A Pipeline Architecture for Processing of DNA Microarrays Images
Journal of VLSI Signal Processing Systems
Recognition of perspectively distorted planar grids
Pattern Recognition Letters
Robust pre-processing and noise reduction in microarray images
BIEN '07 Proceedings of the fifth IASTED International Conference: biomedical engineering
Hi-index | 0.00 |
In this paper, we present a computational framework thatprovides the automatic analysis of spotted DNA microarrayimage data. The challenges are in providing an accuraterepresentation of microarray hybridization observationswhile minimizing user interaction. To obtain this, weneed to segment the observation data and subsequent correctionfor true hybridization level measurements must beaccomplished against the backdrop of signal noise, backgroundsignal variation, and spatial non-uniformity in thearray layout. With the requirements of automation and accuracy,an approach based on data-driven denoising, arrayaddressing, background estimation, and spot segmentationwas developed. We proceeded to validate our approach onsynthetic data as well as the publicly available raw and analyzedmicroarray data from the published Stanford yeastcell cycle analysis project. Spot mean and total intensitieswere examined as well as spot background estimates.By minimizing the user role, a main bottleneck in microarraydata analysis is removed, allowing for more immediateanalysis of large observation data sets. Our implementationhas proven to be relatively fast, and the results of ourapproach have been encouraging.