Abstract: The invention relates to novel imaging-based biomarkers for characterizing the structure or function of a human or animal brain. These biomarkers can be a weighted confluency sum score (WCSS) or a percent shielding by brain lesions (SbBL). Methods implementing these biomarkers are also disclosed.

Abstract: The invention relates to novel imaging-based biomarkers for characterizing the structure or function of a human or animal brain. These biomarkers can be a weighted confluency sum score (WCSS) or a percent shielding by brain lesions (SbBL). Methods implementing these biomarkers are also disclosed.

Abstract: A scanner (10) is used to provide images for automated diagnoses of neurodegenerative diseases, such as Alzheimers disease. The images are registered (90) to a template (78). The aligned image is analyzed (60) in relation to reference image data (76, 80) which has been registered to the template which is contained in a knowledge maintenance engine (70) for similar patterns of hypo-intensity that would indicate (in the case of an FDG tracer) reduced glucose uptake in the brain. The most appropriate reference images for the analysis of the present study are chosen by a filter (74). The present study is then given a dementia score (84) as a diagnostic feature vector that indicates to a clinician the type and severity of the ailment based on the analysis. The scanner (10) can produce PET or other metabolic and MR images for diagnosis. The MR can be used to measure blood flow rate into the brain. From the blood flow rate and the metabolic image, tracer, e.g.

Abstract: When detecting and classifying hypo-metabolic regions in the brain to facilitate dementia diagnosis, a patient's brain scan image, generated using an FDG-PET scan, is compared to a plurality of hypo-metabolic region patterns in brain scan images associated with a plurality of types of dementia. In a fully automated mode, the patient's scan is compared to all scans stored in a knowledge base, and a type of dementia associated with a most likely match is output to a user along with a highlighted image of the patient' s brain. In a semi-automated mode, a user specifies two or more types of dementia, and the patient's scan is compared to scans typical of the specified types. Diagnosis information including respective likelihoods for each type is then output to the user. Additionally, the user can adjust a threshold significance level to increase or decrease a number of voxels that are included in hypo-metabolic regions highlighted in the patient' brain scan image.

Abstract: When detecting and classifying hypo-metabolic regions in the brain to facilitate dementia diagnosis, a patient's brain scan image, generated using an FDG-PET scan, is compared to a plurality of hypo-metabolic region patterns in brain scan images associated with a plurality of types of dementia. In a fully automated mode, the patient's scan is compared to all scans stored in a knowledge base, and a type of dementia associated with a most likely match is output to a user along with a highlighted image of the patient' s brain. In a semi-automated mode, a user specifies two or more types of dementia, and the patient's scan is compared to scans typical of the specified types. Diagnosis information including respective likelihoods for each type is then output to the user. Additionally, the user can adjust a threshold significance level to increase or decrease a number of voxels that are included in hypo-metabolic regions highlighted in the patient' brain scan image.