Adaptive computer-aided diagnosis scheme of digitized mammograms

Zheng, Bin; Chang, Yuan‐Hsiang; Gur, David

doi:10.1016/s1076-6332(96)80270-4

Cited by 30 publications

(27 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each scan, 500 projection images were obtained at 80 kVp, and these images were acquired around the breast for over 360°coverage ͑some excess angular coverage was used as a safeguard in the event of patient motion during the scan͒. The mAs used for each patient depended on the size of the breast and was determined so that the mean glandular dose from a bCT scan was the same as it would be for a two view mammogram 16,17,22 of the same breast. A PAXSCAN detector ͑model 4030CB; Varian Medical Systems, Palo Alto, CA͒ running at 30 frames per second was used in 2 by 2 pixel binning mode ͑0.388 mm pixels͒, resulting in projection images with a pixel dimension projected to isocenter of 0.205 mmϫ 0.205 mm.…”

Section: Iiib Bct Scansmentioning

confidence: 99%

“…In this investigation, we measure and analyze the image power spectrum ͑PS͒ to evaluate the characteristics of anatomical variability in bCT images under the assumption that the statistics associated with breast tissue are locally stationary in the regions sampled. A number of authors [17][18][19][20] have shown that at spatial frequencies below about 0.5 cyc/ mm, power spectra for projection mammography images are well-characterized by a power law: S͑f͒ = ␣ / f ␤ , where f is the radial spatial frequency. The magnitude, ␣, and power-law exponent, ␤, are free parameters.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Characterizing anatomical variability in breast CT images

et al. 2008

View full text Add to dashboard Cite

Previous work ͓Burgess et al., Med. Phys. 28, 419-437 ͑2001͔͒ has shown that anatomical noise in projection mammography results in a power spectrum well modeled over a range of frequencies by a power law, and the exponent ͑␤͒ of this power law plays a critical role in determining the size at which a growing lesion reaches the threshold for detection. In this study, the authors evaluated the power-law model for breast computed tomography ͑bCT͒ images, which can be thought of as thin sections through a three-dimensional ͑3D͒ volume. Under the assumption of a 3D power law describing the distribution of attenuation coefficients in the breast parenchyma, the authors derived the relationship between the power-law exponents of bCT and projection images and found it to be ␤ section = ␤ proj − 1. They evaluated this relationship on clinical images by comparing bCT images from a set of 43 patients to Burgess' findings in mammography. They were able to make a direct comparison for 6 of these patients who had both a bCT exam and a digitized film-screen mammogram. They also evaluated segmented bCT images to investigate the extent to which the bCT power-law exponent can be explained by a binary model of attenuation coefficients based on the different attenuation of glandular and adipose tissue. The power-law model was found to be a good fit for bCT data over frequencies from 0.07 to 0.45 cyc/ mm, where anatomical variability dominates the spectrum. The average exponent for bCT images was 1.86. This value is close to the theoretical prediction using Burgess' published data for projection mammography and for the limited set of mammography data available from the authors' patient sample. Exponents from the segmented bCT images ͑average value: 2.06͒ were systematically slightly higher than bCT images, with substantial correlation between the two ͑r = 0.84͒.

show abstract

Section: Iiib Bct Scansmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Characterizing anatomical variability in breast CT images

et al. 2008

View full text Add to dashboard Cite

show abstract

“…It has been suggested that various classes of images, including mammograms, have power spectra of the form 1/f ␣ . [22][23][24][25] For mammograms, estimated values of ␣ in the range of 1.5 to 2 have been reported. 24,25 A power-law spectrum exponent between 1.5 and 2 indicates that mammograms are not fractals.…”

Section: A Two-component Model Synthesis Frameworkmentioning

confidence: 99%

“…26 Therefore, while some investigations have demonstrated that different mammographic tissue types can be classified according to their estimated fractal dimension, 23 some of these investigations have further demonstrated that the addition of another parameter significantly yields improved classification. 25,27 An additional complication with model- Rolland, Goon, and Yu: Synthesis of textured complex backgrounds ing biological tissue as a fractal is that it is difficult to accurately estimate a fractal dimension from digitized data. 28 The indication that the power spectra of mammograms and various natural images follow some power law may be significant.…”

Section: A Two-component Model Synthesis Frameworkmentioning

confidence: 99%

“…The breast is made essentially of a mixture of fatty tissue, which appears dark on radiographs, connective and epithelial tissue which produce bright radiographic appearances also referred to as mammographic densities, and prominent ducts which yield cord-like structures or a beaded appearance. 25,27 Overall, a set of mammographic radiographs from the same type of breast tissue may be described as a stochastic process with fairly large scale structures that account for mammographic densities on black backgrounds, and smaller scale structures that give the tissue the appearance of texture. We thus propose a model that is based on the decomposition of such complex backgrounds into two components: a mean background ͑i.e.…”

Section: A Two-component Model Synthesis Frameworkmentioning

confidence: 99%

See 1 more Smart Citation

Synthesis of textured complex backgrounds

Rolland

Goon

1998

Opt. Eng

View full text Add to dashboard Cite

The statistical characterization of realistic, complex backgrounds where targets may be embedded is essential in the optimization of methods for target acquisition. A modeling framework for complex backgrounds that yields perceptually realistic images may provide a path towards such essential characterizations. To this end, we developed a framework for the synthesis of statistical textured backgrounds. The results of the syntheses of three rock-like structures and that of grass indicate some of the capabilities of the framework. We further extended the methods to synthesize biological tissue samples which present two forms of background complexity: a slowly, spatially varying meanbackground and a residual texture image. The extended framework allows synthesis of each component independently. A mathematical phantom for modeling inhomogeneous backgrounds is then proposed. First and second order statistics of various textures are then presented and a measure of distance between two images is proposed. Finally we discuss how such a framework may lead to effective statistical descriptions of such complex backgrounds for target acquisition. © 1998 Society of Photo-Optical Instrumentation Engineers. [S0091-3286(98)01807-8] Subject terms: textured backgrounds; complex backgrounds; texture synthesis; first and second order statistics; detection.Paper TAM-18

show abstract

A Knowledge-Based Scheme for Digital Mammography

Singh

Bovis

Topics in Biomedical Engineering International Book Series

View full text Add to dashboard Cite

Adaptive computer-aided diagnosis scheme of digitized mammograms

Cited by 30 publications

References 22 publications

Characterizing anatomical variability in breast CT images

Characterizing anatomical variability in breast CT images

Synthesis of textured complex backgrounds

A Knowledge-Based Scheme for Digital Mammography

Contact Info

Product

Resources

About