A. Zijdenbos, B. Dawant, and R. Marjolin, "Morphometric analysis of white matter lesions in mr images: Methods and validation," IEEE TMI 13(4), pp. 716--724, 1994.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....measures using two independent two dimensional segmentation occasions, a measure of similarity between two segmentations was adopted. For voxel by voxel classification agreement, as is necessary for comparison of MRI segmentation datasets, the Dice similarity coefficient (DSC) has been employed [15, 16]. The DSC is given by 2 2 A n A n A A n c b a a = 1) where a is the number of voxels common to (shared by) both datasets; b is the number of voxels unique to the first dataset; c is the number of voxels unique to the second dataset; A 1 and A 2 are the set of ....

....of voxels unique to the second dataset; A 1 and A 2 are the set of voxels identified as signal in the first and second dataset, respectively and; n A is the number of elements in set A. It has been shown that the DSC may be interpreted as a special case of the widely used Kappa coefficient (see [15], 17] 18] The DSC is appropriate in comparison of agreement studies, and has been employed in previous studies of this nature [17] including, specifically, segmentationagreement [15] It is generally accepted that a value of DSC 0.7 represents excellent agreement [15] 13 Next, the ....

[Article contains additional citation context not shown here]

A. P. Zijdenbos, B. M. Dawant, R. A. Margolin, and A. C. Palmer, "Morphometric Analysis of White Matter Lesions in MR Images: Method and Validation," IEEE Transactions on Medical Imaging, 13, 716-724, 1994.

....which is the classification truth of each voxel. For simplicity, we assume a two class truth by labeling the non tumor class as C 0 and tumor class as C 1 . For the purpose of comparing two sets of binary segmentation results, several accuracy and reliability metrics may be found in the literature [2]. For example, Jaccard (JSC) 3] and Dice (DSC) 4] similarity coefficients are typically used as a measure of overlap; DSC ranges from 0, indicating no similarity between these two sets of binary segmentation results, to 1, indicating complete agreement. In order to evaluate the performance of a ....

Zijdenbos, A. P., Dawant, B.M., Margolin, R. A., Palmer, A. C.: Morphometric analysis of white matter lesions in MR images: method and validation. IEEE Transactions on Medical Imaging 13 (1994) 716-724.

....more classes restricts the system further and therefore lets the algorithm converge faster. 4 Validation To validate this new approach, the left and right STG of four subjects was manually segmented by three raters. We used the Dice Similarity Measure (DSC) described by Zijdenbos et al. [14] to compare manual to the EM MF LP segmentation. The DSC S =2# A1#A2 A1 A2 is derived from the kappa statistic, where A 1 and A 2 are the two segmented areas. S 70 is seen as an excellent agreement between the two. In our approach, in all cases the similarity measure for the ....

A. P. Zijdenbos, B. M. Dawant, R. A. Margolin , A. C. Palmer, "Morphometric analysis of white matter lesions in mr images: Method and validation," IEEE Transactions on Medical Imaging, vol. 13, no. 4, pp. 716--724, 1994.

.... of metrics have been proposed to compare segmentations, including volume measures, spatial overlap measures (such as Dice [3] and Jaccard similarities [4] and boundary measures (such as the Hausdorff measure) Agreement measures between different experts have also been explored for this purpose [5]. Studies of rules to combine segmentations to form an estimate of the underlying true segmentation have as yet not demonstrated any one scheme to be much favourable to another. Per voxel voting schemes have been used in practice [6,7] We present here a new Expectation Maximization (EM) ....

A. P. Zijdenbos, B. M. Dawant, R. A. Margolin, and A. C. Palmer, "Morphometric Analysis of White Matter Lesions in MR Images: Method and Validation," IEEE Transactions on Medical Imaging, vol. 13, pp. 716--724, December 1994.

.... of metrics have been proposed to compare segmentations, including volume measures, spatial overlap measures (such as Dice [2] and Jaccard similarities [3] and boundary measures (such as Hausdorff distance) Agreement measures between different experts have also been explored for this purpose [4]. Studies of rules to combine segmentations to form an estimate of the underlying true segmentation have as yet not demonstrated any one scheme much favourable to another. Pervoxel voting schemes have been used in practice [5] We present here a method for generating both a maximum likelihood ....

Alex P. Zijdenbos, Benoit M. Dawant, Richard A. Margolin, and Andrew C. Palmer, "Morphometric Analysis of White Matter Lesions in MR Images: Method and Validation," IEEE Transactions on Medical Imaging, vol. 13, no. 4, pp. 716--724, December 1994.

....not clear how a human rater combines information obtained from the di#erent channels when multi spectral MR data are examined. Therefore, considerable e#orts have been made by the medical imag#l[ community to come up with fast automated methods that produce more objective and reproducible results [2, 3, 4]. However, most of these techniques still require some human interaction and or ad hoc processing steps, which can make the results not fully objective. Zijdenbos et. al 5, 6] proposed and validated a fully automated pipeline for MS lesionseg# entation from T1 , T2 and PD weig# ted imag#Dfl ....

] A.P. Zijdenbos, B.M. Dawant, R.A. Marg#W in, and A.C. Palmer. Morphometric analysis of white matter lesions in MR imag es: Method and validation. IEEE Transactions on Medical Imaging,

....clear how a human rater combines information obtained from the different channels when multi spectral MR data are examined. Therefore, considerable efforts have been made by the medical imaging community to come up with fast automated methods that produce more objective and reproducible results [2 4]. However, most of these techniques still require some human interaction and or ad hoc processing steps, which can make the results not fully objective. Zijdenbos et. al [5, 6] proposed and validated a fully automated pipeline for MS lesion segmentation from T1 , T2 and PD weighted images. ....

.... take into account any spatial correspondence of the segmented lesions [14] We therefore calculated indices, the definition of which is given in table 2, which take account of the degree of correspondence between two segmentations: the similarity index which was previously used by Zijdenbos et al. [2], the overlap index, and the global spatial correspondence indices recently proposed by Bello and Colchester [14] Fig. 2. Visual comparison of the MS lesion labeling by two experts and by the algorithm. Top: T1 , T2 and PD weighted image. Bottom: MS lesions overlayed in bright color on the ....

A.P. Zijdenbos, B.M. Dawant, R.A. Margolin, and A.C. Palmer. Morphometric analysis of white matter lesions in MR images: Method and validation. IEEE Transactions on Medical Imaging, 13(4):716--724, december 1994.

....into contiguous regions of interest. The problem has recently received much attention largely due to the improved delity and resolution of MR imaging systems, and the e ective clinical utility of image analysis and understanding in diagnosis, monitoring, and intervention (e.g. see references [1] [4] For example, pathological studies show that many neurological diseases are accompanied by subtle abnormal changes in brain tissue quantities and volumes as shown in reference [2] Because of the virtual impossibility for clinicians to quantitatively analyze these pathological changes ....

A. P. Zijdenbos, B. M. Dawant, R. A. Margolin, and A. C. Palmer, \Morphometric analysis of white matter lesions in MR images: method and validation," IEEE Trans. Med. Imaging, vol. 13, no. 4, pp. 716-724, December 1994.

....disease is involved, which has to be used to perform a fine discrimination between white matter (WM) gray matter (GM) peripheral and ventricular cerebro spinal fluid (CSF) in order to locate all possible sites of the lesions. Several approaches have been proposed in the last years: Zijdenbos [15] proposes a neural approach to segment brain in five classes: background, white matter, gray matter, CSF and white matter lesions (WML) by means of a multi layer perceptron trained with the back propagation algorithm. Kamber [11] and Johnston [10] propose stochastic approaches to the 3D ....

Zijdenbos, A.P., Dawant, B.M., Margolin, R.A., Palmer, A.C., Morphometric Analysis of White Matter Lesions in MR Images: Method and Validation, IEEE Transactions on Medical Imaging, vol. 13, no. 4, pp. 716/724, December 1994.

No context found.

A. Zijdenbos, B. Dawant, and R. Marjolin, "Morphometric analysis of white matter lesions in mr images: Methods and validation," IEEE TMI 13(4), pp. 716--724, 1994.

No context found.

Zijdenbos A., Dawant B., and Margolin R. Morphometric analysis of white matter lesions in MR images: Method and validation. IEEE TMI, 13(4):716--724, 1994.

No context found.

Zijdenbos, A., Dawant, B., Margolin, R., 1994. Morphometric analysis of white matter lesions in MR images: Method and validation. IEEE TMI 13 (4), 716--724.

No context found.

A. P. Zijdenbos et al., "Morphometric analysis of white matter lesions in mr images: method and validation," IEEE TMI, vol. 13, no. 4, pp. 716--724, 1994. 136

No context found.

A. P. Zijdenbos, B. M. Dawant, R. A. Margolin, and A. C. Palmer, "Morphometric analysis of white matter lesions in MR images: Method and validation," IEEE Trans Med Imag 13, pp. 716--724, Dec. 1994.

No context found.

A.P. Zijdenbos, B.M. Dawant, R.A. Margolin, and A.C. Palmer. Morphometric analysis of white matter lesions in MR images: method and validation. IEEE Trans. Medical Imaging, 13: 716-724, 1994.

No context found.

ZIJDENBOS A., DAWANT B., MARGOLIN R., PALMER A.: Morphometric analysis of white matter lesions in mr images: Method and validation. IEEE Transactions on Medical Imaging 13, 4 (1994), 716--724. The Eurographics Association 2004.

No context found.

Zijdenbos AP, Dawant BM, Margolin RA, Palmer AC. Morphometric analysis of white matter lesions in MR images: method and validation. IEEE Trans Med Imaging 1994; 13:716 --724.

No context found.

A. Zijdenbos, B. Dawant, A. Margolin, Morphometric analysis of white matter lesions in mr images: Method and validation, IEEE Transactions on Medical Imaging 13 (4) (1994) 716--724.

No context found.

A. P. Zijdenbos, B. M. Dawant, R. A. Margolin, and A. C. Palmer, "Morphometric analysis of white matter lesions in MR images: Method and validation," IEEE Trans Med Imag 13, pp. 716--724, Dec. 1994.

No context found.

Zijdenbos, A., Dawant, B., Margolin, A.: Morphometric analysis of white matter lesions in mr images: Method and validation. IEEE Transactions on Medical Imaging 13 (1994) 716--724

No context found.

Zijdenbos A., Dawant B., and Margolin R. Morphometric analysis of white matter lesions in MR images: Method and validation. IEEE TMI, 13(4):716--724, 1994.

No context found.

A.P. Zijdenbos et al., "Morphometric analysis of white matter lesions in MR images: method and validation," IEEE Trans. Medical Imaging, vol. 13, no. 4, pp. 716--724, 1994.

No context found.

A. P. Zijdenbos, B. M. Dawant, R. A. Margolin, and A. C. Palmer, "Morphometric Analysis of White Matter Lesions in MR Images: Method and Validation," IEEE Transactions on Medical Imaging, vol. 13, no. 4, pp. 716-- 724, December 1994.

No context found.

A. Zijdenbos, B. M. Dawant, R. A. Margolin, and A. C. Palmer. Morphometric analysis of white matter lesions in MR images: Method and validation. IEEE Transactions on Medical Imaging, 13#4#:716#724, December 1994.

No context found.

Zijdenbos AP, Dawant BM, Margolin RA, Palmer AC. Morphometric analysis of white matter lesions in MR images: method and validation. IEEE Trans Med Imaging 1994;13:716--724.

First 50 documents

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC