Automatic Segmentation of Antenatal 3-D Ultrasound Images

Anquez, Jérémie; Angelini, Elsa D.; Grangé, G.; Bloch, Isabelle

doi:10.1109/tbme.2012.2237400

Cited by 36 publications

(26 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…29) It has recently been used to model the saturated 3D ultrasound data acquired from fetal tissue. 23) …”

Section: Methodsmentioning

confidence: 99%

“…Once fully characterized, information regarding PDFs in different regions of the LN parenchyma and surrounding media can be applied to develop a more-robust LN segmentation method using the MAP approach. 23,26) Furthermore, detailed characterization of parameters describing the PDF of non-cancerous vs metastatic LN parenchyma will contribute to more-accurate QUS-based characterization of LNs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modeling the envelope statistics of three-dimensional high-frequency ultrasound echo signals from dissected human lymph nodes

Bui

Coron

Mamou

et al. 2014

Jpn. J. Appl. Phys.

View full text Add to dashboard Cite

This work investigates the statistics of the envelope of three-dimensional (3D) high-frequency ultrasound (HFU) data acquired from dissected human lymph nodes (LNs). Nine distributions were employed, and their parameters were estimated using the method of moments. The Kolmogorov Smirnov (KS) metric was used to quantitatively compare the fit of each candidate distribution to the experimental envelope distribution. The study indicates that the generalized gamma distribution best models the statistics of the envelope data of the three media encountered: LN parenchyma, fat and phosphate-buffered saline (PBS). Furthermore, the envelope statistics of the LN parenchyma satisfy the pre-Rayleigh condition. In terms of high fitting accuracy and computationally efficient parameter estimation, the gamma distribution is the best choice to model the envelope statistics of LN parenchyma, while, the Weibull distribution is the best choice to model the envelope statistics of fat and PBS. These results will contribute to the development of more-accurate and automatic 3D segmentation of LNs for ultrasonic detection of clinically significant LN metastases.

show abstract

“…29) It has recently been used to model the saturated 3D ultrasound data acquired from fetal tissue. 23) …”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Modeling the envelope statistics of three-dimensional high-frequency ultrasound echo signals from dissected human lymph nodes

Bui

Coron

Mamou

et al. 2014

Jpn. J. Appl. Phys.

View full text Add to dashboard Cite

show abstract

“…Based on the work by Anquez in [5], where it is shown that the K-means produce satisfying segmentation results for our images, we have also tested it to obtain an initial segmentation. Basically, the class with the centroid corresponding to the lowest mean shows high correspondence with the amniotic fluid and darker tissues of the mother.…”

Section: The Proposed Adaptive Methodsmentioning

confidence: 99%

“…However, it was identified by Anquez [5] that in fetal 3D ultrasound (US) images, different noise distributions characterize different tissues appearances, depending on pixel intensity saturation and tissue type. For example, it is shown that the noise is governed by a Gaussian distribution in fetus tissues and by an Exponential distribution in amniotic fluid area (in the saturated case).…”

Section: Introductionmentioning

confidence: 99%

Denoising based on non local means for ultrasound images with simultaneous multiple noise distributions

Salvadeo

Bloch

Tupin

et al. 2014

2014 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

In this paper, an extension of the framework proposed by Deledalle et al. [1] for Non Local Means (NLM) method is proposed. This extension is a general adaptive method to denoise images containing multiple noises. It takes into account a segmentation stage that indicates the noise type of a given pixel in order to select the similarity measure and suitable parameters to perform the denoising task, considering a certain patch on the image. For instance, it has been experimentally observed that fetal 3D ultrasound images are corrupted by different types of noise, depending on the tissue. Finally, the proposed method is applied to denoise these images, showing very good results.

show abstract

“…A fetal anatomy detection that uses constrained probabilistic boosting tree to tree has been proposed by Carniero et al [1], and the fetal anatomy size could the be measured by using box area that are detected as fetal object [2]. Segmentation of antenatal on 3D ultrasound images has been proposed by Anquez et al [3]. Tho model the intensity distribution and the regularity of the contrast, Anquez uses bayesian formulation.…”

Section: Figure 1 Intelligent Ultrasound Systemmentioning

confidence: 99%