Image enhancement in intensity projected multichannel MRI using spatially adaptive directional anisotropic diffusion
Anisotropic Diffusion is widely used for noise reduction with simultaneous preservation of vascular structures in maximum intensity projected (MIP) angiograms. However, extension to minimum intensity projected (mIP) venograms in Susceptibility Weighted Imaging (SWI) poses difficulties due to spatially varying baseline. Here, we introduce a modified version of the directional anisotropic diffusion which allows us to simultaneously reduce the noise and enhance vascular structures reconstructed using both M/mIP angiograms. This method is based on spatial adaptation of the diffusion function, separately in the directions of the gradient, and along those of the minimum and maximum curvatures. The existing approach of directional anisotropic diffusion uses binary switched diffusion function to ensure diffusion along the direction of maximum curvature stopped near the vessel borders. Here, the choice of a threshold for detecting the upper limit of diffusion becomes difficult in the presence of spatially varying baseline. Also, the approach of using vesselness measure to steer the diffusion process results in structural discontinuities due to junction suppression in mIP. The merits of the proposed method include elimination of the need for an apriori choice of a threshold to detect the vessel, and problems due to junction suppression. The proposed method is also extended to multi-channel phase contrast angiogram.
Code (0)
등록된 구현이 없습니다.
Tasks
Image EnhancementSimilar Papers 제목 키워드 기반
Spatially constrained vs. unconstrained filtering in neural spatiospectral filters for multichannel speech enhancement
When using artificial neural networks for multichannel speech enhancement, filtering is often achieved by estimating a complex-valued mask that is applied to all or one reference channel of the input signal. The estimati…
Speech EnhancementStudent-Teacher Learning for BLSTM Mask-based Speech Enhancement
Spectral mask estimation using bidirectional long short-term memory (BLSTM) neural networks has been widely used in various speech enhancement applications, and it has achieved great success when it is applied to multich…
Speech Enhancementspeech-recognitionSpeech RecognitionImproving multichannel speech enhancement through accurate room-acoustic simulations
Room-acoustic simulations are widely used to augment training data for deep-learning-based speech enhancement. While most pipelines rely on simplified geometrical acoustics, wave-based approaches offer greater physical a…
Speech EnhancementGradient-Based Low-Light Image Enhancement
A low-light image enhancement is a highly demanded image processing technique, especially for consumer digital cameras and cameras on mobile phones. In this paper, a gradient-based low-light image enhancement algorithm i…
Image EnhancementLow-Light Image EnhancementRobust registration of medical images in the presence of spatially-varying noise
Spatially-varying intensity noise is a common source of distortion in medical images. Bias field noise is one example of such a distortion that is often present in the magnetic resonance (MR) images or other modalities s…
Image Registration