Part 1. Automated Change Detection and Characterization in Serial MR Studies of Brain-Tumor Patients

The goal of this study was to create an algorithm which would quantitatively compare serial magnetic resonance imaging studies of brain-tumor patients. A novel algorithm and a standard classify–subtract algorithm were constructed. The ability of both algorithms to detect and characterize changes was compared using a series of digital phantoms. The novel algorithm achieved a mean sensitivity of 0.87 (compared with 0.59 for classify–subtract) and a mean specificity of 0.98 (compared with 0.92 for classify–subtract) with regard to identification of voxels as changing or unchanging and classification of voxels into types of change. The novel algorithm achieved perfect specificity in seven of the nine experiments. The novel algorithm was additionally applied to a short series of clinical cases, where it was shown to identify visually subtle changes. Automated change detection and characterization could facilitate objective review and understanding of serial magnetic resonance imaging studies in brain-tumor patients.

[1]  R B Buxton,et al.  Target‐point combination of MR images , 1991, Magnetic resonance in medicine.

[2]  Alan C. Evans,et al.  A nonparametric method for automatic correction of intensity nonuniformity in MRI data , 1998, IEEE Transactions on Medical Imaging.

[3]  T E Walsh,et al.  Reporting results. , 1969, Archives of otolaryngology.

[4]  M. Christian,et al.  [New guidelines to evaluate the response to treatment in solid tumors]. , 2000, Bulletin du cancer.

[5]  J. Thirion,et al.  Deformation analysis to detect and quantify active lesions in three-dimensional medical image sequences , 1999, IEEE Transactions on Medical Imaging.

[6]  H. Soltanian-Zadeh,et al.  Optimal transformation for correcting partial volume averaging effects in magnetic resonance imaging , 1992, IEEE Conference on Nuclear Science Symposium and Medical Imaging.

[7]  Bradley James Erickson,et al.  A Review of the Automated Detection of Change in Serial Imaging Studies of the Brain , 2004, Journal of Digital Imaging.

[8]  E. Gehan,et al.  Will there be resistance to the RECIST (Response Evaluation Criteria in Solid Tumors)? , 2000, Journal of the National Cancer Institute.

[9]  M. Bronskill,et al.  Noise and filtration in magnetic resonance imaging. , 1985, Medical physics.

[10]  A. Padhani,et al.  The RECIST criteria: implications for diagnostic radiologists , 2001 .

[11]  Guido Gerig,et al.  Exploring the discrimination power of the time domain for segmentation and characterization of active lesions in serial MR data , 2000, Medical Image Anal..

[12]  David H. Laidlaw,et al.  Partial-volume Bayesian classification of material mixtures in MR volume data using voxel histograms , 1997, IEEE Transactions on Medical Imaging.

[13]  Guido Gerig,et al.  Exploring the Discrimination Power of the Time Domain for Segmentation and Characterization of Lesions in Serial MR Data , 1998, MICCAI.

[14]  Hamid Soltanian-Zadeh,et al.  A comparative analysis of several transformations for enhancement and segmentation of magnetic resonance image scene sequences , 1992, IEEE Trans. Medical Imaging.

[15]  Hamid Soltanian-Zadeh,et al.  Optimal linear transformation for MRI feature extraction , 1996, IEEE Trans. Medical Imaging.

[16]  A. Miller,et al.  Reporting results of cancer treatment , 1981, Cancer.

[17]  Nick C Fox,et al.  Modeling brain deformations in Alzheimer disease by fluid registration of serial 3D MR images. , 1998, Journal of computer assisted tomography.

[18]  J N Lee,et al.  The contrast‐to‐noise in relaxation time, synthetic, and weighted‐sum MR images , 1987, Magnetic resonance in medicine.

[19]  Stephen H. Friedberg,et al.  Introduction to linear algebra with applications , 1986 .

[20]  Dominik S. Meier,et al.  Time-series analysis of MRI intensity patterns in multiple sclerosis , 2003, NeuroImage.

[21]  J N Lee,et al.  MR subtraction angiography with a matched filter. , 1988, Journal of computer assisted tomography.

[22]  J P Windham,et al.  Eigenimage Filtering in MR Imaging , 1988, Journal of computer assisted tomography.

[23]  A. Satterfield,et al.  TREATMENT , 1924, California and western medicine.

[24]  Ronald A. Rensink.  Change detection. , 2002, Annual review of psychology.

[25]  Hamid Soltanian-Zadeh,et al.  Partial volume estimation: an improvement for eigenimage method , 2000, Medical Imaging: Image Processing.

[26]  J N Lee,et al.  CNR enhancement in the presence of multiple interfering processes using linear filters , 1990, Magnetic resonance in medicine.

[27]  Hervé Delingette,et al.  Automatic Detection and Segmentation of Evolving Processes in 3D Medical Images: Application to Multiple Sclerosis , 1999, IPMI.

[28]  Alan C. Evans,et al.  Growth patterns in the developing brain detected by using continuum mechanical tensor maps , 2000, Nature.

[29]  A R Padhani,et al.  The RECIST (Response Evaluation Criteria in Solid Tumors) criteria: implications for diagnostic radiologists. , 2001, The British journal of radiology.

[30]  J P Windham,et al.  Eigenimage filtering in MR imaging: An application in the abnormal chest wall , 1989, Magnetic resonance in medicine.

[31]  T. Mikkelsen,et al.  Feature space analysis of MRI , 1998, Magnetic resonance in medicine.

[32]  P. Therasse,et al.  Response evaluation criteria in solid tumors (RECIST): new guidelines. , 2001, Medical and pediatric oncology.

[33]  Badrinath Roysam,et al.  Image change detection algorithms: a systematic survey , 2005, IEEE Transactions on Image Processing.

[34]  C. Jack,et al.  Rate of medial temporal lobe atrophy in typical aging and Alzheimer's disease , 1998, Neurology.

[35]  Gwenn S. Smith,et al.  Alzheimer disease: measuring loss of cerebral gray matter with MR imaging. , 1991, Radiology.

[36]  Elliot R. Mcveigh,et al.  Optimization of survey protocols for mri , 1990, Magnetic resonance in medicine.

[37]  Michael S. Ambinder,et al.  Change blindness , 1997, Trends in Cognitive Sciences.

[38]  Stephanie Green,et al.  Southwest Oncology Group standard response criteria, endpoint definitions and toxicity criteria , 1992, Investigational New Drugs.

[39]  Bryan F. J. Manly,et al.  Multivariate Statistical Methods : A Primer , 1986 .

[40]  R. Kikinis,et al.  Serial magnetic resonance imaging in multiple sclerosis: correlation with attacks, disability, and disease stage , 2000, Journal of Neuroimmunology.

[41]  Hamid Soltanian-Zadeh,et al.  Feature space analysis: effects of MRI protocols , 2000, Medical Imaging: Image Processing.

[42]  A R Padhani,et al.  Commentary. Are current tumour response criteria relevant for the 21st century? , 2000, The British journal of radiology.