Automated detection and enhancement of microcalcifications in mammograms using nonlinear subband decomposition

Gürcan, Metin N.; Yardımcı, Yasemin; Çetin, A. Enis; Ansari, Rashid

doi:10.1109/icassp.1997.595440

Cited by 9 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Student's t-test was performed compared to the normalized control values at t = 50 min unless otherwise indicated and the null-hypothesis was rejected if p<0.05. We identified outliers using boxplots (Gurcan et al, 1997;Gruetter et al, 2001).…”

Section: Methodsmentioning

confidence: 99%

Effects of glucose and glutamine concentration in the formulation of the artificial cerebrospinal fluid (ACSF)

Radman

et al. 2008

Brain Research

View full text Add to dashboard Cite

The composition of the ACSF is fundamental in controlling the extracellular environment of the brain slice preparation. 'Typical' formulations lack amino acids and contain a higher concentration of glucose (10 mM) than in the cerebrospinal fluid (0.47-4.4 mM). We examined the effects of different concentrations of glutamine, the most abundant amino acid in the CSF, and glucose on rat hippocampal slice physiology. Bipolar paired-pulse stimulation was applied to the Schaffer collaterals and population spikes were monitored in the CA1 pyramidal layer for approximately 1 hour. Addition of glutamine (0.5 mM) to slices superfused with 10 mM of glucose did not enhance population spike amplitude. Higher concentration of glutamine (2-5 mM) resulted in spreading-depression. Decreasing glucose concentration from 10 mM to 5 mM, in the absence of glutamine, attenuated population spikes. Decreasing glucose to 2 mM, in the absence of glutamine, suppressed evoked population spikes. Superfusing brain slices with ACSF containing 'physiological' concentrations of both glucose (2 mM) and glutamine (0.5 mM) similarly suppressed population spikes. In separate experiments, during high-K+ induced epileptiform activity, glutamine (0.5 mM) did not affect the burst duration, frequency or waveform. These results suggest that the concentration of glucose in ACSF should conservatively be 10 mM in order to maximize paired-pulse population responses while the presence of physiological concentration of glutamine (0.5 mM) has minimal effects on paired-pulse responses and high-K+ induced epileptiform activity. These results are discussed in the context of fundamental differences between in vitro brain slice superfusion and in vivo brain perfusion.

show abstract

Section: Methodsmentioning

confidence: 99%

Effects of glucose and glutamine concentration in the formulation of the artificial cerebrospinal fluid (ACSF)

Radman

et al. 2008

Brain Research

View full text Add to dashboard Cite

show abstract

“…The directions of principal components are defined by the eigenvectors = (c21,e2) of S, and the length of each component is the square root of the eigenvalues A1 = (/X, /X). S ( )T (4) rE Knowing the principal components, the projected data are computed by projecting all the points in segment i onto time corresponding eigenvectors using e[x. The projected data is also smoothed using Bézier methods.…”

Section: Classificationmentioning

confidence: 99%

<title>Lesion detection and characterization in digital mammography by Bezier histograms</title>

Snyder

1999

SPIE Proceedings

View full text Add to dashboard Cite

Due to some important properties of Bézier splines, they have great potential use in computer-aided mammogram diagnosis. In this paper, Bézier splines are applied in both lesion detection and characterization processes, where lesion detection is achieved by segmentation using a natural threshold computed from Bézier smoothed histogram; and lesion characterization is achieved by measuring the fitness between Gaussian and Bézier histograms of data projected on principal components of the segmented lesions. Experimental results show that this approach is efficient, easy to use, and can achieve high sensitivity.

show abstract

“…Classification was carried out using wavelet coefficients without inverse wavelet transform. Gurcan et al [16] presented a method based on a 'subband' decomposition filter bank, which used nonlinear filters to classify microcalcifications. They decomposed each mammogram into subimages using the filter bank.…”

Section: Introductionmentioning

confidence: 99%

Performance evaluation of the wave atom algorithm to classify mammographic images

Gedik¹,

Atasoy²

2014

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Abstract:The most common type of cancer seen in women is breast cancer. To enable recovery from this severe disease, monitoring and early detection must be provided, and related precautions must be taken as a first step. During diagnosis, some cases may be overlooked due to fatigue and eyestrain, because the determination of abnormalities is a repetitive procedure. In this study, a computer-aided diagnosis (CAD) system, using the wave atom transform (WAT) algorithm and support vector machine (SVM), is proposed to evaluate mammography images. During the process, the region of interest (ROI) is defined before applying the method. The system includes a feature extraction approach based on the WAT algorithm. In terms of classification, the process has 2 main stages: the classification of normal/abnormal regions and malignant/benign ones. The proposed system also uses principle component analysis (PCA) for further dimensional reduction and feature selection. A dataset from the Mammographic Image Analysis Society database is employed for testing and measuring the performance of the proposed system. The best success rates in this work are obtained using the coefficients at scales of 1, 2, and 3, by employing SVM with PCA. The maximum classification success rate to define the regions of interest as normal/abnormal is 100%. The success rate of malignant/benign classification is also achieved as 100% in the tests. According to the results, it is observed that these features ensure important support for more comprehensive clinical investigations and the results are very encouraging when mammograms are categorized via WAT, PCA, and SVM.

show abstract

Automated detection and enhancement of microcalcifications in mammograms using nonlinear subband decomposition

Cited by 9 publications

References 14 publications

Effects of glucose and glutamine concentration in the formulation of the artificial cerebrospinal fluid (ACSF)

Effects of glucose and glutamine concentration in the formulation of the artificial cerebrospinal fluid (ACSF)

<title>Lesion detection and characterization in digital mammography by Bezier histograms</title>

Performance evaluation of the wave atom algorithm to classify mammographic images

Contact Info

Product

Resources

About