Microarray image segmentation using spot morphological model

Abstract

Abstract-The up-to-date segmentation techniques and software programs for microarray image segmentation require human intervention which in turn may detrimentally affect the biological conclusions reached during microarray experiments. In this paper, an automatic approach for segmenting microarray images, based on the morphological modeling of spots, is presented. The conducted experiments have shown that the proposed approach is very effective even when it is applied to noisy images as well as to images containing spots of various shapes and intensities.

Automatic Segmentation of cDNA Microarray Images Using Different Methods

“…To test the efficiency of the proposed methods, a sub-array in the fourth row and the second column was cropped as shown in figure 4. The accuracy of the proposed segmentation methods were analyzed by means of a statistical analysis [15]. A spot was "very efficiently segmented" if at least 90% of the entire spot area was enclosed in the contour of that spot.…”

“…More precisely, using the proposed approach, 91.5% of spots were "very efficiently segmented", and no spurious spot were detected. A spot was "very efficiently segmented" if at least 90% of the entire spot area was enclosed in the contour of that spot [15]. By comparing the results of applying the four presented segmentation methods; Fixed Circle Segmentation, Adaptive Circle Segmentation, Thresholding Segmentation, Adaptive Shape Segmentation methods, It is clearly obvious that the Adaptive Shape Segmentation method can segment noisy microarray images correctly despite of the degree of noise and the shape and size of the spots.…”