Automated segmentation of multiple sclerosis lesions by model outlier detection

By K. V. Leemput, Frederik Maes, Dirk Vandermeulen, A. Colchester, Paul Suetens. IEEE Transactions on Medical Imaging, 2001

555 citations recorded by the source corpus.

Subfields: Biophysics, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/d5213abee80d40e6f0838c7dc5c4b8bbf4a8417c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Probabilistic segmentation of white matter lesions in MR imaging (2004, methodology): “Van Leemput and Zijdenbos also use the similarity index for measuring the correspondence with a manual segmentation, which reaches maxima of 0.51 and 0.68, respectively .”
The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) (2015, background): “In addition, it was observed that a good understanding of the image resolution and amount of image subsampling can lead to a good trade-off between speed improvements and segmentation quality.”
Constructing Subject- and Disease-Specific Effect Maps: Application to Neurodegenerative Diseases (2016, methodology): “This approach has been applied to brain lesion [13,14,15,16] and recently to neurodegenerative diseases [17].”
A Review of Methods for Correction of Intensity Inhomogeneity in MRI (2007, methodology): “Other automatic approaches [22], [24], [60], [65] used a statistical prob-”
Deep 3D Convolutional Encoder Networks With Shortcuts for Multiscale Feature Integration Applied to Multiple Sclerosis Lesion Segmentation (2016, methodology): “, a subject-specific generative model of tissue intensities [32], [34], [41], [43], or a generative model of image patches representing a healthy population [44].”
Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging (2013, methodology): “IIH correction methods (Vovk et al., 2007) reduce the smooth variation of intensity of the tissues to simplify subsequent segmentation, although some segmentation methods take this effect into account (Ashburner and Friston, 2005; Van Leemput et al., 1999; Wells III et al., 1996).”
Longitudinal multiple sclerosis lesion segmentation: Resource and challenge (2017, unknown): “As previously mentioned Aït-Ali et al. (2005) extended the outlier detection approach (Van Leemput et al., 2001) to the entire time series using TLE followed by reﬁnement steps.”
Reconstructing subject‐specific effect maps (2017, unknown): “stributions, this procedure essentially computes normalized z-scores with outliers having the highest values. Outlier detection has been used for detecting brain lesions and neurodegenerative changes [36,38,30,41]. The main drawback of this approach is its unspecic nature. Outlier detection identies”
Automatic "pipeline" analysis of 3-D MRI data for clinical trials: application to multiple sclerosis (2002, methodology): “Recently, Van Leemput et al.[49] have proposed an adaptive classifier which is re-trained on each individual scan rather than trained once and subsequently applied to all data.”
A review of atlas-based segmentation for magnetic resonance brain images (2011, methodology): “[77] extended their previous work [76] to detect ultiple sclerosis lesions by searching for outliers that follow set of user-defined rules, i.”
Brain templates and atlases (2012, methodology): “These atlases are often used as priors for subsequent lesion classification (e.g. van Leemput et al., 2001).”
A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesions (2009, unknown): “Moreover, none of these techniques except (Leemput et al., 2001) simultaneously compensates for RF field inhomogeneities.”
White matter lesion extension to automatic brain tissue segmentation on MRI (2009, unknown): “Other studies (Zijdenbos et al.,1998; Van Leemput et al., 2001 ) also reported high interobserver and intraobserver variability in WML segmentation and the resulting problem with validating automated segmentation methods.”
q-Space Deep Learning for Twelve-Fold Shorter and Model-Free Diffusion MRI Scans (2015, methodology): “State-of-the-art automatic segmentation [15, 16] (based on non-diffusion images with spatial priors) into healthy white matter (WM), grey matter (GM), cerebrospinal fluid (CSF) and multiple sclerosis lesions was used as ground truth for our proof-of-concept model-free segmentation (based on diffusio”
Outlier Analysis (2013, methodology): “General references on image outlier detection may be found in [68, 206, 374, 466, 393, 418, 446, 447].”