Intensity normalization of DaTSCAN SPECT imaging using a model-based clustering approach
| Autor: | Javier Ramírez, Abdelbasset Brahim, Laila Khedher, Juan Manuel Górriz |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
business.industry
Gaussian Pattern recognition computer.software_genre Mixture model symbols.namesake Kernel (image processing) Voxel Spect imaging Expectation–maximization algorithm symbols Artificial intelligence Linear combination business Quantization (image processing) computer Software Mathematics |
| Zdroj: | Applied Soft Computing. 37:234-244 |
| ISSN: | 1568-4946 |
| DOI: | 10.1016/j.asoc.2015.08.030 |
| Popis: | Graphical abstractDisplay Omitted HighlightsA novel method for intensity normalization of DaTSCAN SPECT brain images.The proposed methodology is based on spatial Gaussian mixture models (GMMs).The intensity values in the non-specific regions are filtered by the GMM.Intersubject differences in the non-specific regions are reduced. This paper presents a novel method for intensity normalization of DaTSCAN SPECT brain images. The proposed methodology is based on Gaussian mixture models (GMMs) and considers not only the intensity levels, but also the coordinates of voxels inside the so-defined spatial Gaussian functions. The model parameters are obtained according to a maximum likelihood criterion employing the expectation maximization (EM) algorithm. First, an averaged control subject image is computed to obtain a threshold-based mask that selects only the voxels inside the skull. Then, the GMM is obtained for the DaTSCAN-SPECT database, performing space quantization by populating it with Gaussian kernels whose linear combination approximates the image intensity. According to a probability threshold that measures the weight of each kernel or "cluster" in the striatum area, the voxels in the non-specific region are intensity-normalized by removing clusters whose likelihood is negligible. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect