Patch-Based Sparse Representation For Bacterial Detection

  title={Patch-Based Sparse Representation For Bacterial Detection},
  author={Ahmed Karam Eldaly and Yoann Altmann and Ahsan R. Akram and Antonios Perperidis and Kevin Dhaliwal and Stephen Mclaughlin},
  journal={2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)},
  • A. Eldaly, Y. Altmann, +3 authors S. Mclaughlin
  • Published 29 October 2018
  • Computer Science
  • 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)
In this paper, we propose an unsupervised approach for bacterial detection in optical endomicroscopy images. This approach splits each image into a set of overlapping patches and assumes that observed intensities are linear combinations of the actual intensity values associated with background image structures, corrupted by additive Gaussian noise and potentially by a sparse outlier term modelling anomalies (which are considered to be candidate bacteria). The actual intensity term representing… Expand
4 Citations
Bayesian bacterial detection using irregularly sampled optical endomicroscopy images
A Bayesian approach for bacterial detection in OEM images is presented, which detects most of the manually annotated regions, and a good correlation between bacteria counts identified by a trained clinician and those of the proposed method. Expand
Enhanced avidity from a multivalent fluorescent antimicrobial peptide enables pathogen detection in a human lung model
NBD-UBIdend demonstrates bacterial labelling specificity for a broad panel of pathogenic bacteria and Aspergillus fumigatus and demonstrates high signal-to-noise fluorescence amplification upon target engagement, and was non-toxic and chemically robust within the inflamed biological environment. Expand
Bayesian Activity Estimation and Uncertainty Quantification of Spent Nuclear Fuel Using Passive Gamma Emission Tomography
The results demonstrate superior performance of the proposed approach in estimating the pin activities in different assembly patterns, in addition to being able to quantify their uncertainty measures, in comparison with existing methods. Expand
Characterising cross-coupling in coherent fibre bundles
A novel approach for quantifying and modelling cross coupling, optimising image reconstruction in fibre-bundle endomicroscopy is introduced. Expand


Robust Markov Random Field outlier detection and removal in subsampled images
This work addresses the problem of data restoration for applications where the observed irregularly distributed samples are corrupted by additive observation noise and sparse outliers (such as broken and damaged fibre cores). Expand
Deconvolution of Irregularly Subsampled Images
This paper proposes a hierarchical Bayesian model in which suitable prior distributions are assigned to the unknown model parameters, and compares two estimation strategies including Markov chain Monte Carlo (MCMC) and variational Bayes (VB), which are used to perform Bayesian inference using the posterior distribution. Expand
Estimating Bacterial and Cellular Load in FCFM Imaging
This work extracts image patches around each pixel as features, and train a classifier to predict if a bacterium or cell is present at that pixel, and applies this approach on two datasets for detecting bacteria and cells respectively. Expand
Deconvolution and Restoration of Optical Endomicroscopy Images
A hierarchical Bayesian model is proposed to solve the problem of deconvolution and restoration of OEM data and three estimation algorithms are compared to exploit the resulting joint posterior distribution. Expand
Learning To Count Objects in Images
This work focuses on the practically-attractive case when the training images are annotated with dots, and introduces a new loss function, which is well-suited for visual object counting tasks and at the same time can be computed efficiently via a maximum subarray algorithm. Expand
Quantitative Comparison of Spot Detection Methods in Fluorescence Microscopy
Seven unsupervised and two supervised detection methods based on the so-called h -dome transform from mathematical morphology or the multiscale variance-stabilizing transform perform comparably, and have the advantage that they do not require a cumbersome learning stage. Expand
Robust Linear Spectral Unmixing Using Anomaly Detection
A Bayesian algorithm for linear spectral unmixing of hyperspectral images that accounts for anomalies present in the data and a Markov random field is used for anomaly detection based on the spatial and spectral structures of the anomalies. Expand
A Laplacian of Gaussian-Based Approach for Spot Detection in Two-Dimensional Gel Electrophoresis Images
An improved protein spot detection approach is presented, which is based on Laplacian of Gaussian algorithm, and the regional maxima is extracted by morphological grayscale reconstruction algorithm, which can reduce the impact of noisy and background in spot detection. Expand
A new detection scheme for multiple object tracking in fluorescence microscopy by joint probabilistic data association filtering
  • I. Smal, W. Niessen, E. Meijering
  • Mathematics, Computer Science
  • 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro
  • 2008
A new object detection scheme is proposed, based on importance sampling from image intensity distributions, and it is shown how it can be easily incorporated into a probabilistic tracking framework based on Kalman or particle filtering. Expand
Multiple object tracking in molecular bioimaging by Rao-Blackwellized marginal particle filtering
This work proposes an improved, fully automated particle filtering algorithm for the tracking of many subresolution objects in fluorescence microscopy image sequences that involves a new track management procedure and allows the use of multiple dynamics models. Expand