An a contrario approach for change detection in 3D multimodal images: application to multiple sclerosis in MRI

Estimating significant changes between two images remains a challenging problem in medical image processing. This paper proposes a non-parametric region based method to detect significant changes in 3D multimodal Magnetic Resonance (MR) sequences. The proposed approach relies on an a contrario model which defines significant changes as events with very low probability. We adapt the a contrario framework to deal with multimodal images from which are extracted measures related to intensity and volume changes. Two fusion rules are carefully designed to handle a set of decision thresholds and a set of image measures. The final decision is taken using multiple testing procedures. The efficiency of the algorithm is demonstrated in the context of multiple sclerosis (MS) lesion analysis over time in multimodal MR sequences. We evaluate the proposed method on synthetic images using the Brainweb simulator. Finally, promising results on multimodal sequences on clinical data are presented.