Automatic Segmentation of the Left Atrium

Segmentation of the left atrium is vital for pre-operative assessment of its anatomy in radio-frequency catheter ablation surgery, which is commonly used for treating atrial fibrillation. In this paper we present an automatic approach for segmenting the left atrium and its pulmonary veins from MR angiography (MRA) data sets. Based on the notion that in MRA the atrium becomes connected to surrounding structures via partial volume affected voxels and narrow vessels, the atrium can be separated if these regions are characterized and identified. The blood pool, obtained by subtracting the preand post-contrast scans, is first segmented using a regiongrowing approach. The segmented blood pool is then subdivided into disjoint subdivisions based on its Euclidean distance transform. These subdivisions are then merged automatically starting from a seed point and stopping at points where the atrium connects to a neighbouring structure. The resulting merged subdivisions produce the segmented atrium.