Segmentation of echocardiographic images using mathematical morphology

Klingler, J.W.; Vaughan, C.; Fraker, Theodore D.; Andrews, L.T.

doi:10.1109/10.8672

Cited by 105 publications

(47 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Since none of these techniques was satisfactory, morphological operators were used. 11 features can be removed from an image while preserving the essential shape of featu res of interest. Morphological operators have been used in a variety of applications, including biomedical image processing, 11 -u skeletonizing, 1~ and shape description.…”

Section: Algorithmsmentioning

confidence: 99%

“…11 features can be removed from an image while preserving the essential shape of featu res of interest. Morphological operators have been used in a variety of applications, including biomedical image processing, 11 -u skeletonizing, 1~ and shape description. 16 Morphological operations involve the following: dilation, erosion, openings, and dosings.…”

Section: Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Automatic measurements of fetal long bones. A feasibility study.

Thomas¹,

Jeanty²,

Peters³

et al. 1991

Journal of Ultrasound in Medicine

View full text Add to dashboard Cite

We investigated whether it would be possible for a computer to propose values for measurements com-· monly obtained (femur and humerus) during obstetrical sonography. ln this preliminary study, the images were scanned and analyzed off-line using morphological operators. The procedure described allowed us to measure the long bones and has a very high coefficient A n important part of obstetrical ultrasound is the measurement of a series of parameters that are used to assess gestational age and evaluate normalcy of growth. Obtaining these measurements is reasonably simple, yet inter-and intraobserver variations are common, not negligible, and have been well documented. M These variations stem from two main sources of error: the acquisition of the proper image and the correct estimation of where to place the calipers. The acquisition of the proper image can only be improved by training and experience. The correct estimation of where the calipers should be placed depends on the subjective estimation by the operator of the limits of the long bone. Known artifacts, such as side·lobe artifacts, may interfere with the appropriate recognition and placement of the calipers. The purpose of this study was to investigate whether a computer program could be devised that would automatically

show abstract

Section: Algorithmsmentioning

confidence: 99%

Section: Algorithmsmentioning

confidence: 99%

Automatic measurements of fetal long bones. A feasibility study.

Thomas¹,

Jeanty²,

Peters³

et al. 1991

Journal of Ultrasound in Medicine

View full text Add to dashboard Cite

show abstract

“…The expert interpolates the endocardic contour in those areas where it is indistinguishable, relying on his knowledge of the morphology of the ventricular cavity, especially of its overall shape. Despite recent progress reported in the literature [1][2][3][4][5][6][7][8][9][10][11][12], there is no general method for automatic boundary detection that provides satisfactory results in these cases. Most of the detection methods use specific a priori information about the characteristics of the target contours to solve the detection problem.…”

Section: Introductionmentioning

confidence: 99%

A Fourier-Shannon approach to closed contours modelling

1998

View full text Add to dashboard Cite

“…The second approach deals only with the segmentation problem taking into account the speckle properties. The segmentation of echographic images using mathematical morphology was studied in (Klingler et al, 1988). A multiresolution texture segmentation approach that addresses texture characterization, image resolution, and the time to complete the segmentation was developed in (Muzzolini et al, 1993).…”

Section: Introductionmentioning

confidence: 99%

Segmentation of ultrasonic images using Support Vector Machines

Kotropoulos

Pitas

2003

Pattern Recognition Letters

View full text Add to dashboard Cite

Support Vector Machines are a general algorithm based on guaranteed risk bounds of statistical learning theory. They have found numerous applications, such as in classification of brain PET images, optical character recognition, object detection, face verification, text categorization and so on. In this paper we propose the use of support vector machines to segment lesions in ultrasound images and we assess thoroughly their lesion detection ability. We demonstrate that trained support vector machines with a Radial Basis Function kernel segment satisfactorily (unseen) ultrasound B-mode images as well as clinical ultrasonic images.

show abstract

Segmentation of echocardiographic images using mathematical morphology

Cited by 105 publications

References 16 publications

Automatic measurements of fetal long bones. A feasibility study.

Automatic measurements of fetal long bones. A feasibility study.

A Fourier-Shannon approach to closed contours modelling

Segmentation of ultrasonic images using Support Vector Machines

Contact Info

Product

Resources

About