Cell sorting in a Petri dish controlled by computer vision.
Ontology highlight
ABSTRACT:
SUBMITTER: Kornyei Z
PROVIDER: S-EPMC3548191 | biostudies-other | 2013
REPOSITORIES: biostudies-other
Publications
Cell sorting in a Petri dish controlled by computer vision.
Környei Z Z Beke S S Mihálffy T T Jelitai M M Kovács K J KJ Szabó Z Z Szabó B B
Scientific reports 20130118
Fluorescence-activated cell sorting (FACS) applying flow cytometry to separate cells on a molecular basis is a widespread method. We demonstrate that both fluorescent and unlabeled live cells in a Petri dish observed with a microscope can be automatically recognized by computer vision and picked up by a computer-controlled micropipette. This method can be routinely applied as a FACS down to the single cell level with a very high selectivity. Sorting resolution, i.e., the minimum distance between ...[more]
Similar Datasets
Project description:The actions of cell adhesion molecules, in particular, cadherins during embryonic development and morphogenesis more generally, regulate many aspects of cellular interactions, regulation and signaling. Often, a gradient of cadherin expression levels drives collective and relative cell motions generating macroscopic cell sorting. Computer simulations of cell sorting have focused on the interactions of cells with only a few discrete adhesion levels between cells, ignoring biologically observed continuous variations in expression levels and possible nonlinearities in molecular binding. In this paper, we present three models relating the surface density of cadherins to the net intercellular adhesion and interfacial tension for both discrete and continuous levels of cadherin expression. We then use then the Glazier-Graner-Hogeweg (GGH) model to investigate how variations in the distribution of the number of cadherins per cell and in the choice of binding model affect cell sorting. We find that an aggregate with a continuous variation in the level of a single type of cadherin molecule sorts more slowly than one with two levels. The rate of sorting increases strongly with the interfacial tension, which depends both on the maximum difference in number of cadherins per cell and on the binding model. Our approach helps connect signaling at the molecular level to tissue-level morphogenesis.
| S-EPMC3196507 | biostudies-literature
Project description:Current robots can manipulate only surface-attached cells seriously limiting the fields of their application for single cell handling. We developed a computer vision-based robot applying a motorized microscope and micropipette to recognize and gently isolate intact individual cells for subsequent analysis, e.g., DNA/RNA sequencing in 1-2 nanoliters from a thin (~100 μm) layer of cell suspension. It can retrieve rare cells, needs minimal sample preparation, and can be applied for virtually any tissue cell type. Combination of 1 μm positioning precision, adaptive cell targeting and below 1 nl liquid handling precision resulted in an unprecedented accuracy and efficiency in robotic single cell isolation. Single cells were injected either into the wells of a miniature plate with a sorting speed of 3 cells/min or into standard PCR tubes with 2 cells/min. We could isolate labeled cells also from dense cultures containing ~1,000 times more unlabeled cells by the successive application of the sorting process. We compared the efficiency of our method to that of single cell entrapment in microwells and subsequent sorting with the automated micropipette: the recovery rate of single cells was greatly improved.
| S-EPMC4746594 | biostudies-literature
Project description:PurposeTo evaluate the prevalence of computer vision syndrome (CVS)-related symptoms in a presbyopic population using the computer as the main work tool, as well as the relationship of CVS with the electronic device use habits and the ergonomic factors.MethodsA sample of 198 presbyopic participants (aged 45-65 years) who regularly work with a computer completed a customised questionnaire divided into: general demographics, optical correction commonly used and for work, habits of electronic devices use, ergonomic conditions during the working hours and CVS-related symptoms during work performance. A total of 10 CVS-related symptoms were questioned indicating the severity with which they occurred (0-4) and the median total symptom score (MTSS) was calculated as the sum of the symptoms.ResultsThe MTSS in this presbyopic population is 7 ± 5 symptoms. The most common symptoms reported by participants are dry eyes, tired eyes and difficulties in refocusing. MTSS is higher in women (p < 0.05), in laptop computer users (p < 0.05) and in teleworkers compared to office workers (p < 0.05). Regarding ergonomic conditions, MTSS is higher in participants who do not take breaks while working (p < 0.05), who have an inadequately lighting in the workspace (p < 0.05) and in the participants reporting neck (p < 0.01) or back pain (p < 0.001).ConclusionThere is a relationship between CVS-related symptoms, the use of electronic devices and the ergonomic factors, which indicates the importance of adapting workplaces, especially for home-based teleworkers, and following basic visual ergonomics rules.
| S-EPMC10133911 | biostudies-literature
Project description:Extracting meaning from a dynamic and variable flow of incoming information is a major goal of both natural and artificial intelligence. Computer vision (CV) guided by deep learning (DL) has made significant strides in recognizing a specific identity despite highly variable attributes. This is the same challenge faced by the nervous system and partially addressed by the concept cells-neurons exhibiting selective firing in response to specific persons/places, described in the human medial temporal lobe (MTL) . Yet, access to neurons representing a particular concept is limited due to these neurons' sparse coding. It is conceivable, however, that the information required for such decoding is present in relatively small neuronal populations. To evaluate how well neuronal populations encode identity information in natural settings, we recorded neuronal activity from multiple brain regions of nine neurosurgical epilepsy patients implanted with depth electrodes, while the subjects watched an episode of the TV series "24". First, we devised a minimally supervised CV algorithm (with comparable performance against manually-labeled data) to detect the most prevalent characters (above 1% overall appearance) in each frame. Next, we implemented DL models that used the time-varying population neural data as inputs and decoded the visual presence of the four main characters throughout the episode. This methodology allowed us to compare "computer vision" with "neuronal vision"-footprints associated with each character present in the activity of a subset of neurons-and identify the brain regions that contributed to this decoding process. We then tested the DL models during a recognition memory task following movie viewing where subjects were asked to recognize clip segments from the presented episode. DL model activations were not only modulated by the presence of the corresponding characters but also by participants' subjective memory of whether they had seen the clip segment, and by the associative strengths of the characters in the narrative plot. The described approach can offer novel ways to probe the representation of concepts in time-evolving dynamic behavioral tasks. Further, the results suggest that the information required to robustly decode concepts is present in the population activity of only tens of neurons even in brain regions beyond MTL.
| S-EPMC9837190 | biostudies-literature
Project description:State-of-the-art computer vision systems use frame-based cameras that sample the visual scene as a series of high-resolution images. These are then processed using convolutional neural networks using neurons with continuous outputs. Biological vision systems use a quite different approach, where the eyes (cameras) sample the visual scene continuously, often with a non-uniform resolution, and generate neural spike events in response to changes in the scene. The resulting spatio-temporal patterns of events are then processed through networks of spiking neurons. Such event-based processing offers advantages in terms of focusing constrained resources on the most salient features of the perceived scene, and those advantages should also accrue to engineered vision systems based upon similar principles. Event-based vision sensors, and event-based processing exemplified by the SpiNNaker (Spiking Neural Network Architecture) machine, can be used to model the biological vision pathway at various levels of detail. Here we use this approach to explore structural synaptic plasticity as a possible mechanism whereby biological vision systems may learn the statistics of their inputs without supervision, pointing the way to engineered vision systems with similar online learning capabilities.
| S-EPMC6015816 | biostudies-literature
Project description:Understanding the extremely variable, complex shape and venation characters of angiosperm leaves is one of the most challenging problems in botany. Machine learning offers opportunities to analyze large numbers of specimens, to discover novel leaf features of angiosperm clades that may have phylogenetic significance, and to use those characters to classify unknowns. Previous computer vision approaches have primarily focused on leaf identification at the species level. It remains an open question whether learning and classification are possible among major evolutionary groups such as families and orders, which usually contain hundreds to thousands of species each and exhibit many times the foliar variation of individual species. Here, we tested whether a computer vision algorithm could use a database of 7,597 leaf images from 2,001 genera to learn features of botanical families and orders, then classify novel images. The images are of cleared leaves, specimens that are chemically bleached, then stained to reveal venation. Machine learning was used to learn a codebook of visual elements representing leaf shape and venation patterns. The resulting automated system learned to classify images into families and orders with a success rate many times greater than chance. Of direct botanical interest, the responses of diagnostic features can be visualized on leaf images as heat maps, which are likely to prompt recognition and evolutionary interpretation of a wealth of novel morphological characters. With assistance from computer vision, leaves are poised to make numerous new contributions to systematic and paleobotanical studies.
| S-EPMC4812720 | biostudies-literature
Project description:Stable cell-cell contacts underpin tissue architecture and organization. Quantification of junctions of mammalian epithelia requires laborious manual measurements that are a major roadblock for mechanistic studies. We designed Junction Mapper as an open access, semi-automated software that defines the status of adhesiveness via the simultaneous measurement of pre-defined parameters at cell-cell contacts. It identifies contacting interfaces and corners with minimal user input and quantifies length, area and intensity of junction markers. Its ability to measure fragmented junctions is unique. Importantly, junctions that considerably deviate from the contiguous staining and straight contact phenotype seen in epithelia are also successfully quantified (i.e. cardiomyocytes or endothelia). Distinct phenotypes of junction disruption can be clearly differentiated among various oncogenes, depletion of actin regulators or stimulation with other agents. Junction Mapper is thus a powerful, unbiased and highly applicable software for profiling cell-cell adhesion phenotypes and facilitate studies on junction dynamics in health and disease.
| S-EPMC7034980 | biostudies-literature
Project description:Noninvasive enumeration of rare circulating cell populations in small animals is of great importance in many areas of biomedical research. In this work, we describe a macroscopic fluorescence imaging system and automated computer vision algorithm that allows in vivo detection, enumeration and tracking of circulating fluorescently-labeled cells from multiple large blood vessels in the ear of a mouse. This imaging system uses a 660 nm laser and a high sensitivity electron-multiplied charge coupled device camera (EMCCD) to acquire fluorescence image sequences from relatively large (∼5 × 5 mm(2) ) imaging areas. The primary technical challenge was developing an automated method for identifying and tracking rare cell events in image sequences with substantial autofluorescence and noise content. To achieve this, we developed a two-step image analysis algorithm that first identified cell candidates in individual frames, and then merged cell candidates into tracks by dynamic analysis of image sequences. The second step was critical since it allowed rejection of >97% of false positive cell counts. Overall, our computer vision IVFC (CV-IVFC) approach allows single-cell detection sensitivity at estimated concentrations of 20 cells/mL of peripheral blood. In addition to simple enumeration, the technique recovers the cell's trajectory, which in the future could be used to automatically identify, for example, in vivo homing and docking events.
| S-EPMC3934567 | biostudies-literature
Project description:Today, computer vision systems are tested by their accuracy in detecting and localizing instances of objects. As an alternative, and motivated by the ability of humans to provide far richer descriptions and even tell a story about an image, we construct a "visual Turing test": an operator-assisted device that produces a stochastic sequence of binary questions from a given test image. The query engine proposes a question; the operator either provides the correct answer or rejects the question as ambiguous; the engine proposes the next question ("just-in-time truthing"). The test is then administered to the computer-vision system, one question at a time. After the system's answer is recorded, the system is provided the correct answer and the next question. Parsing is trivial and deterministic; the system being tested requires no natural language processing. The query engine employs statistical constraints, learned from a training set, to produce questions with essentially unpredictable answers-the answer to a question, given the history of questions and their correct answers, is nearly equally likely to be positive or negative. In this sense, the test is only about vision. The system is designed to produce streams of questions that follow natural story lines, from the instantiation of a unique object, through an exploration of its properties, and on to its relationships with other uniquely instantiated objects.
| S-EPMC4378453 | biostudies-literature
Project description:This paper reviews computer vision and image analysis studies aiming at automated diagnosis or screening of malaria infection in microscope images of thin blood film smears. Existing works interpret the diagnosis problem differently or propose partial solutions to the problem. A critique of these works is furnished. In addition, a general pattern recognition framework to perform diagnosis, which includes image acquisition, pre-processing, segmentation, and pattern classification components, is described. The open problems are addressed and a perspective of the future work for realization of automated microscopy diagnosis of malaria is provided.
| S-EPMC2719653 | biostudies-literature