Segmentation of the Left Atrium and Pulmonary Veins from Contrast-Enhanced MR Images

Atrial brillation is an important cardiovascular disease causing cardiac malfunction. The left atrium and pulmonary veins are the structures most a ected. Radio-frequency catheter ablation has now become a standard procedure for correcting atrial brillation. The procedure is minimally invasive and pre-planning the procedure is essential. It is normally required to image the atrium. Segmentation of the left atrium and pulmonary veins from medical images is an important problem and a necessary step for further analysing the left atrium. This dissertation describes techniques for segmenting the left atrium from MR angiography images. It also describes methods for extracting sub-atrial structures of the atrium such as the central atrial body and pulmonary veins. As pulmonary veins of the left atrium have complex vessel networks, the centrelines of these vessels are extracted allowing for better visualisation and compact representation. Furthermore, the dissertation describes a framework for analysing the atrium. The pulmonary drainage trees are reconstructed using graph structures. Important atrial characteristics relevant to catheter ablation procedures are quanti ed. These include atrial anatomy and ostial diameters. The methods described in the dissertation are evaluated on real patient datasets and compared against manual approaches. A comparative study of the proposed left atrium segmentation algorithm with an existing approach showed that the proposed approach yields better segmentations. Furthermore, results show that the proposed techniques for pulmonary drainage reconstruction correctly compute and classify atrial anatomy in the majority of cases. The computation of ostial diameters also show close agreement with gold-standard measurements. A series of studies performed to investigate the e ect of user parameters on the quality of i segmentation and measurements obtained show reproducibility of results. It is envisaged that the methods proposed will improve the e cacy of catheter ablation by providing useful and accurate atrial characteristics and information