4D Connected component labelling applied to quantitative analysis of MS lesion temporal development
David Metcalf, Ron Kikinis, Charles R.G. Guttmann, Lucia Maria Vaina, Ferenc Andras Jolesz · Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society · 1992
We have developed a 4D connected component labeling algorithm to identify automatically individual lesions on MRI brain images of multiple sclerosis patients, and to follow the changes in each lesion over time. We were also able to use this algorithm as a noise reduction filter to remove misclassified components from the binarized segmentations of the images.