A Robust Generic Method for Grid Detection in White Light Microscopy Malassez Blade Images in the Context of Cell Counting
AbstractIn biology, cell counting is a primary measurement and it is usually performed manually using hemocytometers such as Malassez blades. This work is tedious and can be automated using image processing. An algorithm based on Fourier transform filtering and the Hough transform was developed for Malassez blade grid extraction. This facilitates cell segmentation and counting within the grid. For the present work, a set of 137 images with high variability was processed. Grids were accurately detected in 98% of these images.
Estimation de l’indice foliaire et de la biomasse du blé et des adventices par imagerie visible et machine learning : vers un nouvel indicateur non destructif de la compétition culture-adventices ?
National audience; Cette étude propose d’estimer précocement par imagerie deux variables clés dans la gestion des cultures et dans la compétition culture-adventices : l’indice foliaire (LAI) et la biomasse aérienne sèche (BM). Une expérimentation a été conduite au champ pendant la phase végétative d’une culture de blé. Pour chaque peuplement (culture de blé, adventices), les taux de couverture du sol par la végétation (TCc, TCw) ont été déduits du traitement d’image basé sur une technique de machine learning. LAI et BM ont été mesurés de façon destructive. Puis, une calibration a été réalisée entre TC et LAI d’une part et entre TC et BM d’autre part. Ce travail pourrait, à terme, faciliter …
Effect of high hydrostatic pressure on extraction of B-phycoerythrin from Porphyridium cruentum: Use of confocal microscopy and image processing
International audience; The aim of the study was to extract B-phycoerythrin from Porphyridium cruentum while preserving its structure. The high hydrostatic pressure treatments were chosen as extraction technology. Different methods have been used to observe the effects of the treatment: spectrophotometry and confocal laser scanning microscopy followed by image processing analysis. Image processing led to the generation of masks used for the identification of three clusters: intra, extra and intercellular. All methods showed that high hydrostatic pressure treatments between 50 and 500 MPa failed to extract B-phycoerythrin from Porphyridium cruentum cells. The fluorescence emission was negati…
Automatic Counting of Intra-Cellular Ribonucleo-Protein Aggregates in Saccharomyces cerevisiae Using a Textural Approach.
AbstractIn the context of microbiology, recent studies show the importance of ribonucleo-protein aggregates (RNPs) for the understanding of mechanisms involved in cell responses to specific environmental conditions. The assembly and disassembly of aggregates is a dynamic process, the characterization of the stage of their evolution can be performed by the evaluation of their number. The aim of this study is to propose a method to automatically determine the count of RNPs. We show that the determination of a precise count is an issue by itself and hence, we propose three textural approaches: a classical point of view using Haralick features, a frequency point of view with generalized Fourier…
Potential of visible (RGB) imagery for dynamic monitoring of nitrogen requirements in winter wheat using the innovative APPI-N method
The balance-sheet method has been widely used for decades as a reference method to calculate the amount of nitrogen (N) fertilizer to supply to winter wheat. With this method, the amount of N fertilizer is calculated at the end of the winter to support the N requirement for an estimated yield level. This method is now being questioned because it has become difficult to predict yields, given climate change and the increased presence of pests in agroecological cropping systems, resulting in greater uncertainty about the yield achieved compared to conventional systems of the past. Alternative methods, such as the innovative approach of nitrogen fertilization (APPI-N; Ravier et al., 2018), are …
Automatic Biological Cell Counting Using a Modified Gradient Hough Transform
AbstractWe present a computational method for pseudo-circular object detection and quantitative characterization in digital images, using the gradient accumulation matrix as a basic tool. This Gradient Accumulation Transform (GAT) was first introduced in 1992 by Kierkegaard and recently used by Kaytanli & Valentine. In the present article, we modify the approach by using the phase coding studied by Cicconet, and by adding a “local contributor list” (LCL) as well as a “used contributor matrix” (UCM), which allow for accurate peak detection and exploitation. These changes help make the GAT algorithm a robust and precise method to automatically detect pseudo-circular objects in a microscop…
Mesocosm evaluation of the competittive ability of common and segetal weed species against barley
In conventional cropping systems, arable weed species have always been considered undesirable because their presence can significantly reduce the yield and quality of the crop. Among the weed community, segetal weeds particularly inhabit winter cereal fields and are generally described as rare species (Jauzein, 1997). Following the observed decline in biodiversity in the field, there is a renewed interest in conserving segetal weeds as they represent an invaluable plant heritage as wild relatives of cultivated plants (Fried, 2020). The origin of the regression of these particular annual species is strongly linked to intensive agricultural practices (herbicides, fertilization) but also proba…
Reliable Detection and Smart Deletion of Malassez Counting Chamber Grid in Microscopic White Light Images for Microbiological Applications
AbstractIn biology, hemocytometers such as Malassez slides are widely used and are effective tools for counting cells manually. In a previous work, a robust algorithm was developed for grid extraction in Malassez slide images. This algorithm was evaluated on a set of 135 images and grids were accurately detected in most cases, but there remained failures for the most difficult images. In this work, we present an optimization of this algorithm that allows for 100% grid detection and a 25% improvement in grid positioning accuracy. These improvements make the algorithm fully reliable for grid detection. This optimization also allows complete erasing of the grid without altering the cells, whic…