Ultrasound Image Enhancement Using Structure-Based Filtering
| Autor: | Cho-Li Yen, Guan-Zhi Chen, Shyh-Kuang Ueng |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2014 |
| Předmět: |
Article Subject
Computer science Normal Distribution lcsh:Computer applications to medicine. Medical informatics Kidney General Biochemistry Genetics and Molecular Biology Speckle pattern Image Interpretation Computer-Assisted Median filter Image Processing Computer-Assisted Humans Computer vision Ultrasonography Artifact (error) General Immunology and Microbiology Pixel business.industry Applied Mathematics Ultrasound General Medicine Filter (signal processing) Diffusion Tensor Imaging Liver Modeling and Simulation lcsh:R858-859.7 Anisotropy Artificial intelligence business Artifacts Linear filter Algorithms Software Diffusion MRI Research Article |
| Zdroj: | Computational and Mathematical Methods in Medicine Computational and Mathematical Methods in Medicine, Vol 2014 (2014) |
| ISSN: | 1748-6718 1748-670X |
| Popis: | Ultrasound images are prone to speckle noises. Speckles blur features which are essential for diagnosis and assessment. Thus despeckling is a necessity in ultrasound image processing. Linear filters can suppress speckles, but they smooth out features. Median filter based despeckling algorithms produce better results. However, they may produce artifact patterns in the resulted images and oversmooth nonuniform regions. This paper presents an innovative despeckle procedure for ultrasound images. In the proposed method, the diffusion tensor of intensity is computed at each pixel at first. Then the eigensystem of the diffusion tensor is calculated and employed to detect and classify the underlying structure. Based on the classification result, a feasible filter is selected to suppress speckles and enhance features. Test results show that the proposed despeckle method reduces speckles in uniform areas and enhances tissue boundaries and spots. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text