Improved structure, function and compatibility for CellProfiler: modular high-throughput image analysis software

Kamentsky, Lee; Jones, Thouis R.; Fraser, Adam; Bray, Mark-Anthony; Logan, David J.; Madden, Katherine L.; Ljosa, Vebjorn; Rueden, Curtis; Eliceiri, Kevin W.; Carpenter, Anne E.

doi:10.1093/bioinformatics/btr095

Cited by 946 publications

(809 citation statements)

References 9 publications

Supporting

Mentioning

788

Contrasting

Unclassified

Order By: Relevance

“…In order to better represent the biological information of a sample, the hematoxylin and eosin stains were separated from the original image using the color deconvolution method used in CellProfiler (Kamentsky et al, 2011). This method for color deconvolution uses pseudo inverse matrices as described by Ruifrok and Johnson (Ruifrok and Johnston, 2001 where RGB i,j are the red, green, and blue channel values for pixel i,j and HE i,j are the deconvoluted hematoxylin and eosin values for pixel i,j.…”

Section: Unmixing the Stainsmentioning

confidence: 99%

Automated classification of brain tumor type in whole-slide digital pathology images using local representative tiles

Barker

Hoogi

Depeursinge

et al. 2016

Medical Image Analysis

190

110

View full text Add to dashboard Cite

a b s t r a c tComputerized analysis of digital pathology images offers the potential of improving clinical care (e.g. automated diagnosis) and catalyzing research (e.g. discovering disease subtypes). There are two key challenges thwarting computerized analysis of digital pathology images: first, whole slide pathology images are massive, making computerized analysis inefficient, and second, diverse tissue regions in whole slide images that are not directly relevant to the disease may mislead computerized diagnosis algorithms. We propose a method to overcome both of these challenges that utilizes a coarse-to-fine analysis of the localized characteristics in pathology images. An initial surveying stage analyzes the diversity of coarse regions in the whole slide image. This includes extraction of spatially localized features of shape, color and texture from tiled regions covering the slide. Dimensionality reduction of the features assesses the image diversity in the tiled regions and clustering creates representative groups. A second stage provides a detailed analysis of a single representative tile from each group. An Elastic Net classifier produces a diagnostic decision value for each representative tile. A weighted voting scheme aggregates the decision values from these tiles to obtain a diagnosis at the whole slide level. We evaluated our method by automatically classifying 302 brain cancer cases into two possible diagnoses (glioblastoma multiforme (N = 182) versus lower grade glioma (N = 120)) with an accuracy of 93.1 % (p << 0.001). We also evaluated our method in the dataset provided for the 2014 MICCAI Pathology Classification Challenge, in which our method, trained and tested using 5-fold cross validation, produced a classification accuracy of 100% (p << 0.001). Our method showed high stability and robustness to parameter variation, with accuracy varying between 95.5% and 100% when evaluated for a wide range of parameters. Our approach may be useful to automatically differentiate between the two cancer subtypes.

show abstract

Section: Unmixing the Stainsmentioning

confidence: 99%

Automated classification of brain tumor type in whole-slide digital pathology images using local representative tiles

Barker

Hoogi

Depeursinge

et al. 2016

Medical Image Analysis

190

110

View full text Add to dashboard Cite

show abstract

“…ImageJ (originally called NIH Image) holds a unique position in the area of extensible and interoperable open source tools which makes it the most popular and widespread multi‐functional image analysis tool (Kamentsky et al, 2011; Preibisch et al, 2010; Schneider et al, 2012) [14]). Within ImageJ the 3D Viewer plug‐in renders multi‐fluorophore 3D imaging that enables the user to explore the data.…”

Section: Data Analysis and Data Managementmentioning

confidence: 99%

Advanced light microscopy core facilities: Balancing service, science and career

Ferrando‐May

Hartmann

Reymann

et al. 2016

Microsc. Res. Tech.

View full text Add to dashboard Cite

Core Facilities (CF) for advanced light microscopy (ALM) have become indispensable support units for research in the life sciences. Their organizational structure and technical characteristics are quite diverse, although the tasks they pursue and the services they offer are similar. Therefore, throughout Europe, scientists from ALM‐CFs are forming networks to promote interactions and discuss best practice models. Here, we present recommendations for ALM‐CF operations elaborated by the workgroups of the German network of ALM‐CFs, German Bio‐Imaging (GerBI). We address technical aspects of CF planning and instrument maintainance, give advice on the organization and management of an ALM‐CF, propose a scheme for the training of CF users, and provide an overview of current resources for image processing and analysis. Further, we elaborate on the new challenges and opportunities for professional development and careers created by CFs. While some information specifically refers to the German academic system, most of the content of this article is of general interest for CFs in the life sciences. Microsc. Res. Tech. 79:463–479, 2016. © 2016 THE AUTHORS MICROSCOPY RESEARCH AND TECHNIQUE PUBLISHED BY WILEY PERIODICALS, INC.

show abstract

“…In the next section we evaluate several of these methods for the optimization of eq. (9). The problem in eq.…”

Section: = Arg Minmentioning

confidence: 99%

“…The results are shown in Table 1. The first row represents the results of an edge based method [6], whereas the next two rows correspond with two intensity based images [9,10]. Note that the proposed method, the last row, get the best results both for cell detection metrics, in the first 4 columns, as for the Dice coefficient, which is a metric for segmentation quality.…”

Section: Detectionmentioning

confidence: 99%

“…For isolated nuclei this is rather straightforward, but for touching nuclei this requires an extra step to detect each individual nucleus. This is mainly done by assuming that the detected segments should have a convex shape [2,[9][10][11]. These methods are non optimal since both steps are independent: the second step can only use the result of the first step, instead of all information available, e.g.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cell Nuclei Detection Using Globally Optimal Active Contours with Shape Prior

Vylder

Aelterman

Vandewoestyne

et al. 2012

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. Cell nuclei detection in fluorescent microscopic images is an important and time consuming task for a wide range of biological applications. Blur, clutter, bleed through and partial occlusion of nuclei make this a challenging task for automated detection of individual nuclei using image analysis. This paper proposes a novel and robust detection method based on the active contour framework. The method exploits prior knowledge of the nucleus shape in order to better detect individual nuclei. The method is formulated as the optimization of a convex energy function. The proposed method shows accurate detection results even for clusters of nuclei where state of the art methods fail.

show abstract

Improved structure, function and compatibility for CellProfiler: modular high-throughput image analysis software

Abstract: Supplementary data are available at Bioinformatics online.

Cited by 946 publications

References 9 publications

Automated classification of brain tumor type in whole-slide digital pathology images using local representative tiles

Automated classification of brain tumor type in whole-slide digital pathology images using local representative tiles

Advanced light microscopy core facilities: Balancing service, science and career

Cell Nuclei Detection Using Globally Optimal Active Contours with Shape Prior

Contact Info

Product

Resources

About