Stratified mixture modeling for segmentation of white-matter lesions in brain MR images

Galimzianova, Alfiia; Pernuš, Franjo; Likar, Boštjan; Špiclin, Žiga

doi:10.1016/j.neuroimage.2015.09.047

Cited by 20 publications

(16 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other clinical images, such as T2-weighted or proton density, may be also used in our multi-channel approach, although the hyper parameters require to be tuned accordingly. Most MS lesion segmentation methods reported in the literature show low performance when applied to patient data exhibiting low lesion load and small lesions ( Anbeek et al, 2004 ; Cabezas et al, 2014 ; Galimzianova et al, 2016 ; Sajja et al, 2006 ; Schmidt et al, 2012 ; Steenwijk et al, 2013 ). However, accurate detection especially in the early stages of MS can be crucial for initial diagnosis and subsequent treatment monitoring ( Filippi et al, 2016 ).…”

Section: Discussionmentioning

confidence: 99%

“…DSC is one of the most commonly-used metrics to measure the segmentation quality ( Lladó, Oliver, et al, 2012 ); however, this metric is not appropriate to evaluate the segmentation of small objects ( Schmidt et al, 2012 ). Despite this, DSC is widely used ( Brosch et al, 2016 ; Galimzianova et al, 2016 ; Jain et al, 2015 ) even to this type of data characterized with low lesion load. Interestingly, the median of DSC for the PV-method was significantly higher than for the other two studied methods.…”

Section: Discussionmentioning

confidence: 99%

“…Recently, ( Khademi and Moody, 2015 ) performed image classification using mixed tissue labels as in ( Cuadra et al, 2005 ; Shattuck et al, 2001 ) and estimated the PV fraction in mixed classes using spatial image gradient analysis. Variants of this approach using hierarchical mixture models are employed in ( Galimzianova et al, 2016 ; Sudre et al, 2015 ).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Partial volume-aware assessment of multiple sclerosis lesions

Fartaria

Todea

Kober

et al. 2018

NeuroImage: Clinical

View full text Add to dashboard Cite

White-matter lesion count and volume estimation are key to the diagnosis and monitoring of multiple sclerosis (MS). Automated MS lesion segmentation methods that have been proposed in the past 20 years reach their limits when applied to patients in early disease stages characterized by low lesion load and small lesions. We propose an algorithm to automatically assess MS lesion load (number and volume) while taking into account the mixing of healthy and lesional tissue in the image voxels due to partial volume effects. The proposed method works on 3D MPRAGE and 3D FLAIR images as obtained from current routine MS clinical protocols. The method was evaluated and compared with manual segmentation on a cohort of 39 early-stage MS patients with low disability, and showed higher Dice similarity coefficients (median DSC = 0.55) and higher detection rate (median DR = 61%) than two widely used methods (median DSC = 0.50, median DR < 45%) for automated MS lesion segmentation. We argue that this is due to the higher performance in segmentation of small lesions, which are inherently prone to partial volume effects.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Partial volume-aware assessment of multiple sclerosis lesions

Fartaria

Todea

Kober

et al. 2018

NeuroImage: Clinical

View full text Add to dashboard Cite

show abstract

“…Moreover, most proposed methods have been validated on a restricted number of cases and within single centers or simulated MR imaging acquisitions. 5,17,18 In addition, a validation of the method based on data provided by the MICCAI Grand Challenge workshop 2008 would be unfeasible because of the absence of a DE sequence in the dataset. 6,19 In this study, a validation of the method against manual segmentation in a multicenter context was presented, proving that the method was robust to scanner differences and that its performance was not dependent on MR software and hardware.…”

Section: Discussionmentioning

confidence: 99%

A Semiautomatic Method for Multiple Sclerosis Lesion Segmentation on Dual-Echo MR Imaging: Application in a Multicenter Context

Storelli

Pagani

Rocca

et al. 2016

AJNR Am J Neuroradiol

View full text Add to dashboard Cite

show abstract

“…Magnetic Resonance Imaging (MRI) as non-invasive and most widely used medical imaging modality is paramount for accurate anatomical analysis of human's internal brain layers [1]- [3]. With Radio Frequency (RF) pulses generated in MRI, the subjects T1 and T2 weighted Magnetic Resonance (MR) images are acquired [4].…”

Section: Introductionmentioning

confidence: 99%

Fusion of Gaussian Mixture Model and Spatial Fuzzy C-Means for Brain MR Image Segmentation

Oluwasanmi¹,

Qin²,

Lan³

2018

dtcse

View full text Add to dashboard Cite

Brain image segmentation into white matter, grey matter and cerebrospinal fluid is a very popular yet challenging area in medical image processing. The Fuzzy C-Means clustering algorithm is quite used because of its ability to ensure multiple member of pixels in several clusters. This is further appreciated when the spatial information of the data is considered, as such, the algorithm becomes much more robust to noise. However, pixels which form part of the non-overlapped tissues often come out inaccurate. To solve this problem, a spatial fuzzy algorithm fused with the Gaussian mixture model using the expectation maximization algorithm is presented in this paper. The proposed algorithm is a fusion of the Fuzzy C-Means and gaussian Mixture Model algorithms for segmenting tissues having multiple cluster memembership as well as single clustering. The results of the proposed algorithm are compared with the other classical algorithms against the manually segmented results of the input image. The estimated results of the proposed algorithm using the Dice and Jaccard similarity index indicates improved accuracy to the other algorithms.

show abstract

Stratified mixture modeling for segmentation of white-matter lesions in brain MR images

Cited by 20 publications

References 54 publications

Partial volume-aware assessment of multiple sclerosis lesions

Partial volume-aware assessment of multiple sclerosis lesions

A Semiautomatic Method for Multiple Sclerosis Lesion Segmentation on Dual-Echo MR Imaging: Application in a Multicenter Context

Fusion of Gaussian Mixture Model and Spatial Fuzzy C-Means for Brain MR Image Segmentation

Contact Info

Product

Resources

About