Home     Research     Publications     Vita    Hobbies



Microvasculature Denoising and Enhancement in Fluorescence Microscopy Images

 



V. B. Surya Prasath   Rengarajan Pelapur
  K. Palaniappan
Computer Science, University of Missouri-Columbia, USA


O. Glinskii     V. Glinsky     V. Huxley
School of Medicine, University of Missouri-Columbia, USA




Abstract:

Fluorescence microscopy images are contaminated by noise and improving image quality without blurring vascular structures by filtering is an important step in automatic image analysis. The application of interest here is to automatically extract the structural components of the microvascular system with accuracy from images acquired by fluorescence microscopy. A robust denoising process is necessary in order to extract accurate vascular morphology information. For this purpose, we propose a multiscale tensor with anisotropic diffusion model which progressively and adaptively updates the amount of smoothing while preserving vessel boundaries accurately. Based on a coherency enhancing flow with planar confidence measure and fused 3D structure information, our method integrates multiple scales for microvasculature preservation and noise removal membrane structures. Experimental results on simulated synthetic images and epifluorescence images show the advantage of our improvement over other related diffusion filters.  We further show that the proposed multiscale integration approach improves denoising accuracy of different tensor diffusion methods to obtain better microvasculature segmentation.

Related projects: segmentation, analysis


Restoration Results

Synthetic image:
Synthetic image shown here is generated following a similar set-up as the one in Pop et al [13] by simulating boundary thickness close to real cells and 50% of the membrane pixels are randomly removed. Note that this simulates the acquisition of 2D membrane structures under a 3D fluorescence microscope and we show only 2D cross sections for clarity.

 Kriva
[8]
Weickert [12]
 Drblikova [11] Mosaliganti [9]
 Pop
[13]
 Manniesing [10]  Prasath [3]  Our
 
 
 
 
 
 
 
 
(Click on each image to download the original image files, for citations [xx] see the reference below)


Microscopy image:





Reference:

V. B. S. Prasath, R. Pelapur, O. V. Glinskii, V. V. Glinsky, V. H. Huxley, K. Palaniappan. Multiscale tensor anisotropic filtering of fluorescence microscopy for denoising microvasculature. IEEE International Symposium on Biomedical Imaging (ISBI), April 2015. Proc. IEEE, pp. 540-543.
Poster at figshare: 10.6084/m9.figshare.1309773


Back to research page. Back to the homepage.