Automated segmentation of multiple sclerosis lesions by model outlier detection

Leemput, Koen Van; Maes, Frederik; Vandermeulen, Dirk; Colchester, Alan C. F.; Suetens, Paul

doi:10.1109/42.938237

Cited by 437 publications

(402 citation statements)

References 35 publications

Supporting

Mentioning

399

Contrasting

Order By: Relevance

“…These metrics were originally applied by Leemput et al 11 , Zijdenbos et al 20 , and Anbeek et al 1 to measure the concordance of their results with manual segmentation of white matter lesions. With their segmentation techniques, Leemput et al 11 and Zijdenbos et al 20 , achieved similarity indices of 0.51 and 0.68 respectively, while Anbeek et al 1 , achieved a value of 0.7 for SI for all of their study patients. In our present approach this value is 0.78 suggesting the superior performance of our method.…”

Section: Discussionmentioning

confidence: 99%

“…While this appears to be true for gray matter (GM) and white matter (WM) classes which follow Gaussian distribution, lesions and CSF do not follow any known distribution. For example, Van Leemput et al 11 have identified MS lesions as outliers that are not well handled by this model. In contrast, nonparametric methods such as Parzen window classifier 6 do not assume any distribution for tissues.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unified Approach for Multiple Sclerosis Lesion Segmentation on Brain MRI

Sajja¹,

Datta²,

He³

et al. 2006

Ann Biomed Eng

111

152

View full text Add to dashboard Cite

The presence of large number of false lesion classification on segmented brain MR images is a major problem in the accurate determination of lesion volumes in multiple sclerosis (MS) brains. In order to minimize the false lesion classifications, a strategy that combines parametric and nonparametric techniques is developed and implemented. This approach uses the information from the proton density (PD)-and T2-weighted and fluid attenuation inversion recovery (FLAIR) images. This strategy involves CSF and lesion classification using the Parzen window classifier. Image processing, morphological operations and ratio maps of PD and T2 weighted images are used for minimizing false positives. Contextual information is exploited for minimizing the false negative lesion classifications using hidden Markov random field -expectation maximization (HMRF-EM) algorithm. Lesions are delineated using fuzzy connectivity. The performance of this algorithm is quantitatively evaluated on 23 MS patients. Similarity index, percentages of over, under and correctestimations of lesions are computed by spatially comparing the results of present procedure with expert manual segmentation. The automated processing scheme detected 80% of the manually segmented lesions in the case of low-lesion load and 93% of the lesions in those cases with high lesion load.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Unified Approach for Multiple Sclerosis Lesion Segmentation on Brain MRI

Sajja¹,

Datta²,

He³

et al. 2006

Ann Biomed Eng

111

152

View full text Add to dashboard Cite

show abstract

“…Van Leemput et al (13,14) extended the concept and developed automatic segmentation of MR images of normal brains by statistical classification, using an atlas prior for initialization and also for geometric constraints. A most recent extension detects brain lesions as outliers (15) and was successfully applied for detection of multiple sclerosis lesions. Brain tumors, however, can't be simply modeled as intensity outliers due to overlapping intensities with normal tissue and/or significant size.…”

Section: Introductionmentioning

confidence: 99%

Automatic brain tumor segmentation by subject specific modification of atlas priors1

Prastawa¹,

Bullitt

Moon³

et al. 2003

Academic Radiology

187

143

View full text Add to dashboard Cite

Rationale and Objectives-Manual segmentation of brain tumors from magnetic resonance (MR) images is a challenging and time-consuming task. The authors have developed an automated system for brain tumor segmentation that provides objective, reproducible segmentations that are close to the manual results. Additionally, the method segments white matter, grey matter, cerebrospinal fluid, and edema. The segmentation of pathology and healthy structures is crucial for surgical planning and intervention.Material and Methods-The method performs the segmentation of a registered set of MR images using an Expectation-Maximization scheme. The segmentation is guided by a spatial probabilistic atlas that contains expert prior knowledge about brain structures. This atlas is modified with the subject specific brain tumor prior that is computed based on contrast enhancement. Conclusion-The automated method can be applied to different types of tumors. Although the semi-automated method generates results that have higher level of agreement with the manual raters, the automatic method has the advantage of requiring no user supervision. Results-Five

show abstract

“…Boudraa et al [57] employed the FCM algorithm to 1.5 T twodimensional (2-D) MRI images for classifying normal and abnormal brain structures. Leemput et al [58] designed an automated method by using an intensity-based tissue classification and a stochastic model for detection of MS lesions from 3-D images. Zijdenbos et al [59] developed a CAD framework for the pipeline analysis of MS lesions in MRI data.…”

Section: Multiple Sclerosis Diagnosismentioning

confidence: 99%