Computer-aided localization of neurological diseases
Y. Parlar · 1991
Computers in medicine has brought new dimensions and better understanding of uncertainties in the field of medical sciences in the last decade. This thesis is focused upon the localization of neurological lesions in the human nervous system. It relates clinical neurological test outcomes to pathways of function or malfunction. Certain methods are proposed--empirical, stochastic, deterministic--to estimate the spatial distributions of lesion probabilities. First, a Bayesian model is presented to estimate the posterior probability of lesion from a priori information, based on the test outcomes. Due to unavailable data alternative methods and models are presented: Regression Analysis, Monte Carlo simulation, and finally a new model known as Logistic Sigmoid Nonlinearity is proposed for probability estimation. This dissertation analyzes each of these models and alternative methodologies in detail.