A Quality Pre-processor for Biological Cell Images

Peskin, Adele P.; Kafadar, Karen; Dima, Alden A.

doi:10.1007/978-3-642-10520-3_101

Cited by 5 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each cell in an image, its quality index is found from the pixel intensities within an isolated region containing the cell. These steps, described in detail in (19), are summarized as: Find the 3‐component Gaussian mixture via the EM (Expectation‐Maximization) algorithm, whose components correspond to background ( B ), edge ( E ), and cell ( C ) pixels, and denote the means of the components by μ B , μ E , and μ C . Find the average gradient magnitude at each intensity between μ B and μ E and denote the resulting function by G (Intensity). Because not all possible intensity values are present in the portion of the image containing the cell, there will be gaps where no average gradient magnitude can be calculated.…”

Section: Materials and Methods1mentioning

confidence: 99%

Comparison of segmentation algorithms for fluorescence microscopy images of cells

et al. 2011

View full text Add to dashboard Cite

The analysis of fluorescence microscopy of cells often requires the determination of cell edges. This is typically done using segmentation techniques that separate the cell objects in an image from the surrounding background. This study compares segmentation results from nine different segmentation techniques applied to two different cell lines and five different sets of imaging conditions. Significant variability in the results of segmentation was observed that was due solely to differences in imaging conditions or applications of different algorithms. We quantified and compared the results with a novel bivariate similarity index metric that evaluates the degree of underestimating or overestimating a cell object. The results show that commonly used threshold-based segmentation techniques are less accurate than k-means clustering with multiple clusters. Segmentation accuracy varies with imaging conditions that determine the sharpness of cell edges and with geometric features of a cell. Based on this observation, we propose a method that quantifies cell edge character to provide an estimate of how accurately an algorithm will perform. The results of this study will assist the development of criteria for evaluating interlaboratory comparability. Published 2011 Wiley-Liss, Inc.y Key terms fluorescence microscopy; k-means cluster; image segmentation; cell edge; bivariate similarity index NUMEROUS areas of biomedical research rely on imaging of cells to provide information about molecular and phenotypic responses of cells to pharmaceuticals, toxins, and other environmental factors (1,2). Cell imaging is widely used in biological experiments because it can provide information on several relevant scales simultaneously. Molecular and supramolecular scales can be probed with the use of antibody and other specific affinity reagents and with fluorescent proteins. Gross phenotypic characteristics of cells that characterize their ultimate functional state can be examined in the same experiment, and often the temporal regime can be probed simultaneously. Together, these applications of cell imaging allow inference about the molecular details and the complex outcomes of the cellular biochemistry.Because of the enormous number of parameters that may influence a biological outcome, cell imaging experiments are often done in a ''high content '' mode (3,4), where large numbers of paired and replicate experiments are carried out simultaneously and result in very large (often gigabyte) image datasets. Such a large volume of image data precludes visual inspection of every image, and automated image processing and analysis is the only viable approach to data analysis.Segmentation of cell objects is a common image analysis operation that provides spatial and other features of identified objects and often precedes other operations to quantify parameters such as intracellular fluorescence. Segmentation can pose significant challenges to automated image processing and analysis. Because morphological features are often important in...

show abstract

Section: Materials and Methods1mentioning

confidence: 99%

Comparison of segmentation algorithms for fluorescence microscopy images of cells

et al. 2011

View full text Add to dashboard Cite

show abstract

“…At present, no objective measures of print quality have been proposed, as they have been for other images. For example, the methodology of Peskin et al , for assessing the quality of biological cell images (Figure ) could be adapted to derive a more objective measure of fingerprint image quality (Figure ). The c omparison phase of the A C E‐V method is highly subjective: the examiner selects regions for comparing a latent print with prints from a database. The e valuation phase of the AC E ‐V method likewise is subjective: the examiner identifies features (points or minutiae) that ‘match’. The non‐compulsory guidelines from the Scientific Working Group on Friction and Surface Technology recommend 6–12 points of agreement.…”

Section: Dna Analysis Versus Latent Print Analysismentioning

confidence: 99%

“…At present, no objective measures of print quality have been proposed, as they have been for other images. For example, the methodology of Peskin et al (2009) for assessing the quality of biological cell images ( Figure 2) could be adapted to derive a more objective measure of fingerprint image quality ( Figure 3). (4) The comparison phase of the ACE-V method is highly subjective: the examiner selects regions for comparing a latent print with prints from a database.…”

Section: Dna Analysis Versus Latent Print Analysismentioning

confidence: 99%

See 1 more Smart Citation

Statistical Issues in Assessing Forensic Evidence

Kafadar

2014

Int Statistical Rev

Self Cite

View full text Add to dashboard Cite

In 2009, the National Academy of Sciences released a report that emphasized the need for more scientific research in the evaluation of methods in the forensic science disciplines. This needed research includes statistical issues such as bias quantification, validation and estimates of accuracy and precision in different contexts. This article reviews statistical aspects of forensic science with particular reference to the design of studies that are essential to evaluate inferences from forensic evidence. Many sources can affect both the accuracy and the consistency of decisions at each stage of the process, from specimen collection to final decision. The article discusses the importance of identifying these sources and the statistical principles involved in the quantification of, and uncertainty in, estimated probabilities of error. By contrasting the design of a successful community clinical trial with two previous fingerprint studies and with bullet lead studies, this article emphasizes the need for reduced subjectivity, the types of measurements on physical evidence that can lead to more accurate and consistent decisions and the importance of carefully designed studies in the evaluation of forensic evidence.

show abstract

“…The ratio of the number of pixels in this band around the cell to the total number of cell pixels describes the ratio of pixels at risk during segmentation. Briefly, the edge thickness is determined by estimating the number of physical pixels on the image that represent a cell edge, calculated using a quality index (QI) calculation [7]. The quality index ranges from 0.0 to 2.0, with a perfectly sharp edge at a value of 2.0.…”

Section: Comparison Of Hand-selected Data Setsmentioning

confidence: 99%

A Human Inspired Local Ratio-Based Algorithm for Edge Detection in Fluorescent Cell Images

Chalfoun¹,

Dima²,

Peskin³

et al. 2010

Advances in Visual Computing

Self Cite

View full text Add to dashboard Cite

Abstract. We have developed a new semi-automated method for segmenting images of biological cells seeded at low density on tissue culture substrates, which we use to improve the generation of reference data for the evaluation of automated segmentation algorithms. The method was designed to mimic manual cell segmentation and is based on a model of human visual perception. We demonstrate a need for automated methods to assist with the generation of reference data by comparing several sets of masks from manually segmented cell images created by multiple independent hand-selections of pixels that belong to cell edges. We quantify the differences in these manually segmented masks and then compare them with masks generated from our new segmentation method which we use on cell images acquired to ensure very sharp, clear edges. The resulting masks from 16 images contain 71 cells and show that our semi-automated method for reference data generation locates cell edges more consistently than manual segmentation alone and produces better edge detection than other techniques like 5-means clustering and active contour segmentation for our images.

show abstract

A Quality Pre-processor for Biological Cell Images

Cited by 5 publications

References 11 publications

Comparison of segmentation algorithms for fluorescence microscopy images of cells

Comparison of segmentation algorithms for fluorescence microscopy images of cells

Statistical Issues in Assessing Forensic Evidence

A Human Inspired Local Ratio-Based Algorithm for Edge Detection in Fluorescent Cell Images

Contact Info

Product

Resources

About