STEPS: Similarity and Truth Estimation for Propagated Segmentations and its application to hippocampal segmentation and brain parcelation

Topic: Brain proteins, microglia and lab models

Anatomical segmentation of structures of interest is critical to quantitative analysis in medical imaging. Several automated multi-atlas based segmentation propagation methods that utilise manual delineations from multiple templates appear promising. However, high levels of accuracy and reliability are needed for use in diagnosis or in clinical trials. We propose a new local ranking strategy for template selection based on the locally normalised cross correlation (LNCC) and an extension to the classical STAPLE algorithm by Warfield et al. (2004), which we refer to as STEPS for Similarity and Truth Estimation for Propagated Segmentations. It addresses the well-known problems of local vs. global image matching and the bias introduced in the performance estimation due to structure size. We assessed the method on hippocampal segmentation using a leave-one-out cross validation with optimised model parameters; STEPS achieved a mean Dice score of 0.925 when compared with manual segmentation. This was significantly better in terms of segmentation accuracy when compared to other state-of-the-art fusion techniques. Furthermore, due to the finer anatomical scale, STEPS also obtains more accurate segmentations even when using only a third of the templates, reducing the dependence on large template databases. Using a subset of Alzheimer's Disease Neuroimaging Initiative (ADNI) scans from different MRI imaging systems and protocols, STEPS yielded similarly accurate segmentations (Dice=0.903). A cross-sectional and longitudinal hippocampal volumetric study was performed on the ADNI database. Mean±SD hippocampal volume (mm(3)) was 5195 ± 656 for controls; 4786 ± 781 for MCI; and 4427 ± 903 for Alzheimer's disease patients and hippocampal atrophy rates (%/year) of 1.09 ± 3.0, 2.74 ± 3.5 and 4.04 ± 3.6 respectively. Statistically significant (p<10(-3)) differences were found between disease groups for both hippocampal volume and volume change rates. Finally, STEPS was also applied in a multi-label segmentation propagation scenario using a leave-one-out cross validation, in order to parcellate 83 separate structures of the brain. Comparisons of STEPS with state-of-the-art multi-label fusion algorithms showed statistically significant segmentation accuracy improvements (p<10(-4)) in several key structures.

Key findings

• We assessed the method on hippocampal segmentation using a leave-one-out cross validation with optimised model parameters; STEPS achieved a mean Dice score of 0.925 when compared with manual segmentation.
• This was significantly better in terms of segmentation accuracy when compared to other state-of-the-art fusion techniques.
• Statistically significant (p<10(-3)) differences were found between disease groups for both hippocampal volume and volume change rates.
• Comparisons of STEPS with state-of-the-art multi-label fusion algorithms showed statistically significant segmentation accuracy improvements (p<10(-4)) in several key structures.

Study details

• Study designcross-sectional
• Evidence strengthModerate

Read the original

• DOI: 10.1016/j.media.2013.02.006
• PubMed: 23510558
• Original source →

Free copy unknown: no free-copy check has an answer for this record yet. That does not mean it is paywalled.

@article{jorgecardoso2013-23510558,
  author  = {Jorge Cardoso, M. and Leung, K. and Modat, M. and Keihaninejad, S. and Cash, D. and Barnes, J. and Fox, N. C. and Ourselin, S. and others},
  title   = {{STEPS: Similarity and Truth Estimation for Propagated Segmentations and its application to hippocampal segmentation and brain parcelation}},
  journal = {Medical image analysis},
  year    = {2013},
  doi     = {10.1016/j.media.2013.02.006},
  pmid    = {23510558},
  url     = {https://doi.org/10.1016/j.media.2013.02.006}
}

Related studies in Hippocampus size on brain scans

• A computational atlas of the hippocampal formation using ex vivo, ultra-high resolution MRI: Application to adaptive segmentation of in vivo MRI NeuroImage · 2015-04-29 · usefulness score 36/100
• Heritability of brain morphology related to schizophrenia: a large-scale automated magnetic resonance imaging segmentation study Biological psychiatry · 2007-08-28 · usefulness score 45/100
• Can voxel based morphometry, manual segmentation and automated segmentation equally detect hippocampal volume differences in acute depression? NeuroImage · 2008-11-21 · usefulness score 67/100
• Segmentation of the mouse hippocampal formation in magnetic resonance images NeuroImage · 2011-06-17 · usefulness score 52/100
• The Hippocampus in Depression: More Than the Sum of Its Parts? Advanced Hippocampal Substructure Segmentation in Depression Biological psychiatry · 2018-09-06 · usefulness score 45/100
• Hippocampal volume assessment in temporal lobe epilepsy: How good is automated segmentation? Epilepsia · 2009-08-13 · usefulness score 40/100

Similar studies

• Hippocampus segmentation in MR images using atlas registration, voxel classification, and graph cuts 2008 · Hippocampus size on brain scans
• A longitudinal study of brain morphometrics using quantitative magnetic resonance imaging and difference image analysis 2003 · Hippocampus size on brain scans
• Comparing manual and automatic segmentation of hippocampal volumes: reliability and validity issues in younger and older brains 2014 · Hippocampus size on brain scans
• Identification of common variants associated with human hippocampal and intracranial volumes 2012 · Hippocampus size on brain scans
• Navigation expertise and the human hippocampus: a structural brain imaging analysis 2003 · Hippocampus size on brain scans
• Trauma, PTSD, and the Developing Brain 2017 · Hippocampus size on brain scans

More on Hippocampus size on brain scans

• A review that covers this ground Defining the human hippocampus in cerebral magnetic resonance images--an overview of current segmentation protocols NeuroImage · 2009-05-15 · usefulness score 36/100
• Newest in this subject Biomarker Changes during 20 Years Preceding Alzheimer's Disease The New England journal of medicine · 2024-02-01 · Peer-reviewed · usefulness score 69/100
• Newest in this subject Clinical safety and efficacy of allogenic human adipose mesenchymal stromal cells-derived exosomes in patients with mild to moderate Alzheimer's disease: a phase I/II clinical trial General psychiatry · 2023-10-11 · Peer-reviewed · usefulness score 43/100

See all studies in Hippocampus size on brain scans →