Search

Alzheimer’s disease, the most common form of dementia, is an extremely serious health problem, and one that will become even more so in the coming decades as the global population ages. This has led to a massive effort to develop both new treatments for the condition and new methods of diagnosis; in fact the two are intimately linked as future treatments will depend on earlier diagnosis, which in turn requires the development of biomarkers that can be used to identify and track the disease. This is made possible by studies such as the Alzheimer’s disease neuroimaging initiative which provides previously unimaginable quantities of imaging and other data freely to researchers. It is the task of early diagnosis that this thesis focuses on. We do so by borrowing modern machine learning techniques, and applying them to image data. In particular, we use Gaussian processes (GPs), a previously neglected tool, and show they can be used in place of the more widely used support vector machine (SVM). As combinations of complementary biomarkers have been shown to be more useful than the biomarkers are individually, we go on to show GPs can also be applied to integrate different types of image and non-image data, and thanks to their properties this improves results further than it does with SVMs. In the final two chapters, we also look at different ways to formulate both the prediction of conversion to Alzheimer’s disease as a machine learning problem and the way image data can be used to generate features for input as a machine learning algorithm. Both of these show how unconventional approaches may improve results. The result is an advance in the state-of-the-art for a very clinically important problem, which may prove useful in practice and show a direction of future research to further increase the usefulness of such methods.

Populations of pathogenic and non-pathogenic bacteria were studied in Phaseolus vulgaris. Virulent isolates of the homologous pathogen Pseudomonas phaseolicola multiplied at rates and to final populations which suggested that no inhibitory reaction with the plant was involved. Necrosis-inducing heterologous pathogens multiplied at lower rates and to lower final populations than the homologue. Non-pathogens were static in tissue. A suggestion made elsewhere that the behaviour of non-pathogens and pathogens was determined by their different oxidase activities was not supported. The growth of non-pathogenic bacteria co-inoculated into bean leaves with the homologous or heterologous pathogens was stimulated, indicating that the plant intercellular environment was modified by pathogens to favour general bacterial growth. Inoculation of non-pathogens with nutrient amendments did not affect their behaviour in plant tissue, but when leaves were held in water-soaked conditions following inoculation, non-pathogens multiplied and the heterologous pathogens were stimulated to the same rate and almost to the same final population of the homologue. Free water appears to be the initial limiting factor for the multiplication of bacteria in the intercellular spaces. The growth of heterologous pathogens co-inoculated with the homologue was also stimulated. Pathogenic specificity may be explained by the action of bacterial toxins acting directly or indirectly to increase host cell membrane permeability. When beans were challenged with high concentrations of inocula of non-pathogens, a general inhibition occurred against pathogenic bacteria which were subsequently inoculated. Inhibition induced in plants by bacteria may regulate their final populations.