Intensity normalization of DaTSCAN SPECT imaging using a model-based clustering approach

• Published in: Applied soft computing Vol. 37; pp. 234 - 244
• Main Authors: Brahim, A., Górriz, J.M., Ramírez, J., Khedher, L.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.12.2015
• Subjects: Computer aided diagnosis (CAD); DaTSCAN SPECT images; Gaussian mixture models; Intensity normalization; Parkinson's disease; Computer aided diagnosis (CAD); Gaussian mixture models; Parkinson's disease; DaTSCAN SPECT images; Intensity normalization

[Display omitted] •A 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...