Abstract: An automated process classifies MRI or other medical imaging data as belonging to neurological structures. A training part of the process uses a baseline data set with accompanying classification map, as well as an arbitrary number of training data sets, also with accompanying classification maps. Each training data set is registered to the baseline data set using a warp-based automated registration algorithm. The resulting probability map, mean values and covariance matrices are used to classify structures in an image data set using a maximum likelihood criterion.

Abstract: In a human or animal organ or other region of interest, specific objects, such as liver metastases and brain lesions, serve as indicators, or biomarkers, of disease. In a three-dimensional image of the organ, the biomarkers are identified and quantified. Multiple three-dimensional images can be taken over time, in which the biomarkers can be tracked over time. Statistical segmentation techniques are used to identify the biomarker in a first image and to carry the identification over to the remaining images. Regions of normal and abnormal parameters within the 3D biomarker structure are identified. The information is used to highlight or visualize abnormal regions on the original 2D tomographic images.

Abstract: In a solid tumor or other cancerous tissue in a human or animal patient, specific objects or conditions serve as indicators, or biomarkers, of cancer and its progress. In a three-dimensional image of the region of interest, the biomarkers are identified and quantified. Multiple three-dimensional images can be taken over time, in which the biomarkers can be tracked over time. Statistical segmentation techniques are used to identify the biomarker in a first image and to carry the identification over to the remaining images.