Ultrasonic multifeature tissue characterization for prostate diagnostics

Scheipers, U.; Ermert, H.; Sommerfeld, H.-J.; Garcia-Schurmann, M.; Senge, Theodor; Philippou, Stathis

doi:10.1016/s0301-5629(03)00062-0

Cited by 89 publications

(66 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…B. Tangentenartefakt), der besseren Darstellung gekrümmter Grenzflächen auch verbesserte Möglichkeiten zur Gewinnung von quantitativen Gewebeparametern im Sinne einer Gewebecharakterisierung [5]. Es ist zu erwarten, dass bereits erprobte Verfahren [6,7,8,9] mit dieser Technik weiter verbessert werden können.…”

Section: Echtzeit-spatial-compoundtechnikunclassified

Neue Techniken der Urosonographie

et al. 2004

View full text Add to dashboard Cite

New sonographic techniques in urology, together with their principles of operation, will be presented. Together with the utilization of broadband ultrasound scanners and digital beam formers, leading to better spatial resolution and increased line density in ultrasound imaging, panorama sonography enables the outline of wide lateral regions independent of the width of the scanner. Spatial compound sonography achieves a comparatively better visualization of details in the b-mode image than has yet been available. The continuously improved 3-D, now leading to 4-D, techniques, which means real time capabilities, make the visualization of unrestricted imaging planes, which are not seen in conventional 2-D techniques, possible. The second harmonic imaging technique, including the special applications tissue harmonic imaging (THI) and contrast harmonic imaging (CHI), uses special ultrasound signal processing procedures for capturing and evaluating tissue hemoperfusion-here in combination with ultrasound contrast agents (UCA). Furthermore, microvascular imaging (MVI) enables the visualization of perfusion in tissues reaching the microcirculation regions. This leads to new possibilities for the assessment of pathological perfusion patterns, e.g. in andrology (perfusion of testicles) and uro-oncology (hyperperfusion of malignant regions).

show abstract

Section: Echtzeit-spatial-compoundtechnikunclassified

Neue Techniken der Urosonographie

et al. 2004

View full text Add to dashboard Cite

show abstract

“…We used 12 texture features from the B-scan equivalents of the collected RF frames [4]. They included four statistical moments of the pixel intensities (mean, std, skewness and kurtosis), and eight features from the cooccurrence matrices: correlation, energy, contrast, and homogeneity computed for co-occurrence distance of l = 1 and separately for 0 • and 90…”

Section: Lizzi-feleppa Features (Lf1lf2lf3)mentioning

confidence: 99%

“…Texture features of B-scan images and spectral features (Lizzi-Feleppa features [3]) extracted from calibrated average spectrum of RF signals have been used along with numerous classification approaches for tissue typing [4]. Also, elastography, an automatic method for measuring the elasticity of tissue, has shown promising results in diagnosis of the disease [5].…”

Section: Introductionmentioning

confidence: 99%

Prostate Cancer Probability Maps Based on Ultrasound RF Time Series and SVM Classifiers

Moradi¹,

Mousavi²,

Siemens³

et al. 2008

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2008

View full text Add to dashboard Cite

Abstract. We describe a very efficient method based on ultrasound RF time series analysis and support vector machine classification for generating probabilistic prostate cancer colormaps to augment the biopsy process. To form the RF time series, we continuously record ultrasound RF echoes backscattered from tissue while the imaging probe and the tissue are stationary in position. In an in-vitro study involving 30 prostate specimens, we show that the features extracted from RF time series are significantly more accurate and sensitive compared to two other established categories of ultrasound-based tissue typing methods. The method results in an area under ROC curve of 0.95 in 10-fold cross-validation.

show abstract

“…13 Similarly, Scheipers et al described a multifeature tissue characterization including 1D spectral and texture parameters to detect prostate cancer. 22 In a study of 100 patients, Scheipers' method yielded a ROC curve area of 0.86 when distinguishing hyperechoic and hypoechoic tumors from normal tissue, and a ROC curve area of 0.84 when distinguishing isoechoic tumors from healthy tissue. This performance is as good as, if not superior to, current prostate-cancer imaging by MRI/MRS with a mean area under the ROC curve ranging from 0.69 to 0.76.…”

Section: Introductionmentioning

confidence: 99%

A feasibility study of novel ultrasonic tissue characterization for prostate-cancer diagnosis: 2D spectrum analysis of in vivo data with histology as gold standard

et al. 2009

View full text Add to dashboard Cite

This study demonstrates the feasibility of using a novel 2D spectrum ultrasonic tissue characterization ͑UTC͒ technique for prostate-cancer diagnosis. Normalized 2D spectra are computed by performing Fourier transforms along the range ͑beam͒ and the cross-range directions of the digital radio-frequency echo data, then dividing by a reference spectrum. This 2D spectrum method provides axial and lateral information of tissue microstructures, an improvement over the current 1D spectrum analysis which only provides axial information. A pilot study was conducted on four prostate-cancer patients who underwent radical prostatectomies. Cancerous and noncancerous regions of interest, identified through histology, were compared using four 2D spectral parameters: peak value and 3 dB width of the radially integrated spectral power ͑RISP͒, slope and intercept of the angularly integrated spectral power ͑AISP͒. For noncancerous and cancerous prostatic tissues, respectively, our investigation yielded 23Ϯ 1 and 26Ϯ 1 dB for peak value of RISP, 7.8Ϯ 0.5°and 7.6Ϯ 0.6°for 3 dB of RISP, −2.1Ϯ 0.2 and −2.7Ϯ 0.4 dB/ MHz for slope of AISP, and 92Ϯ 5 and 112Ϯ 6 dB for intercept of AISP. Preliminary results indicated that 2D spectral UTC has the potential for identifying tumor-bearing regions within the prostate gland.

show abstract

Ultrasonic multifeature tissue characterization for prostate diagnostics

Cited by 89 publications

References 59 publications

Neue Techniken der Urosonographie

Neue Techniken der Urosonographie

Prostate Cancer Probability Maps Based on Ultrasound RF Time Series and SVM Classifiers

A feasibility study of novel ultrasonic tissue characterization for prostate-cancer diagnosis: 2D spectrum analysis of in vivo data with histology as gold standard

Contact Info

Product

Resources

About