Invariant geometric evolutions of surfaces and volumetric smoothing
SIAM Journal on Applied Mathematics
IPMI '99 Proceedings of the 16th International Conference on Information Processing in Medical Imaging
MICCAI '98 Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention
Compensation of Spatial Inhomogeneity in MRI Based on a Parametric Bias Estimate
VBC '96 Proceedings of the 4th International Conference on Visualization in Biomedical Computing
Statistical Analysis of Longitudinal MRI Data: Applications for Detection of Disease Activity in MS
MICCAI '02 Proceedings of the 5th International Conference on Medical Image Computing and Computer-Assisted Intervention-Part I
Segmentation of brain tumors in 4D MR images using the hidden Markov model
Computer Methods and Programs in Biomedicine
Bayesian classification of multiple sclerosis lesions in longitudinal MRI using subtraction images
MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part II
STREM: a robust multidimensional parametric method to segment MS lesions in MRI
MICCAI'05 Proceedings of the 8th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Extracting evolving pathologies via spectral clustering
IPMI'13 Proceedings of the 23rd international conference on Information Processing in Medical Imaging
Hi-index | 0.00 |
This paper presents a new approach for the automatic segmentation and characterization of active MS lesions in 4D data of multiple sequences. Traditional segmentation of 4D data applies individual 3D spatial segmentation to each image data set, thus not making use of correlation over time. More recently, a time series analysis has been applied to 4D data to reveal active lesions [3]. However, misregistration at tissue borders led to false positive lesion voxels. Lesion development is a complex spatio-temporal process, consequently methods concentrating exclusively on the spatial or temporal aspects of it cannot be expected to provide optimal results. Active MS lesions were extracted from the 4D data in order to quantify MR-based spatio-temporal changes in the brain. A spatio-temporal lesion model generated by principal component analysis allowed robust identification of active MS lesions overcoming the drawbacks of traditional purely spatial or purely temporal segmentation methods.