholding Algorithm Implemented within the Open-Source Image Analysis Platform ImageJ

Previous studies have used analysis of Ca²⁺ sparks extensively to investigate both normal and pathological Ca²⁺ regulation in cardiac myocytes. The great majority of these studies used line-scan confocal imaging. In part, this is because the development of open-source software for automatic detection of Ca²⁺ sparks in line-scan images has greatly simplified data analysis. A disadvantage of line-scan imaging is that data are collected from a single row of pixels, representing only a small fraction of the cell, and in many instances x-y confocal imaging is preferable. However, the limited availability of software for Ca²⁺ spark analysis in two-dimensional x-y image stacks presents an obstacle to its wider application. This study describes the development and characterization of software to enable automatic detection and analysis of Ca²⁺ sparks within x-y image stacks, implemented as a plugin within the open-source image analysis platform ImageJ. The program includes methods to enable precise identification of cells within confocal fluorescence images, compensation for changes in background fluorescence, and options that allow exclusion of events based on spatial characteristics.     

Automated Detection and Analysis of Ca Sparks in x-y Image Stacks Using a Thresholding Algorithm Implemented within the Open-Source Image Analysis Platform ImageJ

Previous studies have used analysis of Ca²⁺ sparks extensively to investigate both normal and pathological Ca²⁺ regulation in cardiac myocytes. The great majority of these studies used line-scan confocal imaging. In part, this is because the development of open-source software for automatic detection of Ca²⁺ sparks in line-scan images has greatly simplified data analysis. A disadvantage of line-scan imaging is that data are collected from a single row of pixels, representing only a small fraction of the cell, and in many instances x-y confocal imaging is preferable. However, the limited availability of software for Ca²⁺ spark analysis in two-dimensional x-y image stacks presents an obstacle to its wider application. This study describes the development and characterization of software to enable automatic detection and analysis of Ca²⁺ sparks within x-y image stacks, implemented as a plugin within the open-source image analysis platform ImageJ. The program includes methods to enable precise identification of cells within confocal fluorescence images, compensation for changes in background fluorescence, and options that allow exclusion of events based on spatial characteristics.     

WIS‐neuromath enables versatile high throughput analyses of neuronal processes

Automated analyses of neuronal morphology are important for quantifying connectivity and circuitry in vivo, as well as in high content imaging of primary neuron cultures. The currently available tools for quantification of neuronal morphology either are highly expensive commercial packages or cannot provide automated image quantifications at single cell resolution. Here, we describe a new software package called WIS‐NeuroMath, which fills this gap and provides solutions for automated measurement of neuronal processes in both in vivo and in vitro preparations. Diverse image types can be analyzed without any preprocessing, enabling automated and accurate detection of neurites followed by their quantification in a number of application modules. A cell morphology module detects cell bodies and attached neurites, providing information on neurite length, number of branches, cell body area, and other parameters for each cell. A neurite length module provides a solution for images lacking cell bodies, such as tissue sections. Finally, a ganglion explant module quantifies outgrowth by identifying neurites at different distances from the ganglion. Quantification of a diverse series of preparations with WIS‐NeuroMath provided data that were well matched with parallel analyses of the same preparations in established software packages such as MetaXpress or NeuronJ. The capabilities of WIS‐NeuroMath are demonstrated in a range of applications, including in dissociated and explant cultures and histological analyses on thin and whole‐mount sections. WIS‐NeuroMath is freely available to academic users, providing a versatile and cost‐effective range of solutions for quantifying neurite growth, branching, regeneration, or degeneration under different experimental paradigms. © 2012 Wiley Periodicals, Inc. Develop Neurobiol, 2013     

A cost-effective maize ear phenotyping platform enables rapid categorization and quantification of kernels

High-throughput phenotyping systems are powerful, dramatically changing our ability to document, measure, and detect biological phenomena. Here, we describe a cost-effective combination of a custom-built imaging platform and deep-learning-based computer vision pipeline. A minimal version of the maize (Zea mays) ear scanner was built with low-cost and readily available parts. The scanner rotates a maize ear while a digital camera captures a video of the surface of the ear, which is then digitally flattened into a two-dimensional projection. Segregating GFP and anthocyanin kernel phenotypes are clearly distinguishable in ear projections and can be manually annotated and analyzed using image analysis software. Increased throughput was attained by designing and implementing an automated kernel counting system using transfer learning and a deep learning object detection model. The computer vision model was able to rapidly assess over 390 000 kernels, identifying male-specific transmission defects across a wide range of GFP-marked mutant alleles. This includes a previously undescribed defect putatively associated with mutation of Zm00001d002824, a gene predicted to encode a vacuolar processing enzyme. Thus, by using this system, the quantification of transmission data and other ear and kernel phenotypes can be accelerated and scaled to generate large datasets for robust analyses.     

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

In 2010 approximately 68,720 melanomas will be diagnosed in the US alone, with around 8,650 resulting in death ¹. To date, the only effective treatment for melanoma remains surgical excision, therefore, the key to extended survival is early detection ^2,3. Considering the large numbers of patients diagnosed every year and the limitations in accessing specialized care quickly, the development of objective in vivo diagnostic instruments to aid the diagnosis is essential. New techniques to detect skin cancer, especially non-invasive diagnostic tools, are being explored in numerous laboratories. Along with the surgical methods, techniques such as digital photography, dermoscopy, multispectral imaging systems (MelaFind), laser-based systems (confocal scanning laser microscopy, laser doppler perfusion imaging, optical coherence tomography), ultrasound, magnetic resonance imaging, are being tested. Each technique offers unique advantages and disadvantages, many of which pose a compromise between effectiveness and accuracy versus ease of use and cost considerations. Details about these techniques and comparisons are available in the literature ⁴.Infrared (IR) imaging was shown to be a useful method to diagnose the signs of certain diseases by measuring the local skin temperature. There is a large body of evidence showing that disease or deviation from normal functioning are accompanied by changes of the temperature of the body, which again affect the temperature of the skin ^5,6. Accurate data about the temperature of the human body and skin can provide a wealth of information on the processes responsible for heat generation and thermoregulation, in particular the deviation from normal conditions, often caused by disease. However, IR imaging has not been widely recognized in medicine due to the premature use of the technology ^7,8 several decades ago, when temperature measurement accuracy and the spatial resolution were inadequate and sophisticated image processing tools were unavailable. This situation changed dramatically in the late 1990s-2000s. Advances in IR instrumentation, implementation of digital image processing algorithms and dynamic IR imaging, which enables scientists to analyze not only the spatial, but also the temporal thermal behavior of the skin ⁹, allowed breakthroughs in the field.In our research, we explore the feasibility of IR imaging, combined with theoretical and experimental studies, as a cost effective, non-invasive, in vivo optical measurement technique for tumor detection, with emphasis on the screening and early detection of melanoma ^10-13. In this study, we show data obtained in a patient study in which patients that possess a pigmented lesion with a clinical indication for biopsy are selected for imaging. We compared the difference in thermal responses between healthy and malignant tissue and compared our data with biopsy results. We concluded that the increased metabolic activity of the melanoma lesion can be detected by dynamic infrared imaging.     

An image processing system for digital chest X-ray images

This paper investigates the requirements for image processing of digital chest X-ray images. These images are conventionally recorded on film and are characterised by large size, wide dynamic range and high resolution. X-ray detection systems are now becoming available for capturing these images directly in photoelectronic-digital form. In this report, the hardware and software facilities required for handling these images are described. These facilities include high resolution digital image displays, programmable video look up tables, image stores for image capture and processing and a full range of software tools for image manipulation. Examples are given of the application of digital image processing techniques to this class of image.     

多枝柽柳年轮生长速率测量及TRGR指标优势分析

灌木对生境和气候变化具有高度敏感性,其年轮资料在认识区域环境演变过程、全球气候变化和环境保护中具有重要作用。灌木植株在生长过程中受遗传和极端环境的影响,年轮常出现偏心和不规则生长,这使得专业年轮分析软件测量的年轮宽度数据难以准确反映其整体径向生长信息。为探讨适合于寒旱区灌木年轮学研究的年轮测量指标和测量方法,研究以该区域荒漠常见植物多枝柽柳(Tamarix ramosissima Ledeb.)为研究对象,通过U-net深度学习方法,获得年轮提取训练模型,自动获取扫描轮盘各年早材区域。轮盘扫描及语义分割后的图像经GIS配准赋坐标、ENVI图像处理后,借助GIS编辑和测量工具,完成多枝柽柳各年年轮生长速率(Tree-ring growth rate, TRGR)、年轮宽度(Tree-ring width, TRW)和树木基部断面积生长增量(Basal area increment, BAI)的测量;研究基于Timesat Savitzky-Golay(S-G)滤波时间序列拟合,获取点样尺度归一化植被指数(Normalized difference vegetation index, ND...     

An image processing system for digital chest X-ray images

This paper investigates the requirements for image processing of digital chest X-ray images. These images are conventionally recorded on film and are characterised by large size, wide dynamic range and high resolution. X-ray detection systems are now becoming available for capturing these images directly in photoelectronic-digital form. In this report, the hardware and software facilities required for handling these images are described. These facilities include high resolution digital image displays, programmable video look up tables, image stores for image capture and processing and a full range of software tools for image manipulation. Examples are given of the application of digital image processing techniques to this class of image.     

An automated PCR platform with homogeneous time-resolved fluorescence detection and dry chemistry assay kits

We have developed a novel instrument platform, GenomEra, for small-scale analysis of nucleic acids. The platform combines a rapid thermal cycler, an integrated time-resolved fluorescence measurement unit, and user-friendly software for the analysis of results. Disposable low-cost plastic reaction vessels are designed specifically for the instrument and contain all of the assay-specific reagents in dry form. The appropriate assay protocol is specified on barcodes printed under the vessels and is automatically initiated by the software. Detection is based on the use of sequence-specific probes labeled with intrinsically fluorescent europium or terbium chelates and complementary quencher probes, which enable sensitive, homogeneous closed-tube assays without the risk of carryover contamination. The detection limit of the instrument (background + 3 SD) is approximately 20 pmol/L for both chelates with a dynamic range of nearly four orders of magnitude. The functionality of the platform is demonstrated with a dual-label homogeneous polymerase chain reaction (PCR) assay for the detection of Salmonella using a Magda CA Salmonella assay kit. An internal amplification control is included in each reaction to eliminate false negative results caused by PCR inhibition. Qualitative assay results are automatically interpreted by the software and are available 45 min after sample addition.     

Sensitive fluorescent quantitation of myo-inositol 1,2-cyclic phosphate and myo-inositol 1-phosphate by high-performance thin-layer chromatography

A non-radioactive micro-assay for the cyclic phosphodiesterase reaction catalyzed by Bacillus cereus phosphatidylinositol-specific phospholipase C is described. The assay involves high-performance thin-layer chromatography on silica gel to resolve the substrate (myo-inositol 1,2-cyclic phosphate) and the product (myo-inositol 1-phosphate), followed by detection with a lead tetraacetate–fluorescein stain. The quantitation of these inositol phosphates in sample spots relative to a series of standards is accomplished by analysis of the fluorescent plate image with a commercial phosphoimager and associated software. The experimental considerations for reliable quantitation of inositol monophosphates in the range of 0.1 to 50 nmol are presented.     

Determination of the filamentous cyanobacteria Planktothrix rubescens in environmental water samples using an image processing system

Cyanobacteria occur in surface waters worldwide. Many of these produce peptides and/or alkaloids, which can present a risk for animal and human health. Effective risk assessment and management requires continuous and precise observation and quantification of cyanobacterial cell densities. In this respect, quantification of filamentous Planktothrix species is problematic. The aim of this study was to develop an automated system to count filamentous Planktothrix rubescens using image processing. Furthermore, this study aimed to assess optimum sample volumes and filament density for measurement precision and to validate image processing measurement of P. rubescens for an effective risk assessment.Three environmental samples and one cultured sample of P. rubescens were collected by filtration onto nitrocellulose filters. Filament lengths were determined using fluorescence microscopy combined with an image processor. Cell density could be calculated from the resulting images. Cyanobacteria could easily be discriminated from algae via their fluorescence properties. The results were found to be independent of the mode of image acquisition. The precision of total filament length determination was dependent on the total filament length on the filter, i.e. analyses of highest precision could be expected for filters containing 2000–20,000 μm filaments per mm². When using suitable filtration volumes, the detection limits of the described method are sufficient for an effective risk assessment. To summarise, this procedure is a fast, easy and accurate method to determine cell densities of filamentous P. rubescens in water samples without costly and tedious manual handling.     

Development of real-time radioisotope imaging systems for plant nutrient uptake studies

Ionic nutrition is essential for plant development. Many techniques have been developed to image and (or) measure ionic movement in plants. Nevertheless, most of them are destructive and limit the analysis. Here, we present the development of radioisotope imaging techniques that overcome such restrictions and allow for real-time imaging of ionic movement. The first system, called macroimaging, was developed to visualize and measure ion uptake and translocation between organs at a whole-plant scale. Such a device is fully compatible with illumination of the sample. We also modified fluorescent microscopes to set up various solutions for ion uptake analysis at the microscopic level. Both systems allow numerical analysis of images and possess a wide dynamic range of detection because they are based on radioactivity.     

An artificial neural network approach to identify fungal diseases of cucumber (Cucumis sativus L.) plants using digital image processing

Nowadays, artificial intelligence solutions such as digital image processing and artificial neural networks (ANN) have become important applicable techniques in phytomonitoring and plant health detection systems. In this research, an autonomous device was designed and developed for detecting two types of fungi (Pseudoperonospora cubensis, Sphaerotheca fuliginea) that infect the cucumber (Cucumis sativus L.) plant leaves. This device was able to recognise the fungal diseases of plants by detecting their symptoms on plant leaves (downy mildew and powdery mildew). For leaves of cucumber inoculated with different spores of the fungi, it was possible to estimate the amount of hour post inoculation (HPI) by extracting leaves’ image parameters. Device included a dark chamber, a CCD digital camera, a thermal camera, a light dependent resistor lightening module and a personal computer. The proposed programme for precise disease detection was based on an image processing algorithm and ANN. Three textural features and two thermal parameters from the obtained images were measured and normalised. Performance of ANN model was tested successfully for disease recognition and detecting HPI in images using back-propagation supervised learning method and inspection data. Such this machine vision system can be used in robotic intelligent systems to achieve a modern farmer’s assistant in agricultural crop fields.