LEVEL SET SNAKE ALGORITHMS ON THE FETAL HEART

Abstract

The fetal heart has very thin intra-chamber walls which are often not resolved by ultrasound scanners and may drop out as a result of imaging. In order to measure blood volumes from all chambers in isolation, deformable model approaches were used to segment the chambers and fill in the missing structural information. Three level set algorithms in the fetal cardiac segmentation literature (two without and, one with the use of a shape prior) were applied to real ultrasound data. The shape prior term was extracted from the shape prior level set and incorporated into the amorphous snakes for a fairer comparison. To our knowledge this is the first time these existing fetal cardiac non shape based segmentation algorithms have been modified for shape awareness in this way