Morphology-driven automatic segmentation of MR images of the neonatal brain

Gui, Laura; Lisowski, Radoslaw; Faundez, Tamara; Hüppi, Petra Susan; Lazeyras, François; Kocher, Michel

doi:10.1016/j.media.2012.07.006

Cited by 112 publications

(125 citation statements)

References 45 publications

Supporting

Mentioning

124

Contrasting

Order By: Relevance

“…It has been proven that the continuous max-flow model (9) is equivalent to the convex relaxation problem (8).…”

Section: Convex Optimization and Continuous Max-flow Algorithmmentioning

confidence: 99%

“…Neonatal brain MR images tend to suffer from high image noise (the patients are not sedated and therefore the images have some additional motion artefacts), low tissue contrast, and considerable inter-subject anatomical variability, making most of the methods used in adult population not applicable to these images. 8 Although some automatic neonatal MR segmentation methods were developed, 9-11 most of works segmented neonatal brain in MR images into white matter (WM), gray matter (GM), and CSF, and did not focus on the ventricular system. Moreover, their methods were only validated on healthy neonate images.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

3D MR ventricle segmentation in pre-term infants with post-hemorrhagic ventricle dilation

et al. 2015

View full text Add to dashboard Cite

Intraventricular hemorrhage (IVH) or bleed within the brain is a common condition among pre-term infants that occurs in very low birth weight preterm neonates. The prognosis is further worsened by the development of progressive ventricular dilatation, i.e., post-hemorrhagic ventricle dilation (PHVD), which occurs in 10-30% of IVH patients. In practice, predicting PHVD accurately and determining if that specific patient with ventricular dilatation requires the ability to measure accurately ventricular volume. While monitoring of PHVD in infants is typically done by repeated US and not MRI, once the patient has been treated, the follow-up over the lifetime of the patient is done by MRI. While manual segmentation is still seen as a gold standard, it is extremely time consuming, and therefore not feasible in a clinical context, and it also has a large inter-and intra-observer variability. This paper proposes an segmentation algorithm to extract the cerebral ventricles from 3D T1-weighted MR images of pre-term infants with PHVD. The proposed segmentation algorithm makes use of the convex optimization technique combined with the learned priors of image intensities and label probabilistic map, which is built from a multi-atlas registration scheme. The leave-one-out cross validation using 7 PHVD patient T1 weighted MR images showed that the proposed method yielded a mean DSC of 89.7% ± 4.2%, a MAD of 2.6 ± 1.1 mm, a MAXD of 17.8 ± 6.2 mm, and a VD of 11.6% ± 5.9%, suggesting a good agreement with manual segmentations.

show abstract

“…It has been proven that the continuous max-flow model (9) is equivalent to the convex relaxation problem (8).…”

Section: Convex Optimization and Continuous Max-flow Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

3D MR ventricle segmentation in pre-term infants with post-hemorrhagic ventricle dilation

et al. 2015

View full text Add to dashboard Cite

show abstract

“…The second part based on binary mathematical morphology and region growing method framework selected target organizations. Markov Random Field (MRF) [3] have a good effect on the image noise removal but MRF has high time complexity, so they raised an algorism based on Markov Random Field (MRF) and Ant Colony Optimization (ACO) to achieve faster convergence to improve execution speed of the system. Several experiments on phantom and real images were performed.…”

Section: Introductionmentioning

confidence: 99%

The Recognition of Basal Ganglia Area in the Brain MRI Image with Hybrid Classifier

Wu¹,

Chin²,

Chin³

et al. 2017

IJIEE

View full text Add to dashboard Cite

Abstract-To understand the relationship between the volume of basal ganglia and parkinson's disease, this paper proposes the recognition of basal ganglia in the brain MRI image with hybrid classifier. It can locate the position of basal ganglia in the 2D brain MRI image. It employs three feature extraction methods to extract the texture feature of basal ganglia. The three feature extraction methods include GLCM, Law's mask and Hu's method .Next, we uses rank search method and genetic search method to perform feature selection. It can reduce computation complexity. Finally, hybrid classifier combining neuro-fuzzy system and adaboost algorithm is used to achieve recognition. From experimental result, we discovered that our proposed method has the high recognition rate.Index Terms-Parkinson's disease, magnetic resonance imaging, basal ganglia, feature pooling, neural-fuzzy-based adaboost.

show abstract

“…Accurate segmentation of infant brain MR images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) in this critical phase is of great importance for studying the normal and abnormal early brain development Hanson et al, 2013;Li et al, 2014a;Li et al, 2013a;Li et al, 2014b;Li et al, 2013bLi et al, , 2014cLi et al, 2014d;Li et al, 2014e;Lyall et al, 2014;Nie et al, 2012;Nie et al, 2014;Verma et al, 2005). However, the segmentation of infant brain MRI is challenging due to the reduced tissue contrast (Weisenfeld and Warfield, 2009), increased noise, severe partial volume effect (Xue et al, 2007), and ongoing white matter myelination (Gui et al, 2012;Weisenfeld and Warfield, 2009). In fact, there are three distinct stages in the first-year brain MR images, including (1) infantile stage (≤5 months), (2) isointense stage (6-8 months), and (3) early adult-like stage (≥9 months).…”

Section: Introductionmentioning

confidence: 99%

LINKS: Learning-Based Multi-source IntegratioN FrameworK for Segmentation of Infant Brain Images

Wang

Gao

Shi

et al. 2014

Medical Computer Vision: Algorithms for Big Data

View full text Add to dashboard Cite

Segmentation of infant brain MR images is challenging due to insufficient image quality, severe partial volume effect, and ongoing maturation and myelination processes. In the first year of life, the image contrast between white and gray matters of the infant brain undergoes dramatic changes. In particular, the image contrast is inverted around 6-8 months of age, and the white and gray matter tissues are isointense in both T1-and T2-weighted MR images and thus exhibit the extremely low tissue contrast, which poses significant challenges for automated segmentation. Most previous studies used multi-atlas label fusion strategy, which has the limitation of equally treating the different available image modalities and is often computationally expensive. To cope with these limitations, in this paper, we propose a novel learning-based multi-source integration framework for segmentation of infant brain images. Specifically, we employ the random forest technique to effectively integrate features from multi-source images together for tissue segmentation. Here, the multi-source images include initially only the multi-modality (T1, T2 and FA) images and later also the iteratively estimated and refined tissue probability maps of gray matter, white matter, and cerebrospinal fluid. Experimental results on 119 infants show that the proposed method achieves better performance than other state-of-the-art automated segmentation methods. Further validation was performed on the MICCAI grand challenge and the proposed method was ranked top among all competing methods. Moreover, to alleviate the possible Publisher's Disclaimer: This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final citable form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. anatomical errors, our method can also be combined with an anatomically-constrained multi-atlas labeling approach for further improving the segmentation accuracy. NIH Public Access

show abstract

Morphology-driven automatic segmentation of MR images of the neonatal brain

Cited by 112 publications

References 45 publications

3D MR ventricle segmentation in pre-term infants with post-hemorrhagic ventricle dilation

3D MR ventricle segmentation in pre-term infants with post-hemorrhagic ventricle dilation

The Recognition of Basal Ganglia Area in the Brain MRI Image with Hybrid Classifier

LINKS: Learning-Based Multi-source IntegratioN FrameworK for Segmentation of Infant Brain Images

Contact Info

Product

Resources

About