Intensity normalization of DaTSCAN SPECT imaging using a model-based clustering approach |
| |
Affiliation: | 1. Department of Nuclear Medicine, Odense University Hospital, Sønder Boulevard 29, Odense DK-5000, Denmark;2. Institute of Clinical Research, University of Southern Denmark, Winsløwparken 19, DK-5000, Odense, Denmark;3. Department of Urology, Odense University Hospital, Sønder Boulevard 29, Odense DK-5000, Denmark;1. School of Computer Science and Engineering, Xi''an University of Technology, Xi''an 710048, China;2. Shaanxi Key Laboratory for Network Computing and Security Technology, Xi''an 710048, China |
| |
Abstract: | 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. |
| |
Keywords: | Parkinson's disease DaTSCAN SPECT images Computer aided diagnosis (CAD) Intensity normalization Gaussian mixture models |
本文献已被 ScienceDirect 等数据库收录! |
|