Authors:
Mathieu Bouyrie
1
;
Cristina Manfredotti
2
;
Nadine Peyriéras
3
and
Antoine Cornuéjols
2
Affiliations:
1
AgroParisTech and BioEmergences Lab, France
;
2
AgroParisTech, France
;
3
BioEmergences Lab, France
Keyword(s):
3D Image Denoising, Biomedical Imaging, Mixed Poisson-Gaussian Noise, Isotropic Undecimated Wavelet Transform, Stabilizing Transform, Hypothesis Testing, Optimization Algorithm, Cell Detection.
Related
Ontology
Subjects/Areas/Topics:
Convex Optimization
;
Information Retrieval and Learning
;
Pattern Recognition
;
Sparsity
;
Theory and Methods
Abstract:
This paper presents a new multiscale method to denoise three-dimensional images of cell nuclei. The specificity
of this method is its awareness of the noise distribution and object shapes. It combines a multiscale
representation called Isotropic Undecimated Wavelet Transform (IUWT) with a nonlinear transform, a statistical
test and a variational method, to retrieve spherical shapes in the image. Beyond extending an existing
2D approach to a 3D problem, our algorithm takes the sampling grid dimensions into account. We compare
our method to the two algorithms from which it is derived on a representative image analysis task, and show
that it is superior to both of them. It brings a slight improvement in the signal-to-noise ratio and a significant
improvement in cell detection.