Temporally Consistent Probabilistic Detection of New Multiple Sclerosis Lesions in Brain MRI

• Published in: IEEE transactions on medical imaging Vol. 32; no. 8; pp. 1490 - 1503
• Main Authors: Elliott, Colm, Arnold, Douglas L., Collins, D. Louis, Arbel, Tal
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.08.2013
• Subjects: Bayes methods; Bayes Theorem; Bayesian inference; Brain - pathology; change detection; Databases, Factual; Humans; Image Interpretation, Computer-Assisted - methods; Image segmentation; Joints; Lesions; machine learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Manuals; multiple sclerosis; Multiple Sclerosis - diagnosis; Multiple Sclerosis - pathology; new lesion segmentation; Probabilistic logic; Reproducibility of Results; subtraction imaging
• ISSN: 0278-0062; 1558-254X
• DOI: 10.1109/TMI.2013.2258403

Detection of new Multiple Sclerosis (MS) lesions on magnetic resonance imaging (MRI) is important as a marker of disease activity and as a potential surrogate for relapses. We propose an approach where sequential scans are jointly segmented, to provide a temporally consistent tissue segmentation while remaining sensitive to newly appearing lesions. The method uses a two-stage classification process: 1) a Bayesian classifier provides a probabilistic brain tissue classification at each voxel of reference and follow-up scans, and 2) a random-forest based lesion-level classification provides a final identification of new lesions. Generative models are learned based on 364 scans from 95 subjects from a multi-center clinical trial. The method is evaluated on sequential brain MRI of 160 subjects from a separate multi-center clinical trial, and is compared to 1) semi-automatically generated ground truth segmentations and 2) fully manual identification of new lesions generated independently by nine expert raters on a subset of 60 subjects. For new lesions greater than 0.15 cc in size, the classifier has near perfect performance (99% sensitivity, 2% false detection rate), as compared to ground truth. The proposed method was also shown to exceed the performance of any one of the nine expert manual identifications.