An objective comparison of cell-tracking algorithms.
Ontology highlight
ABSTRACT:
SUBMITTER: Ulman V
PROVIDER: S-EPMC5777536 | biostudies-literature | 2017 Dec
REPOSITORIES: biostudies-literature
Publications
An objective comparison of cell-tracking algorithms.
Ulman Vladimír V Maška Martin M Magnusson Klas E G KEG Ronneberger Olaf O Haubold Carsten C Harder Nathalie N Matula Pavel P Matula Petr P Svoboda David D Radojevic Miroslav M Smal Ihor I Rohr Karl K Jaldén Joakim J Blau Helen M HM Dzyubachyk Oleh O Lelieveldt Boudewijn B Xiao Pengdong P Li Yuexiang Y Cho Siu-Yeung SY Dufour Alexandre C AC Olivo-Marin Jean-Christophe JC Reyes-Aldasoro Constantino C CC Solis-Lemus Jose A JA Bensch Robert R Brox Thomas T Stegmaier Johannes J Mikut Ralf R Wolf Steffen S Hamprecht Fred A FA Esteves Tiago T Quelhas Pedro P Demirel Ömer Ö Malmström Lars L Jug Florian F Tomancak Pavel P Meijering Erik E Muñoz-Barrutia Arrate A Kozubek Michal M Ortiz-de-Solorzano Carlos C
Nature methods 20171030 12
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 trac ...[more]
Similar Datasets
Project description:MotivationAutomatic 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.ResultsThe 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 implementationThe 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.
| S-EPMC4029039 | biostudies-literature
Project description:Particle tracking is of key importance for quantitative analysis of intracellular dynamic processes from time-lapse microscopy image data. Because manually detecting and following large numbers of individual particles is not feasible, automated computational methods have been developed for these tasks by many groups. Aiming to perform an objective comparison of methods, we gathered the community and organized an open competition in which participating teams applied their own methods independently to a commonly defined data set including diverse scenarios. Performance was assessed using commonly defined measures. Although no single method performed best across all scenarios, the results revealed clear differences between the various approaches, leading to notable practical conclusions for users and developers.
| S-EPMC4131736 | biostudies-literature
Project description:We present a comprehensive analysis of the submissions to the first edition of the Endoscopy Artefact Detection challenge (EAD). Using crowd-sourcing, this initiative is a step towards understanding the limitations of existing state-of-the-art computer vision methods applied to endoscopy and promoting the development of new approaches suitable for clinical translation. Endoscopy is a routine imaging technique for the detection, diagnosis and treatment of diseases in hollow-organs; the esophagus, stomach, colon, uterus and the bladder. However the nature of these organs prevent imaged tissues to be free of imaging artefacts such as bubbles, pixel saturation, organ specularity and debris, all of which pose substantial challenges for any quantitative analysis. Consequently, the potential for improved clinical outcomes through quantitative assessment of abnormal mucosal surface observed in endoscopy videos is presently not realized accurately. The EAD challenge promotes awareness of and addresses this key bottleneck problem by investigating methods that can accurately classify, localize and segment artefacts in endoscopy frames as critical prerequisite tasks. Using a diverse curated multi-institutional, multi-modality, multi-organ dataset of video frames, the accuracy and performance of 23 algorithms were objectively ranked for artefact detection and segmentation. The ability of methods to generalize to unseen datasets was also evaluated. The best performing methods (top 15%) propose deep learning strategies to reconcile variabilities in artefact appearance with respect to size, modality, occurrence and organ type. However, no single method outperformed across all tasks. Detailed analyses reveal the shortcomings of current training strategies and highlight the need for developing new optimal metrics to accurately quantify the clinical applicability of methods.
| S-EPMC7026422 | biostudies-literature
Project description:In their operations private chauffeur companies have to solve variations of the multiple objective dial a ride problem. The number and type of restrictions make the problem extremely intricate and, when manually done, requires specialized people with a deep knowledge of the modus operandi of the company and of the environment in which the procedure takes place. Nevertheless, the scheduling can be automated through mean of computational methods, allowing to deliver solutions faster and, possible, optimized. In this context, this paper compares six algorithms applied to solving a multiple objective dial a ride problem, using data from a company mainly working in the Algarve, Portugal. The achieved results show that
| S-EPMC7304764 | biostudies-literature
Project description:UNLABELLED: BACKGROUND: Particle tracking passive microrheology relates recorded trajectories of microbeads, embedded in soft samples, to the local mechanical properties of the sample. The method requires intensive numerical data processing and tools allowing control of the calculation errors. RESULTS: We report the development of a software package collecting functions and scripts written in Python for automated and manual data processing, to extract viscoelastic information about the sample using recorded particle trajectories. The resulting program package analyzes the fundamental diffusion characteristics of particle trajectories and calculates the frequency dependent complex shear modulus using methods published in the literature. In order to increase conversion accuracy, segmentwise, double step, range-adaptive fitting and dynamic sampling algorithms are introduced to interpolate the data in a splinelike manner. CONCLUSIONS: The presented set of algorithms allows for flexible data processing for particle tracking microrheology. The package presents improved algorithms for mean square displacement estimation, controlling effects of frame loss during recording, and a novel numerical conversion method using segmentwise interpolation, decreasing the conversion error from about 100% to the order of 1%.
| S-EPMC3545843 | biostudies-other
Project description:Research on microscopy data from developing biological samples usually requires tracking individual cells over time. When cells are three-dimensionally and densely packed in a time-dependent scan of volumes, tracking results can become unreliable and uncertain. Not only are cell segmentation results often inaccurate to start with, but it also lacks a simple method to evaluate the tracking outcome. Previous cell tracking methods have been validated against benchmark data from real scans or artificial data, whose ground truth results are established by manual work or simulation. However, the wide variety of real-world data makes an exhaustive validation impossible. Established cell tracking tools often fail on new data, whose issues are also difficult to diagnose with only manual examinations. Therefore, data-independent tracking evaluation methods are desired for an explosion of microscopy data with increasing scale and resolution. In this paper, we propose the uncertainty footprint, an uncertainty quantification and visualization technique that examines nonuniformity at local convergence for an iterative evaluation process on a spatial domain supported by partially overlapping bases. We demonstrate that the patterns revealed by the uncertainty footprint indicate data processing quality in two algorithms from a typical cell tracking workflow - cell identification and association. A detailed analysis of the patterns further allows us to diagnose issues and design methods for improvements. A 4D cell tracking workflow equipped with the uncertainty footprint is capable of self diagnosis and correction for a higher accuracy than previous methods whose evaluation is limited by manual examinations.
| S-EPMC5812295 | biostudies-literature
Project description:Background and aimsBig data analytics leverage patterns in data to harvest valuable information, but are rarely implemented in clinical care. Optimising thiopurine therapy for inflammatory bowel disease [IBD] has proved difficult. Current methods using 6-thioguanine nucleotide [6-TGN] metabolites have failed in randomized controlled trials [RCTs], and have not been used to predict objective remission [OR]. Our aims were to: 1) develop machine learning algorithms [MLA] using laboratory values and age to identify patients in objective remission on thiopurines; and 2) determine whether achieving algorithm-predicted objective remission resulted in fewer clinical events per year.MethodsObjective remission was defined as the absence of objective evidence of intestinal inflammation. MLAs were developed to predict three outcomes: objective remission, non-adherence, and preferential shunting to 6-methylmercaptopurine [6-MMP]. The performance of the algorithms was evaluated using the area under the receiver operating characteristic curve [AuROC]. Clinical event rates of new steroid prescriptions, hospitalisations, and abdominal surgeries were measured.ResultsRetrospective review was performed on medical records of 1080 IBD patients on thiopurines. The AuROC for algorithm-predicted remission in the validation set was 0.79 vs 0.49 for 6-TGN. The mean number of clinical events per year in patients with sustained algorithm-predicted remission [APR] was 1.08 vs 3.95 in those that did not have sustained APR [p < 1 x 10-5]. Reductions in the individual endpoints of steroid prescriptions/year [-1.63, p < 1 x 10-5], hospitalisations/year [-1.05, p < 1 x 10-5], and surgeries/year [-0.19, p = 0.065] were seen with algorithm-predicted remission.ConclusionsA machine learning algorithm was able to identify IBD patients on thiopurines with algorithm-predicted objective remission, a state associated with significant clinical benefits, including decreased steroid prescriptions, hospitalisations, and surgeries.
| S-EPMC5881698 | biostudies-literature
Project description:BackgroundStudies on genome-wide associations help to determine the cause of many genetic diseases. Genome-wide associations typically focus on associations between single-nucleotide polymorphisms (SNPs). Genotyping every SNP in a chromosomal region for identifying genetic variation is computationally very expensive. A representative subset of SNPs, called tag SNPs, can be used to identify genetic variation. Small tag SNPs save the computation time of genotyping platform, however, there could be missing data or genotyping errors in small tag SNPs. This study aims to solve Tag SNPs selection problem using many-objective evolutionary algorithms.MethodsTag SNPs selection can be viewed as an optimization problem with some trade-offs between objectives, e.g. minimizing the number of tag SNPs and maximizing tolerance for missing data. In this study, the tag SNPs selection problem is formulated as a many-objective problem. Nondominated Sorting based Genetic Algorithm (NSGA-III), and Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D), which are Many-Objective evolutionary algorithms, have been applied and investigated for optimal tag SNPs selection. This study also investigates different initialization methods like greedy and random initialization. optimization.ResultsThe evaluation measures used for comparing results for different algorithms are Hypervolume, Range, SumMin, MinSum, Tolerance rate, and Average Hamming distance. Overall MOEA/D algorithm gives superior results as compared to other algorithms in most cases. NSGA-III outperforms NSGA-II and other compared algorithms on maximum tolerance rate, and SPEA2 outperforms all algorithms on average hamming distance.ConclusionExperimental results show that the performance of our proposed many-objective algorithms is much superior as compared to the results of existing methods. The outcomes show the advantages of greedy initialization over random initialization using NSGA-III, SPEA2, and MOEA/D to solve the tag SNPs selection as many-objective optimization problem.
| S-EPMC9731481 | biostudies-literature
Project description:Traditionally, the kinetics of DNA repair have been estimated using immunocytochemistry by labeling proteins involved in the DNA damage response (DDR) with fluorescent markers in a fixed cell assay. However, detailed knowledge of DDR dynamics across multiple cell generations cannot be obtained using a limited number of fixed cell time-points. Here we report on the dynamics of 53BP1 radiation induced foci (RIF) across multiple cell generations using live cell imaging of non-malignant human mammary epithelial cells (MCF10A) expressing histone H2B-GFP and the DNA repair protein 53BP1-mCherry. Using automatic extraction of RIF imaging features and linear programming techniques, we were able to characterize detailed RIF kinetics for 24 hours before and 24 hours after exposure to low and high doses of ionizing radiation. High-content-analysis at the single cell level over hundreds of cells allows us to quantify precisely the dose dependence of 53BP1 protein production, RIF nuclear localization and RIF movement after exposure to X-ray. Using elastic registration techniques based on the nuclear pattern of individual cells, we could describe the motion of individual RIF precisely within the nucleus. We show that DNA repair occurs in a limited number of large domains, within which multiple small RIFs form, merge and/or resolve with random motion following normal diffusion law. Large foci formation is shown to be mainly happening through the merging of smaller RIF rather than through growth of an individual focus. We estimate repair domain sizes of 7.5 to 11 µm2 with a maximum number of ~15 domains per MCF10A cell. This work also highlights DDR which are specific to doses larger than 1 Gy such as rapid 53BP1 protein increase in the nucleus and foci diffusion rates that are significantly faster than for spontaneous foci movement. We hypothesize that RIF merging reflects a "stressed" DNA repair process that has been taken outside physiological conditions when too many DSB occur at once. High doses of ionizing radiation lead to RIF merging into repair domains which in turn increases DSB proximity and misrepair. Such finding may therefore be critical to explain the supralinear dose dependence for chromosomal rearrangement and cell death measured after exposure to ionizing radiation.
| S-EPMC4479605 | biostudies-literature
Project description:Tracking and action-recognition algorithms are currently widely used in video surveillance, monitoring urban activities and in many other areas. Their development highly relies on benchmarking scenarios, which enable reliable evaluations/improvements of their efficiencies. Presently, benchmarking methods for tracking and action-recognition algorithms rely on manual annotation of video databases, prone to human errors, limited in size and time-consuming. Here, using gained experiences, an alternative benchmarking solution is presented, which employs methods and tools obtained from the computer-game domain to create simulated video data with automatic annotations. Presented approach highly outperforms existing solutions in the size of the data and variety of annotations possible to create. With proposed system, a potential user can generate a sequence of random images involving different times of day, weather conditions, and scenes for use in tracking evaluation. In the design of the proposed tool, the concept of crowd simulation is used and developed. The system is validated by comparisons to existing methods.
| S-EPMC7506927 | biostudies-literature