2013
DOI: 10.1007/978-3-642-38868-2_23
|View full text |Cite
|
Sign up to set email alerts
|

Joint Co-segmentation and Registration of 3D Ultrasound Images

Abstract: Contrast-enhanced ultrasound (CEUS) allows a visualization of the vascularization and complements the anatomical information provided by conventional ultrasound (US). However, these images are inherently subject to noise and shadows, which hinders standard segmentation algorithms. In this paper, we propose to use simultaneously the different information coming from 3D US and CEUS images to address the problem of kidney segmentation. To that end, we introduce a generic framework for joint co-segmentation and re… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2013
2013
2019
2019

Publication Types

Select...
2
2
1

Relationship

1
4

Authors

Journals

citations
Cited by 6 publications
(4 citation statements)
references
References 19 publications
0
4
0
Order By: Relevance
“…In [11] the authors present a graph-based method applied on MR brain images where the registration constraints are relaxed in the presence of brain tumors, while their formulation provides also segmentation masks of the tumor area. Using ultrasound images, a joint variational framework for the joint cosegmentation and registration has been proposed in [13], while in [5] the authors address both tasks in a joint framework, evaluating them on infant brain images. Even though there is a wide range of methods addressing image segmentation and registration jointly, showing that one solution impacts the other, according to our knowledge, this is the first time that an efficient formulation based on deep learning is presented and evaluated on brain MR images.…”
Section: Related Workmentioning
confidence: 99%
“…In [11] the authors present a graph-based method applied on MR brain images where the registration constraints are relaxed in the presence of brain tumors, while their formulation provides also segmentation masks of the tumor area. Using ultrasound images, a joint variational framework for the joint cosegmentation and registration has been proposed in [13], while in [5] the authors address both tasks in a joint framework, evaluating them on infant brain images. Even though there is a wide range of methods addressing image segmentation and registration jointly, showing that one solution impacts the other, according to our knowledge, this is the first time that an efficient formulation based on deep learning is presented and evaluated on brain MR images.…”
Section: Related Workmentioning
confidence: 99%
“…Registration methods that are designed to register two target and reference images containing the same object e.g. [15], [16], [17], [18], [19], [20], [21], [22], [23], are not suitable for comparison as they cannot align 2D images that contain different parts of a 3D volume and of an object of interest. The methods presented in [5], [6] are limited to temporal sequences forming two orthogonal stacks of slices.…”
Section: Experimental Results and Analysismentioning
confidence: 99%
“…However, its integration strategy inspired our proposed integrated registration method for spaced data, as explained in Section 3.1. Prevost et al [22] developed a similar method for co-segmenting the kidney from contrast-enhanced and 3D ultrasounds using additional prior-knowledge constraints on the recovered shape. Unal et al [23] proposed a variation of the work in [21] for co-segmentation and regularized non-rigid registra-tion of two volumes.…”
Section: Previous Workmentioning
confidence: 99%
“…Prior work on kidney segmentation in CEUS is limited to two of our conference papers [7] and [8], of which this chapter is an extended version.…”
Section: Introductionmentioning
confidence: 99%