Reconstruction of echocardiographic images for the detection of several congenital heart defects

摘要

The purpose of this thesis was the research of a new segmentation methodto detect and extract the heart cavities in echocardiographic images. To satisfythe clinical practice requirements, it is demanded that the segmentationalgorithm is capable of providing reliable boundary extraction. This is crucialto the correct diagnosis of potential congenital malformations and diseases.The proposed algorithm is based on Log-Gabor wavelets to detect symmetricfeatures in the images, and a level set evolution in order to extractsimultaneously all heart cavities in an accurate way. The formulation of thelevel set uses a new logarithmic based stopping function, which improved theboundary detection when compared to other level set methods.Experiments were performed on echocardiographic images of childrenhearts. The validation of the algorithm included comparisons using stateof-art methods as the manual contours drawn by a trained physician, andthe error quantification using similarity metrics.Our method outperforms the state-of-art in echocardiographic heart segmentation,encouraging its future application in the clinical practice. Thisnew segmentation method has potential to improve the performance of 3Dreconstruction algorithms, since the increased accuracy of the extracted heartcontours simplifies its alignment in space and henceforth the recover of the3D structure.