Search

Small extracellular vesicles (sEVs) are cell-derived vesicles of nanoscale size (~30-200 nm) that function as conveyors of information between cells, reflecting the cell of their origin and its physiological condition in their content. Valuable information on the shape and even on the composition of individual sEVs can be recorded using transmission electron microscopy (TEM). Unfortunately, sample preparation for TEM image acquisition is a complex procedure, which often leads to noisy images and renders automatic quantification of sEVs an extremely difficult task. We present a completely deep-learning-based pipeline for the segmentation of sEVs in TEM images. Our method applies a residual convolutional neural network to obtain fine masks and use the Radon transform for splitting clustered sEVs. Using three manually annotated datasets that cover a natural variability typical for sEV studies, we show that the proposed method outperforms two different state-of-the-art approaches in terms of detection and segmentation performance. Furthermore, the diameter and roundness of the segmented vesicles are estimated with an error of less than 10%, which supports the high potential of our method in biological applications. We want to acknowledge the support of NVIDIA Corporation with the donation of the Titan X (Pascal) GPU used for this research. This work was supported by the Spanish Ministry of Economy and Competitiveness (TEC2013-48552-C2-1-R, TEC2015-73064-EXP, TEC2016-78052-R) (EGM-AMB), a 2017 Leonardo Grant for Researchers and Cultural Creators, BBVA Foundation (EGM-AMB), and the Czech Science Foundation (GA17-05048S)(MM-PM) and (GJ17-11776Y) (AK-VP).

We present a 3D bioimage analysis workflow to quantitatively analyze single, actin-stained cells with filopodial protrusions of diverse structural and temporal attributes, such as number, length, thickness, level of branching, and lifetime, in time-lapse confocal microscopy image data. Our workflow makes use of convolutional neural networks trained using real as well as synthetic image data, to segment the cell volumes with highly heterogeneous fluorescence intensity levels and to detect individual filopodial protrusions, followed by a constrained nearest-neighbor tracking algorithm to obtain valuable information about the spatio-temporal evolution of individual filopodia. We validated the workflow using real and synthetic 3-D time-lapse sequences of lung adenocarcinoma cells of three morphologically distinct filopodial phenotypes and show that it achieves reliable segmentation and tracking performance, providing a robust, reproducible and less time-consuming alternative to manual analysis of the 3D+t image data.

Motivation Objective assessment of bioimage analysis methods is an essential step towards understanding their robustness and parameter sensitivity, calling for the availability of heterogeneous bioimage datasets accompanied by their reference annotations. Because manual annotations are known to be arduous, highly subjective and barely reproducible, numerous simulators have emerged over past decades, generating synthetic bioimage datasets complemented with inherent reference annotations. However, the installation and configuration of these tools generally constitutes a barrier to their widespread use. Results We present a modern, modular web-interface, CytoPacq, to facilitate the generation of synthetic benchmark datasets relevant for multi-dimensional cell imaging. CytoPacq poses a user-friendly graphical interface with contextual tooltips and currently allows a comfortable access to various cell simulation systems of fluorescence microscopy, which have already been recognized and used by the scientific community, in a straightforward and self-contained form. Availability and implementation CytoPacq is a publicly available online service running at https://cbia.fi.muni.cz/simulator. More information about it as well as examples of generated bioimage datasets are available directly through the web-interface. Supplementary information Supplementary data are available at Bioinformatics online.

Development, parameter tuning, and objective benchmarking of bioimage analysis workflows heavily rely on the availability of diverse bioimage datasets accompanied by reference annotations. In this paper, we present a new benchmark dataset, FiloData3D, designed for in-depth performance assessments of fully 3D filopodium segmentation and tracking algorithms that emerged recently in the field. It consists of 180 synthetic, fully annotated, 3D time-lapse sequences of single lung cancer cells, combining different cell shapes, signal-to-noise ratios, and anisotropy ratios, which are the well-known factors that influence the quality of segmentation and tracking results. Using FiloData3D, we show that the number of filopodia and their lengths extracted are significantly underestimated in the case of traditional 2D protocols that prevail in daily practice compared to fully 3D measurements, calling for a procedural change in filopodial analyses of 3D+t bioimage data.

Automated image analysis has become key to extract quantitative information from scientific microscopy bioimages, but the methods involved are now often so refined that they can no longer be unambiguously described using written protocols. We introduce BIAFLOWS, a software tool with web services and a user interface specifically designed to document, interface, reproducibly deploy, and benchmark image analysis workflows. BIAFLOWS allows image analysis workflows to be compared fairly and shared in a reproducible manner, safeguarding research results and promoting the highest quality standards in bioimage analysis. A curated instance of BIAFLOWS is available online; it is currently populated with 34 workflows that can be triggered to process image datasets illustrating 15 common bioimage analysis problems organized in 9 major classes. As a complete case study, the open benchmarking of 7 nuclei segmentation workflows, including classical and deep learning techniques, was performed on this online instance. All the results presented can be reproduced online.

Labeled training images of high quality are required for developing well-working analysis pipelines. This is, of course, also true for biological image data, where such labels are usually hard to get. We distinguish human labels (gold corpora) and labels generated by computer algorithms (silver corpora). A naturally arising problem is to merge multiple corpora into larger bodies of labeled training datasets. While fusion of labels in static images is already an established field, dealing with labels in time-lapse image data remains to be explored. Obtaining a gold corpus for segmentation is usually very time-consuming and hence expensive. For this reason, gold corpora for object tracking often use object detection markers instead of dense segmentations. If dense segmentations of tracked objects are desired later on, an automatic merge of the detection-based gold corpus with (silver) corpora of the individual time points for segmentation will be necessary. Here we present such an automatic merging system and demonstrate its utility on corpora from the Cell Tracking Challenge. We additionally release all label fusion algorithms as freely available and open plugins for Fiji (https://github.com/xulman/CTC-FijiPlugins).

Extracellular vesicles (EVs) function as important conveyers of information between cells and thus can be exploited as drug delivery systems or disease biomarkers. Transmission electron microscopy (TEM) remains the gold standard method for visualisation of EVs, however the analysis of individual EVs in TEM images is time-consuming if performed manually. Therefore, we present here a software tool for computer-assisted evaluation of EVs in TEM images. TEM ExosomeAnalyzer detects EVs based on their shape and edge contrast criteria and subsequently analyses their size and roundness. The software tool is compatible with common negative staining protocols and isolation methods used in the field of EV research; even with challenging TEM images (EVs both lighter and darker than the background, images containing artefacts or precipitated stain, etc.). If the fully-automatic analysis fails to produce correct results, users can promptly adjust the detected seeds of EVs as well as their boundaries manually. The performance of our tool was evaluated for three different modes with variable levels of human interaction, using two datasets with various heterogeneity. The semi-automatic mode analyses EVs with high success rate in the homogenous dataset (F1 score 0.9094, Jaccard coefficient 0.8218) as well as in the highly heterogeneous dataset containing EVs isolated from cell culture medium and patient samples (F1 score 0.7619, Jaccard coefficient 0.7553). Moreover, the extracted size distribution profiles of EVs isolated from malignant ascites of ovarian cancer patients overlap with those derived by cryo-EM and are comparable to NTA- and TRPS-derived data. In summary, TEM ExosomeAnalyzer is an easy-to-use software tool for evaluation of many types of vesicular microparticles and is available at http://cbia.fi.muni.cz/exosome-analyzer free of charge for non-commercial and research purposes. The web page contains also detailed description how to use the software tool including a video tutorial.

Summary Image analysis is key to extracting quantitative information from scientific microscopy images, but the methods involved are now often so refined that they can no longer be unambiguously described by written protocols. We introduce BIAFLOWS, an open-source web tool enabling to reproducibly deploy and benchmark bioimage analysis workflows coming from any software ecosystem. A curated instance of BIAFLOWS populated with 34 image analysis workflows and 15 microscopy image datasets recapitulating common bioimage analysis problems is available online. The workflows can be launched and assessed remotely by comparing their performance visually and according to standard benchmark metrics. We illustrated these features by comparing seven nuclei segmentation workflows, including deep-learning methods. BIAFLOWS enables to benchmark and share bioimage analysis workflows, hence safeguarding research results and promoting high-quality standards in image analysis. The platform is thoroughly documented and ready to gather annotated microscopy datasets and workflows contributed by the bioimaging community., Highlights • Image analysis is inescapable in extracting quantitative data from scientific images • It can be difficult to deploy and apply state-of-the-art image analysis methods • Comparing heterogeneous image analysis methods is tedious and error prone • We introduce a platform to deploy and fairly compare image analysis workflows, The Bigger Picture Image analysis is currently one of the major hurdles in the bioimaging chain, especially for large datasets. BIAFLOWS seeds the ground for virtual access to image analysis workflows running in high-performance computing environments. Providing a broader access to state-of-the-art image analysis is expected to have a strong impact on research in biology, and in other fields where image analysis is a critical step in extracting scientific results from images. BIAFLOWS could also be adopted as a federated platform to publish microscopy images together with the workflows that were used to extract scientific data from these images. This is a milestone of open science that will help to accelerate scientific progress by fostering collaborative practices., While image analysis is becoming inescapable in the extraction of quantitative information from scientific images, it is currently challenging for life scientists to find, test, and compare state-of-the-art image analysis methods compatible with their own microscopy images. It is also difficult and time consuming for algorithm developers to validate and reproducibly share their methods. BIAFLOWS is a web platform addressing these needs. It can be used as a local solution or through an immediately accessible and curated online instance.

Complementing collections of 3D time-lapse image data with comprehensive manual annotations is an extremely laborious and often impracticable task, which hinders objective benchmarking of bioimage analysis workflows as well as training of widespread deep-learning-based approaches. In this paper, we present a novel simulation system capable of generating synthetic 3D time-lapse sequences of multiple mutually interacting cells with filopodial protrusions, accompanied by inherently generated reference annotations, in order to stimulate the development of fully 3D bioimage analysis workflows for filopodium segmentation and tracking in complex scenarios with multiple mutually interacting cells. The system integrates its predecessor, which was designed for single-cell, collision-unaware scenarios only, with proactive, mechanics-based handling of collisions between multiple filopodia, multiple cell bodies, or their combinations. We demonstrate its potential on two generated 3D time-lapse sequences of multiple lung cancer cells with curvilinear filopodia, which visually resemble confocal fluorescence microscopy image data.

We present the architecture, training strategy and evaluation of a convolutional neural network (CNN) designed for the segmentation of actin-stained cells in 3D+t confocal microscopy image data. The segmentation performance of the CNN is evaluated using time-lapse sequences of lung adenocarcinoma cells with three genetically distinct variants of the tubulin adaptor protein, a key protein in the process of assembly of the cell cytoskeleton, displaying three different phenotypes in regards to the morphology of the cells and in particular, to the number and length of filopodial structures. We show that the CNN significantly outperforms a baseline method based on the minimization of the Chan-Vese model using graph cuts, and we discuss the inherent benefits of using the CNN over the baseline method.

We present a combined report on the results of three editions of the Cell Tracking Challenge, an ongoing initiative aimed at promoting the development and objective evaluation of cell segmentation and tracking algorithms. With 21 participating algorithms and a data repository consisting of 13 data sets from various microscopy modalities, the challenge displays today's state-of-the-art methodology in the field. We analyzed the challenge results using performance measures for segmentation and tracking that rank all participating methods. We also analyzed the performance of all of the algorithms in terms of biological measures and practical usability. Although some methods scored high in all technical aspects, none obtained fully correct solutions. We found that methods that either take prior information into account using learning strategies or analyze cells in a global spatiotemporal video context performed better than other methods under the segmentation and tracking scenarios included in the challenge.

International audience; The existence of benchmark datasets is essential to objectively evaluate various image analysis methods. Nevertheless, manual annotations of fluorescence microscopy image data are very laborious and not often practicable, especially in the case of 3D+t experiments. In this work, we propose a simulation system capable of generating 3D time-lapse sequences of single motile cells with filopodial protrusions, accompanied by inherently generated ground truth. The system consists of three globally synchronized modules, each responsible for a separate task: the evolution of filopodia on a molecular level, linear elastic deformation of the entire cell with filopodia, and generation of realistic, time-coherent cell texture. The capability of our system is demonstrated by generating a synthetic 3D time-lapse sequence of a single lung cancer cell with two growing filopodia, visually resembling its real counterpart acquired using a confocal fluorescence microscope.

Motivation: Automatic tracking of cells in multidimensional time-lapse fluorescence microscopy is an important task in many biomedical applications. A novel framework for objective evaluation of cell tracking algorithms has been established under the auspices of the IEEE International Symposium on Biomedical Imaging 2013 Cell Tracking Challenge. In this article, we present the logistics, datasets, methods and results of the challenge and lay down the principles for future uses of this benchmark. Results: The main contributions of the challenge include the creation of a comprehensive video dataset repository and the definition of objective measures for comparison and ranking of the algorithms. With this benchmark, six algorithms covering a variety of segmentation and tracking paradigms have been compared and ranked based on their performance on both synthetic and real datasets. Given the diversity of the datasets, we do not declare a single winner of the challenge. Instead, we present and discuss the results for each individual dataset separately. Availability and implementation: The challenge Web site (http://www.codesolorzano.com/celltrackingchallenge) provides access to the training and competition datasets, along with the ground truth of the training videos. It also provides access to Windows and Linux executable files of the evaluation software and most of the algorithms that competed in the challenge. Contact: codesolorzano@unav.es Supplementary information: Supplementary data are available at Bioinformatics online.

Exosomes are nanosized, cell-derived vesicles that appear in different biological fluids. They attract a growing interest of the researcher community due to their important role in intercellular communication. An easy to use and reliable method for their quantification and characterization at the single-vesicle level is tremendously needed to help evaluating exosomal preparations in research as well as clinical studies. In this paper, we present a morphological method for automatic detection and segmentation of exosomes in transmission electron microscopy images. The exosome segmentation is carried out using morphological seeded watershed on gradient magnitude image, with the seeds established by applying a series of hysteresis thresholdings, followed by morphological filtering and cluster splitting. We tested the method on a diverse image data set, yielding the detection performance of slightly over 80 %.

The simulation plays an important role in biomedical image analysis as it can inherently provide large collections of image data with absolute ground truth. Compared to real image data typically annotated by some expert, the computer generated data still lacks the authenticity due to the simplifications of various natural phenomena. In this paper, we focus on simulating the photobleaching effect and the uneven illumination, being simplified or even omitted from the majority of present simulation toolkits, to considerably improve the authenticity of computer generated data.

We present a fully automatic approach to quantitatively analyze filopodia-based migration of fluorescent cells in 3D time-lapse series. The proposed method involves three steps. First, each frame of the time-lapse series is preprocessed using a steerable filter and binarized to obtain a coarse segmentation of the cell shape. Second, a sequence of morphological filters is applied on the coarse binary mask to separate the cell body from individual filopodia. Finally, their length is estimated using a geodesic distance transform. The proposed approach is validated on 3D time-lapse series of lung adenocarcinoma cells. We show that the number of filopodia and their average length can be used as a descriptor to discriminate between different phenotypes of migrating cells.

We present a fast and robust approach to tracking the evolving shape of whole fluorescent cells in time-lapse series. The proposed tracking scheme involves two steps. First, coherence-enhancing diffusion filtering is applied on each frame to reduce the amount of noise and enhance flow-like structures. Second, the cell boundaries are detected by minimizing the Chan-Vese model in the fast level set-like and graph cut frameworks. To allow simultaneous tracking of multiple cells over time, both frameworks have been integrated with a topological prior exploiting the object indication function. The potential of the proposed tracking scheme and the advantages and disadvantages of both frameworks are demonstrated on 2-D and 3-D time-lapse series of rat adipose-derived mesenchymal stem cells and human lung squamous cell carcinoma cells, respectively.

We present a fast and robust approach to tracking whole fluorescent cells in time-lapse series. The proposed tracking scheme involves two steps. First, coherence-enhancing diffusion filtering is applied on each frame to reduce the amount of noise and enhance flow-like structures. Second, the enhanced cell boundaries are detected by minimizing the Chan-Vese model in a fast level set-like framework. To allow simultaneous tracking of multiple cells over time, the contour evolution has been integrated with a topological prior exploiting the object indication function. Preliminary tracking experiments on 2D time-lapse series of GFP-transfected adipose-derived stem cells demonstrate high accuracy and short execution times.

This paper describes free software (called Acquiarium, http://cbia.fi.muni.cz/acquiarium.html) for carrying out the common pipeline of many spatial cell studies using fluorescence microscopy. It addresses image capture, raw image correction, image segmentation, the quantification and spatial arrangement of segmented objects, volume rendering, and statistical evaluation. The software is designed for the easy processing of a collection of many 3D images. It can be used for the analysis of a collection of 2D images or time lapse series of 2D or 3D images as well. It has a modular design and is extensible via plug-ins. The paper gives an overview of the software and its key design ideas.

Methods based on combinatorial graph cut algorithms received a lot of attention in the recent years for their robustness as well as reasonable computational demands. These methods are built upon an underlying Maximum a Posteriori estimation of Markov Random Fields and are suitable to solve accurately many different problems in image analysis, including image segmentation. In this paper we present a two-stage graph cut based model for segmentation of touching cell nuclei in fluorescence microscopy images. In the first stage voxels with very high probability of being foreground or background are found and separated by a boundary with a minimal geodesic length. In the second stage the obtained clusters are split into isolated cells by combining image gradient information and incorporated a priori knowledge about the shape of the nuclei. Moreover, these two qualities can be easily balanced using a single user parameter. Preliminary tests on real data show promising results of the method.

Image segmentation, one of the fundamental task of image processing, can be accurately solved using the level set framework. However, the computational time demands of the level set methods make them practically useless, especially for segmentation of large three-dimensional images. Many approximations have been introduced in recent years to speed up the computation of the level set methods. Although these algorithms provide favourable results, most of them were not properly tested against ground truth images. In this paper we present a comparison of three methods: the Sparse-Field method [1], Deng and Tsui's algorithm [2] and Nilsson and Heyden's algorithm [3]. Our main motivation was to compare these methods on 3D image data acquired using fluorescence microscope, but we suppose that presented results are also valid and applicable to other biomedical images like CT scans, MRI or ultrasound images. We focus on a comparison of the method accuracy, speed and ability to detect several objects located close to each other for both 2D and 3D images. Furthermore, since the input data of our experiments are artificially generated, we are able to compare obtained segmentation results with ground truth images.