Adaptive image inversion of contrast 3D echocardiography for enabling automated analysis

Research output: Contribution to journal › Article › peer-review

Standard

Adaptive image inversion of contrast 3D echocardiography for enabling automated analysis. / Shaheen, Anjuman; Rajpoot, Kashif.

In: Computers in Biology and Medicine, Vol. 63, 01.08.2015, p. 99-107.

Research output: Contribution to journal › Article › peer-review

Harvard

Shaheen, A & Rajpoot, K 2015, 'Adaptive image inversion of contrast 3D echocardiography for enabling automated analysis', Computers in Biology and Medicine, vol. 63, pp. 99-107. https://doi.org/10.1016/j.compbiomed.2015.05.009

APA

Shaheen, A., & Rajpoot, K. (2015). Adaptive image inversion of contrast 3D echocardiography for enabling automated analysis. Computers in Biology and Medicine, 63, 99-107. https://doi.org/10.1016/j.compbiomed.2015.05.009

Vancouver

Shaheen A, Rajpoot K. Adaptive image inversion of contrast 3D echocardiography for enabling automated analysis. Computers in Biology and Medicine. 2015 Aug 1;63:99-107. https://doi.org/10.1016/j.compbiomed.2015.05.009

Author

Shaheen, Anjuman ; Rajpoot, Kashif. / Adaptive image inversion of contrast 3D echocardiography for enabling automated analysis. In: Computers in Biology and Medicine. 2015 ; Vol. 63. pp. 99-107.

Bibtex

@article{18d456f62f3e4e83b86d469184f20526,
title = "Adaptive image inversion of contrast 3D echocardiography for enabling automated analysis",
abstract = "IntroductionContrast 3D echocardiography (C3DE) is commonly used to enhance the visual quality of ultrasound images in comparison with non-contrast 3D echocardiography (3DE). Although the image quality in C3DE is perceived to be improved for visual analysis, however it actually deteriorates for the purpose of automatic or semi-automatic analysis due to higher speckle noise and intensity inhomogeneity. Therefore, the LV endocardial feature extraction and segmentation from the C3DE images remains a challenging problem.MethodsTo address this challenge, this work proposes an adaptive pre-processing method to invert the appearance of C3DE image. The image inversion is based on an image intensity threshold value which is automatically estimated through image histogram analysis.ResultsIn the inverted appearance, the LV cavity appears dark while the myocardium appears bright thus making it similar in appearance to a 3DE image. Moreover, the resulting inverted image has high contrast and low noise appearance, yielding strong LV endocardium boundary and facilitating feature extraction for segmentation.ConclusionsOur results demonstrate that the inverse appearance of contrast image enables the subsequent LV segmentation.",
keywords = "Contrast 3D echocardiography, 3D echocardiography, Image inversion, LV segmentation, Histogram analysis",
author = "Anjuman Shaheen and Kashif Rajpoot",
year = "2015",
month = aug,
day = "1",
doi = "10.1016/j.compbiomed.2015.05.009",
language = "English",
volume = "63",
pages = "99--107",
journal = "Computers in biology and medicine",
issn = "0010-4825",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Adaptive image inversion of contrast 3D echocardiography for enabling automated analysis

AU - Shaheen, Anjuman

AU - Rajpoot, Kashif

PY - 2015/8/1

Y1 - 2015/8/1

N2 - IntroductionContrast 3D echocardiography (C3DE) is commonly used to enhance the visual quality of ultrasound images in comparison with non-contrast 3D echocardiography (3DE). Although the image quality in C3DE is perceived to be improved for visual analysis, however it actually deteriorates for the purpose of automatic or semi-automatic analysis due to higher speckle noise and intensity inhomogeneity. Therefore, the LV endocardial feature extraction and segmentation from the C3DE images remains a challenging problem.MethodsTo address this challenge, this work proposes an adaptive pre-processing method to invert the appearance of C3DE image. The image inversion is based on an image intensity threshold value which is automatically estimated through image histogram analysis.ResultsIn the inverted appearance, the LV cavity appears dark while the myocardium appears bright thus making it similar in appearance to a 3DE image. Moreover, the resulting inverted image has high contrast and low noise appearance, yielding strong LV endocardium boundary and facilitating feature extraction for segmentation.ConclusionsOur results demonstrate that the inverse appearance of contrast image enables the subsequent LV segmentation.

AB - IntroductionContrast 3D echocardiography (C3DE) is commonly used to enhance the visual quality of ultrasound images in comparison with non-contrast 3D echocardiography (3DE). Although the image quality in C3DE is perceived to be improved for visual analysis, however it actually deteriorates for the purpose of automatic or semi-automatic analysis due to higher speckle noise and intensity inhomogeneity. Therefore, the LV endocardial feature extraction and segmentation from the C3DE images remains a challenging problem.MethodsTo address this challenge, this work proposes an adaptive pre-processing method to invert the appearance of C3DE image. The image inversion is based on an image intensity threshold value which is automatically estimated through image histogram analysis.ResultsIn the inverted appearance, the LV cavity appears dark while the myocardium appears bright thus making it similar in appearance to a 3DE image. Moreover, the resulting inverted image has high contrast and low noise appearance, yielding strong LV endocardium boundary and facilitating feature extraction for segmentation.ConclusionsOur results demonstrate that the inverse appearance of contrast image enables the subsequent LV segmentation.

KW - Contrast 3D echocardiography

KW - 3D echocardiography

KW - Image inversion

KW - LV segmentation

KW - Histogram analysis

U2 - 10.1016/j.compbiomed.2015.05.009

DO - 10.1016/j.compbiomed.2015.05.009

M3 - Article

VL - 63

SP - 99

EP - 107

JO - Computers in biology and medicine

JF - Computers in biology and medicine

SN - 0010-4825

ER -