Abstract:
We propose an ultrasound speckle filtering method that preserves edge features and filters tissue-dependent complex speckle noises. Phase asymmetry (PAS), a phase congruence-based edge significance measure, takes 0 in non-edge smooth regions, 1 at the idea step edge, and intermediate values at slowly varying ramp edges.
We propose a new fractional TV framework to achieve the best despeckling performance with ramp edge preservation and reduce the staircase effect caused by integral-order filters by using the PAS metric to design weighting coefficients to balance fractional-order anisotropic diffusion and total variation (TV) filters in TV cost function.
To preserve low-contrast edges in diffusion filtering, we use the PAS metric to design a new fractional-order diffusion coefficient. Finally, the PAS metric-based adaptive fractional-order diffusion filter enhances weak edges in spatially transitional areas between objects. Gradient descent minimizes the fractional TV model to denoise the image.
The proposed method outperforms other state-of-the-art ultrasound despeckling filters for speckle reduction and feature preservation in visual evaluation and quantitative indices.
The mean and median dice similarity coefficients for breast ultrasound segmentation are 96.25% and 96.15%, respectively, and feature similarity indices have reached 0.867, 0.844, and 0.834 under three noise levels.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
