Segmentation of human skull in MRI using statistical shape information from CT data

Wang, Defeng; Shi, Lin; Chu, Winnie C.W.; Cheng, Jack C. Y.; Heng, Pheng‐Ann

doi:10.1002/jmri.21864

Cited by 13 publications

(11 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed method is able to approximate the skull contours and differentiate air from bone with similar accuracy as the results presented in Wang et al (11), that reported a Dice coefficient of 0.75, even though they only showed results on the upper half of the skull. Additionally, their method requires previous annotation of the database by an expert, while our method requires no previous manual intervention.…”

Section: Discussionsupporting

confidence: 74%

See 1 more Smart Citation

Multi‐atlas and label fusion approach for patient‐specific MRI based skull estimation

Torrado‐Carvajal

Herraiz

Hernández-Tamames

et al. 2015

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose: MRI-based skull segmentation is a useful procedure for many imaging applications. This study describes a methodology for automatic segmentation of the complete skull from a single T1-weighted volume. Methods: The skull is estimated using a multi-atlas segmentation approach. Using a whole head computed tomography (CT) scan database, the skull in a new MRI volume is detected by nonrigid image registration of the volume to every CT, and combination of the individual segmentations by label-fusion. We have compared Majority Voting, Simultaneous Truth and Performance Level Estimation (STAPLE), Shape Based Averaging (SBA), and the Selective and Iterative Method for Performance Level Estimation (SIMPLE) algorithms. Results: The pipeline has been evaluated quantitatively using images from the Retrospective Image Registration Evaluation database (reaching an overlap of 72.46 6 6.99%), a clinical CT-MR dataset (maximum overlap of 78.31 6 6.97%), and a whole head CT-MRI pair (maximum overlap 78.68%). A qualitative evaluation has also been performed on MRI acquisition of volunteers. Conclusion: It is possible to automatically segment the complete skull from MRI data using a multi-atlas and label fusion approach. This will allow the creation of complete MRI-based tissue models that can be used in electromagnetic dosimetry applications and attenuation correction in PET/MR. Magn Reson Med 000:000-000, 2015. V C 2015 Wiley Periodicals, Inc.

show abstract

Section: Discussionsupporting

confidence: 74%

“…Rifai et al (10) proposed a three-dimensional (3D) method for segmenting bone regions in MRI volumes using deformable models and taking the partial volume effect into account. In Wang et al (11) the authors proposed the use of a CT database to create a reliable shape model used to locate the skull shape in MRI.…”

Section: Image Postprocessingmentioning

confidence: 99%

Multi‐atlas and label fusion approach for patient‐specific MRI based skull estimation

Torrado‐Carvajal

Herraiz

Hernández-Tamames

et al. 2015

Magnetic Resonance in Med

View full text Add to dashboard Cite

show abstract

“…in facial sinuses in the head images [1]. To overcome this problem, several segmentation approaches have been proposed, such as a combination of consequent thresholding and mathematical morphological operations [8] or CT-derived model-based segmentation algorithms [9]. However, due to close signal intensity of cortical bone to that of air, these methods fail to robustly separate bony structures from proximal air cavities.…”

Section: Discussionmentioning

confidence: 99%

Generation of MR-Based Attenuation Correction Map of PET Images in the Brain Employing Joint Segmentation of Skull and Soft-Tissue from Single Short-TE MR Imaging Modality

Kazerooni

Aarabi

et al. 2015

Computational Methods for Molecular Imaging

View full text Add to dashboard Cite

Recently introduced PET/MRI scanners present significant advantages in comparison with PET/CT, including better soft-tissue contrast, lower radiation dose, and truly simultaneous imaging capabilities. However, the lack of an accurate method for generation of MR-based attenuation map (µ-map) at 511 keV is hampering further development and wider acceptance of this technology. Here, we present a new method for the MR-based attenuation correction map (µ-map), employing a proposed short echo-time (STE) MR imaging technique along with the nearly automatic segmentation. This method repeatedly applies active contours inhomogeneity correction, multi-class spatial fuzzy clustering (SFCM), followed by shape analysis, to classify the images into cortical bone, air, and soft tissue classes. The proposed segmentation method returned sensitivity of 81 % for cortical bone and above 90 % for soft tissue and air. These results suggest that this technique is accurate, efficient, and robust for discriminating bony structures from the neighboring air and soft tissue in STE-MR images, which is suitable for generating MR-based µ-maps.

show abstract

“…For scalp and skull segmentation from MRI, previous works in the literature have proposed the morphology method, machine‐learning‐based methods (Neural Network, SVM) and atlas‐based methods . Moreover, information from CT data can be used for segmentation.…”

Section: Introductionmentioning

confidence: 99%

3D brain magnetic resonance imaging segmentation by using bitplane and adaptive fast marching

Tuan

Kim

Bao

2018

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Diagnosis using medical images helps doctors detect diseases and treat patients effectively. A system that segments objects automatically from magnetic resonance imaging (MRI) plays an important role when doctors diagnose injuries and brain diseases. This article presents a method for automatic brain, scalp, and skull segmentation from MRI that uses Bitplane and the Adaptive Fast Marching method (FMM). We focus on the segmentation of these tissues, especially the brain, because they are the essential objects, and their segmentation is the first step in the segmentation of other tissues. First, the type of each slice is set based on the shape of the brain, and the head region is segmented by removing its background. Second, the sure region and the unsure region are segmented based on the Bitplane method. Finally, this work proposes an approach for classification that is based on the Adaptive FMM. This approach is evaluated with the BrainWeb and Neurodevelopmental MRI databases and compared with other methods. The Dice Averages for brain, scalp, and skull segmentation are 96%, 80%, and 93%, respectively, on the BrainWeb database and 91%, 67%, and 80%, respectively, on the Neurodevelopmental MRI database.

show abstract

Segmentation of human skull in MRI using statistical shape information from CT data

Cited by 13 publications

References 18 publications

Multi‐atlas and label fusion approach for patient‐specific MRI based skull estimation

Multi‐atlas and label fusion approach for patient‐specific MRI based skull estimation

Generation of MR-Based Attenuation Correction Map of PET Images in the Brain Employing Joint Segmentation of Skull and Soft-Tissue from Single Short-TE MR Imaging Modality

3D brain magnetic resonance imaging segmentation by using bitplane and adaptive fast marching

Contact Info

Product

Resources

About