چكيده به لاتين
Abstract
Two challenging issues for accurate and effective human interpretation and computer-assisted analysis are: 1-Noise suppression and 2-Accurate analysis of small transient motions of myocardium and valves during real time visualization. This research seeks to address these challenges by introducing a novel framework based on temporal information and sparse representation. The proposed method involves analysing intensity variation time curves (IVTCs) assessed in each pixel.
For noise reduction propose using an over-complete dictionary that contains prototype signal-atoms, IVTCs can be reconstructed as linear combinations of a few of these atoms. The performance of the proposed method was then evaluated and compared with other speckle reduction filters. The experimental results demonstrate that the proposed algorithm can be used to achieve better-preserved edges and reduce blurring.
For accurate analysis of small transient motions, a higher frame rate video may reduce this difficulty, and temporal super resolution (TSR) is useful for illustrating the fast-moving structures. For this propose, we designed both low-resolution and high-resolution over-complete dictionaries based on prior knowledge of the temporal signals and a set of pre-specified known functions. The IVTCs can then be described as linear combinations of a few prototype atoms in the low-resolution dictionary. We used the Bayesian Compressive Sensing (BCS) sparse recovery algorithm to find the sparse coefficients of the signals. We extracted the sparse coefficients and the corresponding active atoms in the low-resolution dictionary in order to construct new sparse coefficients corresponding to the high-resolution dictionary. Using the estimated atoms and the high-resolution dictionary, a new IVTC with more samples was constructed. Finally, by placing the new IVTC signals in the original IVTC positions, we were able to reconstruct the original echocardiography video with more frames. The proposed method which applied on 2D and 3D echocardiographic images,does not require training of low-resolution and high-resolution dictionaries. Nor does it require motion estimation; it does not blur fast-moving objects, and does not have blocking artifacts.
Keywords: echocardiographic images, noise reduction, temporal information, sparse representation, Temporal super resolution
