&lt;title&gt;Interactive relaxation labeling for 3D cardiac image analysis&lt;/title&gt;

Higgins, William E.; Hansen, Marit; Sharp, Werner L.

doi:10.1117/12.148692

Cited by 8 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The adaptive thresholding scheme in [10] has now been replaced by interactive relaxation labeling, however, the anatomy-related ambiguity is again resolved using manual delineation. The performance of the scheme presented in [11] is about the same as those presented in [10]. The major difference between the approach presented in this paper and the approaches presented in [10] and [11] is the way the anatomy-related ambiguity is resolved.…”

Section: Segmentation Resultsmentioning

confidence: 72%

“…Since no numerical average difference has been provided, an estimate from the plot indicates that the average difference is between five to ten percent, which is compatible with the performance of this approach. In [11], a method of image segmentation applicable to general circumstances is described and the results of extracting left ventricle chambers are presented. The adaptive thresholding scheme in [10] has now been replaced by interactive relaxation labeling, however, the anatomy-related ambiguity is again resolved using manual delineation.…”

Section: Segmentation Resultsmentioning

confidence: 99%

“…These operations are defined as an ordered combinations of fundamental operations, dilation and erosion, which can be written as 7) (8where and denote the operators opening and closing, respectively, and and denote the operators, erosion, and dilation, respectively. If the translation operation is defined as (9) then the operators erosion and dilation can be written as (10) (11) where is the image and is the structuring element. Note that denotes the reflection of with regard to the origin, denotes a point in space, and is a point in the image .…”

Section: Initial Morphological Operationsmentioning

confidence: 99%

“…The consequence may be a large area attached to or hollow space inside the left ventricle chamber even after the initial morphological operations. Existing schemes dealing with such problem all introduced human interferences one way or another, either outlining the valves by a human operator, or applying additional constraints interactively to the location where the ambiguity is present [11] and [14].…”

Section: Knowledge-based Morphological Operationsmentioning

confidence: 99%

“…To segment such biomedical structures from the 3-D volumetric images, labor-intensive and operator-dependent outlining of region-of-interest has traditionally been employed [8]- [10]. Recently, there have been some attempts working toward a robust and operator-independent segmentation of desired biomedical structures from given volumetric images [11]- [14]. However, these algorithms would require either initial input or interactive interface of a human operator for every set of images to overcome the difficulties in segmenting the spatially varying intensity as well as in identifying the ambiguous anatomical structures.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Image segmentation via adaptive K-mean clustering and knowledge-based morphological operations with biomedical applications

Chen

Luo

Parker

1998

IEEE Trans. on Image Process.

247

View full text Add to dashboard Cite

Image segmentation remains one of the major challenges in image analysis. In medical applications, skilled operators are usually employed to extract the desired regions that may be anatomically separate but statistically indistinguishable. Such manual processing is subject to operator errors and biases, is extremely time consuming, and has poor reproducibility. We propose a robust algorithm for the segmentation of three-dimensional (3-D) image data based on a novel combination of adaptive K-mean clustering and knowledge-based morphological operations. The proposed adaptive K-mean clustering algorithm is capable of segmenting the regions of smoothly varying intensity distributions. Spatial constraints are incorporated in the clustering algorithm through the modeling of the regions by Gibbs random fields. Knowledge-based morphological operations are then applied to the segmented regions to identify the desired regions according to the a priori anatomical knowledge of the region-of-interest. This proposed technique has been successfully applied to a sequence of cardiac CT volumetric images to generate the volumes of left ventricle chambers at 16 consecutive temporal frames. Our final segmentation results compare favorably with the results obtained using manual outlining. Extensions of this approach to other applications can be readily made when a priori knowledge of a given object is available.

show abstract