A method, an apparatus, a computer readable recording medium, and a medical imaging system are provided for segmenting an image of an object from an image of an organ. The method includes: generating a reference model of the object by using a priori knowledge related to the object of the organ; determining whether the first image includes a first area in which a shape of the object is unidentified; and in response to determining that the first image excludes the first area, segmenting a second image of the object from the first image, and in response to determining that the first image includes the first area, estimating a progression direction of the first area from the reference model to segment the second image from the first image.