Title | Hybrid Spot Segmentation in Four-Channel Microarray Genotyping Image Data |
Publication Type | Conference Paper |
Year of Publication | 2006 |
Authors | Abbaspour, M., R. Abugharbieh, M. Podder, B. W. Tripp, and S. J. Tebbutt |
Conference Name | Signal Processing and Information Technology, 2006 IEEE International Symposium on |
Pagination | 11 -16 |
Date Published | aug. |
Keywords | array signal processing, donut-shaped spots, filtering theory, four-channel microarray genotyping image data, four-dimensional clustering approach, fully-automated spot segmentation, genetics, hybrid spot segmentation, image denoising, image segmentation, intensity variations, irregular spot shapes, iterative method, iterative methods, medical image processing, microarray data sets, nonlinear diffusion filtering, pattern clustering, spatial shape detection, spot extraction algorithm, spot masking, two-channel microarray image data |
Abstract | In this paper we present a novel hybrid algorithm for spot segmentation in four-channel genotyping microarray images. A new four-dimensional clustering approach for fully-automated spot segmentation is proposed, along with a new iterative method to automatically identify the number of clusters in a single-spot area. A spatial shape detection step is simultaneously applied, which assists a nonlinear diffusion filtering step in detecting the connected objects, while a spot masking step prevents various noise types from misleading the spot extraction algorithm. The developed analysis system successfully handles various four-channel as well as traditional two-channel microarray image data obtained from different sources. The platform is tested on 34 microarray data sets. The segmentation algorithm accurately segments donut-shaped spots, as well as irregular spot shapes, spots with intensity variations and different noise types effectively. The data extracted from the samples is fed to genotyping algorithms with the results achieving high accuracy rates of up to 99.8% with a call rate of 90.8% |
URL | http://dx.doi.org/10.1109/ISSPIT.2006.270761 |
DOI | 10.1109/ISSPIT.2006.270761 |