Segmentation of abdominal ultrasound images of the prostate using a priori information and an adapted noise filter

Betrouni, Nacim; Vermandel, Maximilien; Pasquier, David; Maouche, S.; Rousseau, Jean

doi:10.1016/j.compmedimag.2004.07.007

Cited by 64 publications

(43 citation statements)

References 30 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The average DSC value of our method with 0.95±0.01 is comparable to mean DSC values achieved by Betrouni et al 7 and Ladak et al 17 and inferior to the area overlap measure of Abolmaesumi et al 16 of 98%. However, it is to be noted that we have used more images (24 images) compared to 6 images of Abolmaesumi et al Our MAD value of 1.50±0.41 mm is comparable to Gong et al…”

Section: Resultssupporting

confidence: 69%

See 1 more Smart Citation

Prostate segmentation with local binary patterns guided active appearance models

et al. 2011

View full text Add to dashboard Cite

Real-time fusion of Magnetic Resonance (MR) and Trans Rectal Ultra Sound (TRUS) images aid in the localization of malignant tissues in TRUS guided prostate biopsy. Registration performed on segmented contours of the prostate reduces computational complexity and improves the multimodal registration accuracy. However, accurate and computationally efficient segmentation of the prostate in TRUS images could be challenging in the presence of heterogeneous intensity distribution inside the prostate gland, and other imaging artifacts like speckle noise, shadow regions and low Signal to Noise Ratio (SNR). In this work, we propose to enhance the texture features of the prostate region using Local Binary Patterns (LBP) for the propagation of a shape and appearance based statistical model to segment the prostate in a multi-resolution framework. A parametric model of the propagating contour is derived from Principal Component Analysis (PCA) of the prior shape and texture information of the prostate from the training data. The estimated parameters are then modified with the prior knowledge of the optimization space to achieve an optimal segmentation. The proposed method achieves a mean Dice Similarity Coefficient (DSC) value of 0.94±0.01 and a mean segmentation time of 0.68±0.02 seconds when validated with 70 TRUS images of 7 datasets in a leave-one-patient-out validation framework. Our method performs computationally efficient and accurate prostate segmentation in the presence of intensity heterogeneities and imaging artifacts.

show abstract

Section: Resultssupporting

confidence: 69%

“…To address the challenges of prostate segmentation in TRUS images Shen et al 6 and Betrouni et al 7 proposed to use prior prostate shape information in their models. Prior shape information made the models robust to imaging artifacts and detected true prostate edges in low SNR.…”

Section: Introductionmentioning

confidence: 99%

Prostate segmentation with local binary patterns guided active appearance models

et al. 2011

View full text Add to dashboard Cite

show abstract

“…Analyzing the results, we observe that our mean DSC value is better than the area overlap accuracy values of Betrouni et al [3] and Ladak et al [14] and very similar to the area overlap error of Shen et al [18]. However, it is to be noted that we have used more images compared to Shen et al Our MAD value also shows improvement when compared to [3], [18], [14], [6] and [19]. From these observations we may infer our method performs well in overlap and contour accuracy measures when assessed qualitatively.…”

Section: Resultsmentioning

confidence: 77%

“…The mean segmentation time of the method is 0.67±0.02 seconds with an unoptimized Matlab code. Even with an unoptimized Matlab Table 2 we observe that our mean segmentation time is better when compared to [3], [18] and [6], although inferior to [19]. However, [19] used an optimized C++ code to achieve their results.…”

Section: Resultsmentioning

confidence: 91%

A Supervised Learning Framework for Automatic Prostate Segmentation in Trans Rectal Ultrasound Images

Ghose

Mitra

Oliver

et al. 2012

Advanced Concepts for Intelligent Vision Systems

View full text Add to dashboard Cite

Abstract. Heterogeneous intensity distribution inside the prostate gland, significant variations in prostate shape, size, inter dataset contrast variations, and imaging artifacts like shadow regions and speckle in Trans Rectal Ultrasound (TRUS) images challenge computer aided automatic or semi-automatic segmentation of the prostate. In this paper, we propose a supervised learning schema based on random forest for automatic initialization and propagation of statistical shape and appearance model. Parametric representation of the statistical model of shape and appearance is derived from principal component analysis (PCA) of the probability distribution inside the prostate and PCA of the contour landmarks obtained from the training images. Unlike traditional statistical models of shape and intensity priors, the appearance model in this paper is derived from the posterior probabilities obtained from random forest classification. This probabilistic information is then used for the initialization and propagation of the statistical model. The proposed method achieves mean Dice Similarity Coefficient (DSC) value of 0.96±0.01, with a mean segmentation time of 0.67±0.02 seconds when validated with 24 images from 6 datasets with considerable shape, size, and intensity variations, in a leave-one-patient-out validation framework. The model achieves statistically significant t-test p-value<0.0001 in mean DSC and mean mean absolute distance (MAD) values compared to traditional statistical models of shape and intensity priors.

show abstract

“…Shen et al [125] proposed an automated technique that utilized Gabor [126]based appearance features to guide an ASM for prostate segmentation. Another automated technique proposed by Betrouni et al [127] was based on optimizing an ASM to segment the prostate. Zaim and Jankun [128] used an ASM, guided by extracted image appearance features to find the prostate boundary.…”

Section: A In-vitro Prostate Cancer Diagnostic Technologiesmentioning

confidence: 99%

A novel NMF-based DWI CAD framework for prostate cancer.

McClure¹

View full text Add to dashboard Cite

Segmentation of abdominal ultrasound images of the prostate using a priori information and an adapted noise filter

Cited by 64 publications

References 30 publications

Prostate segmentation with local binary patterns guided active appearance models

Prostate segmentation with local binary patterns guided active appearance models

A Supervised Learning Framework for Automatic Prostate Segmentation in Trans Rectal Ultrasound Images

A novel NMF-based DWI CAD framework for prostate cancer.

Contact Info

Product

Resources

About