2020
DOI: 10.1007/978-3-030-61056-2_9
|View full text |Cite
|
Sign up to set email alerts
|

Combined Estimation of Shape and Pose for Statistical Analysis of Articulating Joints

Abstract: Quantifying shape variations in articulated joints is of utmost interest to understand the underlying joint biomechanics and associated clinical symptoms. For joint comparisons and analysis, the relative positions of the bones can confound subsequent analysis. Clinicians design specific image acquisition protocols to neutralize the individual pose variations. However, recent studies have shown that even specific acquisition protocols fail to achieve consistent pose. The individual pose variations are largely a… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
11
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
4
1

Relationship

2
3

Authors

Journals

citations
Cited by 5 publications
(11 citation statements)
references
References 26 publications
0
11
0
Order By: Relevance
“…Our findings suggest that indeed, a unified multi-object modelling approach is much better suited for such segmentation scenarios. One benefit of the DMFC-GPM is the approach maintains the statistics of single object variation such as SSMs [4], [7], SAMs [3], [6] or SSPMs [12], [13], [14], [15] and these can be retrieved on demand without any need to retrain the model. An additional benefit is that where strong correlations between different objects exist, these can be leveraged to make a prediction of a targeted object with partial or no observation of the target in the image.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…Our findings suggest that indeed, a unified multi-object modelling approach is much better suited for such segmentation scenarios. One benefit of the DMFC-GPM is the approach maintains the statistics of single object variation such as SSMs [4], [7], SAMs [3], [6] or SSPMs [12], [13], [14], [15] and these can be retrieved on demand without any need to retrain the model. An additional benefit is that where strong correlations between different objects exist, these can be leveraged to make a prediction of a targeted object with partial or no observation of the target in the image.…”
Section: Discussionmentioning
confidence: 99%
“…This allows the integration of inter-object shape correlations in the latent space, which is important for understanding anatomicalphysiological relationships between articulated objects. Statistical modelling of shape and pose: Similar to the shape case, pose variation analysis using linear descriptors has been previously reported [12], [13], [14], [15]. Reports abound in the literature on efforts to use methods more suited for managing the non-linearity of pose descriptors [5], [16], [17], [18].…”
Section: Related Workmentioning
confidence: 99%
“…From this initial Unscaled SSM , a two‐step alignment method described by Agrawal and colleagues was used to remove variability in size and pose from the model (Figure 1). 33 In the first alignment step, hip size (i.e., scale) was normalized across the population via generalized Procrustes analysis, resulting in the SSM with Pose . In the second step, mean femur and hemi‐pelvis shapes generated from the SSM with Pose were used as alignment templates to remove individual pose variations of the separate bones (femur and hemi‐pelvis); these shapes were then used to generate the SSM of Shape (Figure 1).…”
Section: Methodsmentioning
confidence: 99%
“…In the second step, mean femur and hemi‐pelvis shapes generated from the SSM with Pose were used as alignment templates to remove individual pose variations of the separate bones (femur and hemi‐pelvis); these shapes were then used to generate the SSM of Shape (Figure 1). 33 Principal component analysis (PCA) was used to reduce the dimensionality of the correspondence model into a smaller number of modes that described dominant shape variations. PCA was applied to the correspondence model of the Unscaled SSM and after each step of the alignment process.…”
Section: Methodsmentioning
confidence: 99%
See 1 more Smart Citation