Quantitative comparison of spot detection methods in live-cell fluorescence microscopy imaging

Authors:
Ihor Smal;Marco Loog;Wiro Niessen;Erik Meijering
Affiliations:
Biomedical Imaging Group Rotterdam, Departments of Medical Informatics and Radiology, Erasmus MC, University Medical Center Rotterdam, The Netherlands;Pattern Recognition Group, Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, The Netherlands;Biomedical Imaging Group Rotterdam, Departments of Medical Informatics and Radiology, Erasmus MC, University Medical Center Rotterdam, The Netherlands;Biomedical Imaging Group Rotterdam, Departments of Medical Informatics and Radiology, Erasmus MC, University Medical Center Rotterdam, The Netherlands
Venue:
ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
Year:
2009

Citing 2
Cited 2

Microscope Image Processing

Microscope Image Processing
Automatic tracking of individual fluorescence particles: application to the study of chromosome dynamics

IEEE Transactions on Image Processing

Particle tracking in fluorescent microscopy images improved by morphological source separation

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Scale selection for supervised image segmentation

Image and Vision Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In live-cell fluorescence microscopy imaging, quantitative analysis of biological image data generally involves the detection of many subresolution objects, appearing as diffraction-limited spots. Due to acquisition limitations, the signal-to-noise ratio (SNR) can be extremely low, making automated spot detection a very challenging task. In this paper, we quantitatively evaluate the performance of the most frequently used supervised and unsupervised detection methods for this purpose. Experiments on synthetic images of three different types, for which ground truth was available, as well as on real image data sets acquired for two different biological studies, for which we obtained expert manual annotations for comparison, revealed that for very low SNRs (≅2), the supervised (machine learning) methods perform best overall, closely followed by the detectors based on the so-called h-dome transform from mathematical morphology and the multiscale variance-stabilizing transform, which do not require a learning stage. At high SNRs (5), the difference in performance of all considered detectors becomes negligible.