Magnetic resonance imaging (MRI) is the modality of choice as far as imaging diagnosis of pathologies in the pituitary gland is concerned. Furthermore, the advent of dynamic contrast enhanced (DCE) has enhanced the capability of this modality in detecting minute benign but endocrinologically significant tumors called microadenoma. These lesions are visible with difficulty and a low confidence level in routine MRI sequences, even after administration of intravenous gadolinium. Techniques to enhance the visualization of such foci would be an asset in improving the overall accuracy of DCE-MRI for detection of pituitary microadenomas. The present study proposes an algorithm for postprocessing DCE-MRI data using multistable stochastic resonance (MSSR) technique. Multiobjective ant lion optimization optimizes the contrast enhancement factor (CEF) and anisotropy of an image by varying the parameters associated with the dynamics of MSSR. The marked regions of interest (ROIs) are labeled as normal and microadenoma of pituitary obtained with increased level of accuracy and confidence using proposed algorithm. The increased difference between the mean intensity curves obtained using these ROIs validated the obtained subjective results. Furthermore, the proposed MSSR-based algorithm has been evaluated on standard T1 and T2 weighted BrainWeb dataset images and quantified in terms of CEF, peak signal to noise ratio (PSNR), structure similarity index measure (SSIM), and universal quality index (UQI). The obtained mean values of CEF 1.22, PSNR 27.68, SSIM 0.75, UQI 0.83 for twenty dataset images were highest among considered contrast enhancement algorithms for the comparison.
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Electrical and Electronic Engineering
- Health Information Management