AUTOMATED EDGE-DRIVEN MARKOV RANDOM FIELD SEGMENTATION OF EX VIVO MOUSE BRAIN MRM IMAGES

In biological image processing the segmentation of a volume is, although tedious, required for many applications, like the comparison of structures and annotation purposes. To automate this process, we present a segmentation method for various structures of the mouse brain which consists of two parts. First a rough affine atlas based registration was performed and second, the edges were refined by an adapted Markov random field clustering approach. The segmentations results were compared to manual segmentations of two experts which resulted in good kappa indices for 11 out of 16 structures. The presented segmentation method is quick, intuitive and suitable for biological objectives, like comparison, annotation but also registration purposes