Neural networks for volumetric MR imaging of the brain
Erol Gelenbe, Yu Feng, K Ranga, Rama Krishnan · 2002
There has been a great increase in our knowledge of the biochemical machinery of the nervous system. This knowledge has been primarily developed from in vitro and in vivo experiments in invertebrates and mammals. With new imaging technologies such as MRI and positron emission tomography (PET) it has become possible to explore the integrated central nervous system (both biochemically and biophysically) in living humans. A major limitation in utilizing these techniques in an optimal fashion has been the lack of sophisticated image analysis systems which can extract the relevant information from the images in an automated or semiautomated manner. Brain MR images contain massive information requiring lengthy and complex interpretation, quantitative evaluation, and sophisticated interpretation. We survey the clinical and research needs for brain imaging. We discuss the use of novel artificial neural networks which have a recurrent structure to extract precise morphometric information from MRI scans of the human brain. Experimental data using our novel approach is presented and suggestions are made for future research.