Segmentation and quantification of black holes in multiple sclerosis

Datta, Sushmita; Sajja, Balasrinivasa R.; He, Renjie; Wolinsky, Jerry S.; Gupta, Rakesh K.; Narayana, Ponnada A.

doi:10.1016/j.neuroimage.2005.07.042

Cited by 71 publications

(73 citation statements)

References 18 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…25,26 These methods have limited efficiency and reproducibility, particularly with regard to assessing large data sets in multicenter clinical trial settings or comparing data across analysis centers. Recently, Datta et al 27 developed an automated method based on fuzzy connectedness principles for identification and quantification of T1-hypointense lesions. This method holds promise as it involves minimal operator interaction.…”

Section: T1 Hypointense Lesionsmentioning

confidence: 99%

MRI in Multiple Sclerosis: What’s Inside the Toolbox?

et al. 2007

View full text Add to dashboard Cite

Summary: Magnetic resonance imaging (MRI) has played a central role in the diagnosis and management of multiple sclerosis (MS). In addition, MRI metrics have become key supportive outcome measures to explore drug efficacy in clinical trials. Conventional MRI measures have contributed to the understanding of MS pathophysiology at the macroscopic level yet have failed to provide a complete picture of underlying MS pathology. They also show relatively weak relationships to clinical status such as predictive strength for clinical progression. Advanced quantitative MRI measures such as magnetization transfer, spectroscopy, diffusion imaging, and relaxometry techniques are somewhat more specific and sensitive for underlying pathology. These measures are particularly useful in revealing diffuse damage in cerebral white and gray matter and therefore may help resolve the dissociation between clinical and conventional MRI findings. In this article, we provide an overview of the array of tools available with brain and spinal cord MRI technology as it is applied to MS. We review the most recent data regarding the role of conventional and advanced MRI techniques in the assessment of MS. We focus on the most relevant pathologic and clinical correlation studies relevant to these measures.

show abstract

Section: T1 Hypointense Lesionsmentioning

confidence: 99%

MRI in Multiple Sclerosis: What’s Inside the Toolbox?

et al. 2007

View full text Add to dashboard Cite

show abstract

“…This module was rewritten in IDL (Interactive Data Language; RSI Inc., Boulder, CO, USA) and integrated with rest of the analysis software used in these studies. The extrameningeal tissues were identified on the FSE images and removed (via image stripping or brain extraction) using a semiautomatic procedure described elsewhere (13,14). Since images acquired with different sequences were coregistered with the FSE images, the mask generated from the FSE images following extrameningeal tissue removal was applied for stripping the FLAIR and T1-weighted images.…”

Section: Image Preprocessingmentioning

confidence: 99%

Segmentation of gadolinium‐enhanced lesions on MRI in multiple sclerosis

Datta

Sajja

et al. 2007

Magnetic Resonance Imaging

Self Cite

View full text Add to dashboard Cite

Purpose: To develop and implement a method for identification and quantification of gadolinium (Gd) enhancements with minimal human intervention. Materials and Methods:Dual fast spin echo (FSE), fluid attenuation inversion recovery (FLAIR), and pre-and postcontrast T1-weighted spin echo were acquired on 22 subjects. The enhancements were identified on the postcontrast T1-weighted images based on morphological operations. A single threshold based on the ratio of the difference of postcontrast and precontrast T1 images with that of precontrast T1 images is applied to the reconstructed images to reduce the false classifications. False classification of enhancements arising from enhancing vasculature and structures such as the choroid plexus that lack a blood-brain barrier were reduced by assuming that the true enhancements are always associated with hyperintense lesions on T2-weighted images (T2 lesions). The enhanced lesions were further delineated based on fuzzy connectivity. Results:The segmented Gd enhancements were evaluated quantitatively with manually identified enhancements based on similarity measures. The average similarity index (SI) of 0.76 suggests excellent performance of the proposed methodology. The Bland-Altman plot shows a close agreement between the results obtained manually and those based on the proposed methodology. Conclusion:The proposed algorithm identifies and quantifies Gd enhancements accurately with minimal human intervention.

show abstract

“…We describe the algorithm for extending the G-K algorithm to multi-channel MR image segmentation by denoting (12) and (13) where [15,17] denotes the norm matrix. The Lagrangean multiplier is adopted to include the constraints into the optimization, and the augmented objective function becomes (14) Taking the derivative of F m with respect to u ik for p >1, and equating to zero, and with the constraint we get (15) For a positive definite matrix L, for any vector x, we know that (16) Taking the derivative of F m with respect to v i and equating to zero, and using the result in Eqn.…”

Section: Extension Of Afcm Algorithm With G-k Measurementioning

confidence: 99%

“…Prior to segmentation, the extrameningeal tissues from the images were removed using a semiautomatic procedure that is described elsewhere [12,29] and these stripped brain images were used as the input to the algorithms. The output of the algorithms included inhomogeneity corrected images, cluster centers, bias field, and memberships of the image volume.…”

Section: Image Acquisitionmentioning

confidence: 99%

Generalized fuzzy clustering for segmentation of multi-spectral magnetic resonance images

Datta

Sajja

et al. 2008

Computerized Medical Imaging and Graphics

Self Cite

View full text Add to dashboard Cite

An integrated approach for multi-spectral segmentation of MR images is presented. This method is based on the fuzzy c-means (FCM) and includes bias field correction and contextual constraints over spatial intensity distribution and accounts for the non-spherical cluster's shape in the feature space. The bias field is modeled as a linear combination of smooth polynomial basis functions for fast computation in the clustering iterations. Regularization terms for the neighborhood continuity of intensity are added into the FCM cost functions. To reduce the computational complexity, the contextual regularizations are separated from the clustering iterations. Since the feature space is not isotropic, distance measure adopted in Gustafson-Kessel (G-K) algorithm is used instead of the Euclidean distance, to account for the nonspherical shape of the clusters in the feature space. These algorithms are quantitatively evaluated on MR brain images using the similarity measures.

show abstract

Segmentation and quantification of black holes in multiple sclerosis

Cited by 71 publications

References 18 publications

MRI in Multiple Sclerosis: What’s Inside the Toolbox?

MRI in Multiple Sclerosis: What’s Inside the Toolbox?

Segmentation of gadolinium‐enhanced lesions on MRI in multiple sclerosis

Generalized fuzzy clustering for segmentation of multi-spectral magnetic resonance images

Contact Info

Product

Resources

About