Microscopy Conference 2023

Prof. Dr.

Session chairs

Prof.

Machine learning and pollen Identification: CNN for identification of Ambrosia among late season pollen

Abstract text (incl. figure legends and references) Introduction In the past years Convolutional Neuronal Networks (CNN) have reached a state where this software has the potential to simplify and accelerate the processing of images and data. A promising field is aerobiology, where the current standard is to sample particles and make a slide for Light Microscopic inspection by eye. Microscope Image Analysis System (MIAS®) enables to digitize samples on a slide as a series of high quality images. A logical next step is implementing CNN for the identification of the particles. After successful tests on tree pollen the identification of Ambrosia among late season pollen was the next application for our CNN.Ambrosia artemisiifolia has been seen as an aggressive invasive species in Germany over the last decade and been object to ongoing surveys in Europe. Materials and Methods The MIAS® relies on Standard methods for the sampling and staining of samples. Operating our automatic light microscope aeroIScope® simulates the routine particle counting: It produces a series of adjacent images and the details of the particles are documented by images from adjoining focus levels. Samples for the training of the CNN, the inspection of these images is supported by a tool named Marker, which enables efficiently labelling and image-related listing of structures.The CNN of MIAS® was trained to discriminate Ambrosia pollen against pollen from relevant late season species at an accuracy over 80%. Results: The CNN reached an identification accuracy in comparing pollen of Ambrosia (99%), Amaranth (96%), Brassica (95%), Plantago (84%), Rumex (100%) and Urtica (100%), using a training set of only a few hundred pollen images for each species. Results and Discussion Using CNN in MIAS® makes the analysis of pollen objective and effective: Pollen from a daily slide are recognized in few minutes. - Based on a series of adjacent images provided by the aeroScope® - photographic documentation including clear relation to position on the slide is provided - comfortable evaluation anywhere is possible - a quality suitable for digital analysis to detect and classify distinct pollen is reached. The digitalization of aerobiological samples makes it possible to share, conserve and compare these samples. Conclusions With further adjustments and training the CNN should be capable of facilitating and accelerating the analysis of large quantities of imigary. References Campesato, Oswald; "Artificial Intelligence - Machine Learning and Deep Learning"; Mercury Learning and Information; Dulles, Virgina; 2020. Ansari, Shamshad; "Building Computer Vision Applications Using Artificial Neural Networks"; Apress Medi LLC, Springer Science+Business Media New York; 2020. Campesato, Oswald; "TensorFlow 2.0: Pocket Primer"; Mercury Learning and Information; Dulles, Virgina; 2020. Gulli, Antonio; Kapoor, Amita; Pal, Sujit ;"Deep Learning with TensorFlow 2 and Keras: Regression, ConvNets, GANs, RNNs, NLP, and more with TensorFlow 2 and the Keras API, 2nd Edition"; Packt Publishing; 2019. Starfinger, Uwe; &quot;The Action Programme Ambrosia in Germany – State of the art and future prospects&quot;, Julius Kühn Institut, Bundesforschungsinstitut für Kulturpflanzen; Quedlinburg, Germany; 2012. Beate Alberternst, Stefan Nawrath und Frank Klingenstein; &quot; Biology, distribution and pathways of introduction of Ambrosia artemisiifolia in Germany and assessment from a nature conservation point of view&quot;; Eugen Ulmer KG, Stuttgart, Germany; 2006.

LS 3: Imaging of large volumes and plastic section tomography

LS 4: Image analysis of large data sets

Poster

Influence of segmentation protocols on simulations based on 3D X-ray microscopy images

Abstract text (incl. figure legends and references) The study of filtration properties, such as solvent permeability and diffusion through a material, is an essential step in developing efficient filter elements. Aiming at flexible and efficient filter production processes, fluid flow simulations can complement the empirical determination of these parameters with help from 3D X-ray images of real filters. Phase-contrast X-ray microscopy imaging is a technique suitable for imaging materials with low electron density. However, the segmentation of phase-contrast images is not trivial, frequently leading to unreliable results. Here, we analyzed a fibrous matrix of a filter material using different phase-contrast X-ray imaging conditions and evaluated the effects of a semi-automatic segmentation protocol in the simulation of solvent permeability and diffusion properties. We observed that the segmentation strongly influences the results output, causing significant variations in the values of diffusion coefficients (k) and apparent molecular diffusivity. Therefore, before running the simulations, there is a need to apply segmentation protocols that can be validated by other imaging techniques to guarantee relevant results.

High-throughput transmission electron microscopy for screening yeast deletion mutants

Abstract text (incl. figure legends and references) The yeast Saccharomyces cerevisiae is a well-established model organism for cell biological research. The availability of large mutant collections, the fast growth and easy handling make it ideally suited for systematic large-scale analyses. However, sample preparation of yeast cells for transmission electron microscopy (TEM) of thin sections is a time-consuming process, limiting the feasibility of large-scale screening for yeast mutants with altered ultrastructure by TEM. Here, we present two approaches to reduce the time necessary for conducting a systematic TEM-based screen of yeast deletion mutants. First, we apply pooling of ten different strains to increase the amount of mutants that can be simultaneously screened for a specific ultrastructural phenotype. In a proof of concept experiment, we were able to reliably identify samples containing mutants with altered mitochondrial ultrastructure. Second, we employ a microwave-assisted protocol to accelerate sample preparation. This reduces the time requirement for chemical fixation and Epon embedding to less than 24 hours, making it ideally suited when dealing with a high number of samples. Taken together, both approaches facilitate large-scale screening of yeast deletion mutants.

LS 7: Advances in sample preparation

Step-by-step pre-processing of 3D SEM images of neurons

Abstract text (incl. figure legends and references) Introduction Traditionally, neuron reconstructions from serial EM micrographs and synapses localizations are done manually, which is extremely time consuming. Currently used, semi-automatic selection tools for segmenting are faster compared to manual selection. In order for those tools to work properly, prior to segmentation, noise reduction is necessary, while keeping membrane integrity and structural features of synapses preserved at the same time. Objectives Here we introduce a solution, which includes pre-processing of electron micrographs. Pre-processed images are suitable for the use of more advanced, fast selecting tools, which significantly shorten the amount of time needed for segmentation. Materials and methods Stacks of serial electron micrographs of identified neurons of the locust, Locusta migratoria were produced by serial block face scanning electron microscopy. This was followed by multiple image processing steps on these stacks by Image J software. First preprocessing step: A histogram matching algorithm was used to homogenize the initial brightness levels within the stack, followed by a low pass Fourier transform band-filter to isolate small structures like cell-membranes. Further a rolling ball algorithm was used to give the cell membranes a higher contrast and thereby the stack was set up for an automated Otsu threshold. The thresholded stacks were analyzed with the particle analyzer implemented in ImageJ to filter out small irregular components present in the original stack not belonging to the cell membranes. In parallel, the particle analyzer was used once more with settings that enabled keeping the large particles such as mitochondria. The result was subtracted from the result of the first round with the particle analyzer. Second preprocessing step: mitochondria, representing an obstacle during and after segmentation, where the target. For this purpose the histogram - matched stacks were filtered with a median filter after a contrasting step. Finally a Huang´s auto threshold was used to get a binary image (that contained the mitochondria) which was subtracted from the first preprocessing step. Results The first step successfully removed many structures inside the cells, but mitochondria attached to the membranes were still visible, compromising the results of the following segmenting steps. This can slow down fast selection tools subsequently used for segmentation (such as &quot;Blow&quot; in Amira). (Fig. 1B) During the second preprocessing step most of the structures inside the cells were deleted. However, at certain locations the membranes appeared discontinuous. Nevertheless combining both steps with fast selection tools significantly enhanced segmentation efficiency compared to a traditional manual approach. (Fig. 1C) Conclusion Pre-processing can improve the accuracy and efficiency of segmenting algorithms.

Membrane analysis toolkit: a quantitative way to analyse protein lipid mixtures from cryo-EM images

Abstract text (incl. figure legends and references) Cryo-EM is a powerful tool to study protein membrane interactions as it delivers high-resolution images of vitrified macromolecules including biological membranes. The quantitative analysis of protein-induced effects on the membrane structure is a challenging and time-consuming task as they are not amenable to established single-particle image reconstruction techniques. However, due to the high contrast of phospholipid bilayers, the images are suitable for detailed analysis and can yield characteristic lipid features and membrane shapes. Currently, localisation of such membrane structures and the extraction of their features is often performed interactively and is, therefore, subjective and a time-consuming task. Here we present the &quot;membrane analysis toolkit&quot;, a toolkit currently in development which aims to automate the membrane analysis and facilitate quantitative comparison of large functional datasets, e.g capturing the variations such as protein mutations and lipid compositions. The membrane structures are localized using convolutional neural networks and sequentially analysed by a variety of image processing techniques. Typical determined features are membrane thickness, curvature and distance structures along the membranes in addition to shape information about the continuous membrane structures like total area and shape classification. The membrane analysis toolkit can be used for any sample containing lipid bilayers and can lead to a more quantitative understanding of membrane-active proteins or other environmental influences.

PS 12
Poster session LS 4: Image analysis of large data sets

Appointment

Session chairs

Programme

PS 12Poster session LS 4: Image analysis of large data sets

Appointment

Session chairs

Programme

PS 12
Poster session LS 4: Image analysis of large data sets