A neural network classifier capable of recognizing the patterns of all major subcellular structures in fluorescence microscope images of HeLa cells

By Michael V. Boland, Robert F. Murphy. Bioinform., 2001

494 citations recorded by the source corpus.

Subfields: Biophysics, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/7e69f6339d3684adfeec45254fdd73b7e88e5c4e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

In Molecular Biology

Citations in the corpus

Handcrafted vs. non-handcrafted features for computer vision classification (2017, methodology): “ HE (2D HeLa dataset) [50]: contains images acquired using a fluorescence microscope.”
Machine learning in cell biology – teaching computers to recognize phenotypes (2013, methodology): “…is particularly superior to conventional image processing programs when it comes to solving complex multi-dimensional data analysis tasks such as discriminating morphologies that are not easily described by a few parameters (Boland and Murphy, 2001; Conrad et al., 2004; Neumann et al., 2010).”
Building a 3D Integrated Cell (2017, methodology): “Image feature-based methods have previously been employed to describe and model cell organization (Boland & Murphy, 2001; Carpenter et al., 2006; Rajaram et al., 2012).”
SupportNet: solving catastrophic forgetting in class incremental learning with support data (2018, background): “The HeLa image dataset 2 (Boland and Murphy, 2001) contains the ﬂuorescence microscope images of the 10 major subcellular structures in HeLa cells.”
CellCognition: time-resolved phenotype annotation in high-throughput live cell imaging (2010, methodology): “We first implemented a canonical strategy for automated annotation of morphological classe”
Local binary patterns variants as texture descriptors for medical image analysis (2010, background): “Classifying protein subcellular patterns is important since the knowledge of the subcellular location of a protein is useful in understanding its specific function and in describing the cell behavior under different conditions [29].”
High-Content Screening for Quantitative Cell Biology. (2016, background): “Instead, many of the existing applications of neural networks have been applied to precomputed image features rather than to the underlying pixels [46].”
CellProfiler: image analysis software for identifying and quantifying cell phenotypes (2006, background): “[39,40], but also complex measurements like Zernike shape”
Automated subcellular location determination and high-throughput microscopy. (2007, methodology): “Over the past decade, however, the feasibility of using machine learning methods to automate the determination of subcellular location from fluorescence microscope images has been demonstrated convincingly (Boland et al., 1997, 1998; Boland and Murphy, 2001; Huang and Murphy, 2004b).”
Computer vision for high content screening (2016, background): “…classify cellular phenotypes include support vector machines (SVM) (Chong et al ., 2015; Fuchs et al ., 2010; Held et al ., 2010; Loo et al ., 2007), adaptive boosting (Jones et al ., 2008), random forests (Kaynig et al ., 2010), and neural networks (Boland & Murphy, 2001; Horvath et al ., 2011).”
Large‐scale image‐based screening and profiling of cellular phenotypes (2017, methodology): “Interestingly, several past studies have consistently found that Haralick’s texture features are highly informative (22,40,86,88,91,97), and therefore these features are recommended to be included as part of the standard initial feature set in phenotypic profiling.”
Scoring diverse cellular morphologies in image-based screens with iterative feedback and machine learning (2009, background): “Previous work has demonstrated that machine learning algorithms can be successfully trained by using all cells from positive and negative control samples to create a training set, even for some phenotypes that cannot be visually distinguished by humans (25).”
Comparison of quantitative methods for cell‐shape analysis (2007, background): “,1998; Boland & Murphy, 2001; Hu & Murphy, 2004), there has been little work towards determining useful sets of descriptive features for cell shape.”
Segmentation and Classification of Cell Cycle Phases in Fluorescence Imaging (2009, unknown): “Our choice of feature vector (64 bins of intensity histogram and 64 bins of intensity surface curvature histogram) captures the characteristic texture information of each class without more elaborated feature vector computations such as [13, 14, 7].”
Cellular heterogeneity: when do differences make a difference? (2010, background): “…or marker localization, whereas strategies striving for comprehensiveness may use features derived from general-purpose transformations, such as Haralick texture features or Zernike moments that report large numbers of statistical properties of marker staining patterns (Boland and Murphy, 2001).”
Generative Modeling with Conditional Autoencoders: Building an Integrated Cell (2017, methodology): “Image feature-based methods have previously been em-Preprint ployed to describe and model cell organization (Boland & Murphy, 2001; Carpenter et al., 2006; Rajaram et al., 2012).”