The comparison of serial MR examinations of the brain is a procedure performed frequently by neuroradiologists for diseases such as tumors, multiple sclerosis, Alzheimer’s disease, and others. The primary objective of such imaging is to detect and characterize any changes. Comparison of serial MR studies of brain-tumor patients is a task whose difficulty is widely recognized. This difficulty results from the method of data presentation, as well as factors related to image acquisition and processing. Various methods have been used to effect serial comparisons, including manual inspection, measurement sampling, volumetrics, warping, and temporal analysis. However, each of these methods possesses both merits and shortcomings. Mayo Clinic investigators have developed an automated system which compares two serial MR brain studies for the purposes of detecting and characterizing changes in a series of images from a given patient over time. The system has been designed to be relatively unaffected by changes in scanner and acquisition parameters, and requires minimal or no user intervention.
An automated system to identify and quantify lesions in the brain in magnetic resonance imaging (MRI) data, including lesions arising from metastatic tumors, multiple sclerosis, and other white matter disease processes.
Stage of Development
It has been shown that this algorithm can separate cases which are stable from those which are progressing. Furthermore, the algorithm was also shown to detect progression in a substantial fraction of cases judged to be stable by humans but which proceeded to progression in a short period of time, which may allow for earlier detection. This software system has been implemented in the Department of Radiology at Mayo Clinic.
- Patriarche J, Erickson B., Part 1. Automated change detection and characterization in serial MR studies of brain-tumor patients. J Digit Imaging. 2007 Sept; 20(3): 203-22.
- Patriarche J, Erickson B., Part 2. Automated change detection and characterization applied to serial MR of brain tumors may detect progression earlier than human experts. J Digit Imaging. 2007 Dec; 20(4):321-8.
- Erickson BJ, et al., Optimal presentation modes for detecting brain tumor progression. AJNR Am J Neuroradiol. 2011 Oct; 32(9): 1652-1657.