Both normal aging and neurodegenerative diseases such as Alzheimer’s disease (AD) cause morphological changes of the brain due to neurodegeneration. As neurodegeneration due to disease may be difficult to distinguish from that of normal aging, interpretation of magnetic resonance (MR) brain images in the context of diagnosis of neurodegenerative diseases is challenging, especially in the early stages of the disease. This thesis presented comprehensive models of the aging brain and novel computer-aided diagnosis methods, based on advanced, quantitative analysis of brain MR images, facilitating the differentiation between normal and abnormal neurodegeneration. I aimed to evaluate and develop methods for clinical decision support using features derived from MR brain images: I evaluated a classification method to predict global cognitive decline in the general population, evaluated five brain segmentation methods and developed a spatio-temporal model of morphological differences in the brain due to normal aging. To create this model I developed two novel techniques that allow performing non-rigid groupwise image registration on large imaging datasets. The novel aging brain models and computer-aided diagnosis methods facilitate the differentiation between normal and abnormal neurodegeneration. This will help in establishing more accurate diagnoses of patients, and in identifying patients at risk of developing neurodegenerative disease before symptoms emerge. In the future, the method’s performance and efficacy should be evaluated in clinical practice.

, , ,
W.J. Niessen (Wiro) , S. Klein (Stefan) , D.H.J. Poot (Dirk)
Erasmus University Rotterdam
hdl.handle.net/1765/115711

Huizinga, W. (2018). Advanced Image Analysis for Modeling the Aging Brain. Retrieved from http://hdl.handle.net/1765/115711