Unsupervised 2D gel electrophoresis image segmentation based on active contours
Pattern Recognition
Hi-index | 0.00 |
This work addresses the detection of protein spots in 2D gel electrophoresis images. A novel morphology-based approach is proposed, which utilizes the dilation operator for the localization of regional intensity maxima associated with protein spots. A disk-shaped structuring element (SE) is selected in agreement with the prevalent roundish shape of the majority of protein spots. Thus, spots within rectangular-shaped streaks are correctly detected. SE size is set considering that a certain radius value allows the discrimination of individual spots located in complex spot regions as well as small-sized spots. Moreover, spurious intensity maxima associated with noise are ignored by applying regional intensity constraints. The results of the experimental evaluation lead to the conclusion that the proposed approach detects more actual protein spots and less false spots than a renowned 2D-GE image analysis software package. Furthermore, it does not require user intervention.