Extraction of the midsagittal plane from morphological neuroimages using the Kullback–Leibler’s measure

Volkau, Ihar; Prakash, Kritika; Ananthasubramaniam, Anand; Aziz, Aamer; Nowinski, Wiesław L.

doi:10.1016/j.media.2006.07.005

Cited by 47 publications

(77 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To extract the mid-sagittal plane, we implemented an algorithm based on Kullback-Leibler's measure according to the method described by Nowinski and associates. 28,29 The AC-PC line was approximated by the vector from the most inferior points of the genu to that of the splenium of the CC in the mid-sagittal plane. The CC in the mid-sagittal plane was extracted using a minimum FA threshold of 0.25 and a maximum crossing angle threshold of 459be-tween the normal vector of the mid-sagittal plane and the major eigenvector of the diŠusion tensor.…”

Section: Data Preprocessingmentioning

confidence: 99%

Automatic Extraction of the Cingulum Bundle in Diffusion Tensor Tract-specific Analysis: Feasibility Study in Parkinson's Disease with and without Dementia

et al. 2013

View full text Add to dashboard Cite

Purpose: Tract-speciˆc analysis (TSA) measures diŠusion parameters along a speciˆĉ ber that has been extracted byˆber tracking using manual regions of interest (ROIs), but TSA is limited by its requirement for manual operation, poor reproducibility, and high time consumption. We aimed to develop a fully automated extraction method for the cingulum bundle (CB) and to apply the method to TSA in neurobehavioral disorders such as Parkinson's disease (PD).Materials and Methods: We introduce the voxel classiˆcation (VC) and auto diŠusion tensorˆber-tracking (AFT) methods of extraction. The VC method directly extracts the CB, skipping theˆber-tracking step, whereas the AFT method usesˆber tracking from automatically selected ROIs. We compared the results of VC and AFT to those obtained by manual diŠusion tensorˆber tracking (MFT) performed by 3 operators. We quantiˆed the Jaccard similarity index among the 3 methods in data from 20 subjects (10 normal controls [NC] and 10 patients with Parkinson's disease dementia [PDD]). We used all 3 extraction methods (VC, AFT, and MFT) to calculate the fractional anisotropy (FA) values of the anterior and posterior CB for 15 NC subjects, 15 with PD, and 15 with PDD.Results: The Jaccard index between results of AFT and MFT, 0.72, was similar to the inter-operator Jaccard index of MFT. However, the Jaccard indices between VC and MFT and between VC and AFT were lower. Consequently, the VC method classiˆed among 3 diŠerent groups (NC, PD, and PDD), whereas the others classiˆed only 2 diŠerent groups (NC, PD or PDD).Conclusion: For TSA in Parkinson's disease, the VC method can be more useful than the AFT and MFT methods for extracting the CB. In addition, the results of patient data analysis suggest that a reduction of FA in the posterior CB may represent a useful biological index for monitoring PD and PDD.

show abstract

Section: Data Preprocessingmentioning

confidence: 99%

Automatic Extraction of the Cingulum Bundle in Diffusion Tensor Tract-specific Analysis: Feasibility Study in Parkinson's Disease with and without Dementia

et al. 2013

View full text Add to dashboard Cite

show abstract

“…Challenges occur due to accentuated asymmetries found in patients with schizophrenia, epilepsy and Alzheimer's diseases as well as cerebral malformations caused eventually by surgical procedures. Approaches in the second group try to detect the fissure mainly by applying snakes [5], the Hough transform [6], or Kullback-Leibler divergence [7]. The fact that the fissure is often not planar even in normal brains limits robustness of these approaches [3].…”

Section: Introductionmentioning

confidence: 99%

Reliable extraction of the mid-sagittal plane in 3D brain MRI via hierarchical landmark detection

Schwing

Zheng

2014

2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

Reliable detection of the mid-sagittal plane is the key for brain image registration, asymmetry analysis, and group studies. Although the brain presents most of the time a regular structure, outliers in the data consisting of brain tumors or various deformations pose challenges to the existing approaches. We propose in this paper a robust approach for mid-sagittal plane extraction based on hierarchical landmark detection. Crossvalidated results demonstrate comparable accuracy (1.08• plane normal error) to those of human experts on a volumetric data set that contains pediatric patients as well as elderly with different diseases.

show abstract

“…This method uses two-stage non-interative searching strategy to localize the IF region and to identify IF line segments with the maximum local symmetry which are subsequently used to construct the MSP. The second method presented in [21] defines the MSP as a plane with the maximum KL-measure with respect to the reference planes. This approach has been validated for MR images (T1, T2, MRA, SPGR, FLAIR) and tried initially for a few CT scans.…”

Section: Introductionmentioning

confidence: 99%

“…A common limitation possessed by the previous methods is that most of them have a preliminary assumption that the MSP should be oriented close to a vertical plane [18,20,21,24,25], except [7]. Therefore, the algorithms break down when the head is tilted more than several degrees, for instance, 30 • in method [20] or 7 • in coronal direction in method [21].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust calculation of the midsagittal plane in CT scans using the Kullback–Leibler’s measure

et al. 2009

View full text Add to dashboard Cite

show abstract

Extraction of the midsagittal plane from morphological neuroimages using the Kullback–Leibler’s measure

Cited by 47 publications

References 25 publications

Automatic Extraction of the Cingulum Bundle in Diffusion Tensor Tract-specific Analysis: Feasibility Study in Parkinson's Disease with and without Dementia

Automatic Extraction of the Cingulum Bundle in Diffusion Tensor Tract-specific Analysis: Feasibility Study in Parkinson's Disease with and without Dementia

Reliable extraction of the mid-sagittal plane in 3D brain MRI via hierarchical landmark detection

Robust calculation of the midsagittal plane in CT scans using the Kullback–Leibler’s measure

Contact Info

Product

Resources

About