Improving RGB-D Point Cloud Registration by Learning Multi-scale Local Linear Transformation

Wang, Ziming; Xiaoliang, Huo,; Chen, Zhenghao; Zhang, Jing; Sheng, Lu; Xu, Dong

doi:10.1007/978-3-031-19824-3_11

Cited by 8 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Linear Registration) allows adjustment of maximum of 12 parameters (i.e. rotation, translation, scaling, and shearing on x, y, and z coordinate axes) during transformation [16,17,18,19]. In addition to the choice of image registration algorithm, it is also important to choose the type of atlas to use.…”

Section: Figure 1: the Four Main Lobar Sections Of Human Brainmentioning

confidence: 99%

“…One, we used linear registration for aligning the images. Linear registration is known to underperform in comparison with non-linear registration because linear registration is restricted to a maximum of 12 affine transformation [62,17,18,19]. We could not use Non-linear registration because of lack of computational resources (i.e.…”

Section: Atlases Selection Using Atrophy Measurementioning

confidence: 99%

See 1 more Smart Citation

Parcellation of Brain Magnetic Resonance Images using Improved Atlases Selection Model

Owate,

Aribisala,

Uwadia

et al. 2023

JRRS

View full text Add to dashboard Cite

Introduction: Multiple atlas-based parcellation model has been demonstrated to perform better than single atlas-based parcellation model in terms of accuracy of the parcellation of human brain Magnetic Resonance Images (MRI). The weakness of the existing multiple atlas-based parcellation models is that the level of accuracy is limited if used for the ageing brain due to the presence of age-related changes such as atrophy. Aim: The aim of this study is to develop a novel multiple atlases selection model that ensures improved accuracy for the parcellation of the ageing brain by combining Cost function with the Similarity metric and Atrophy measure for atlases selection. This model is called COSA. Materials and Methods: A dataset with ten brain MRIs and ten atlases was used. A brain MRI was used one at a time as the target image while the remaining images constituted the source images. Using each target image, consensus atlases were obtained for COSA from the combination of a cost function, similarity index, and atrophy measure. These atlases were consequently used to parcellate the target image. Performance was assessed using Dice Coefficient and COSA was compared with existing atlases selection models. The existing atlases selection models investigated were Normalized Mutual Information (NMI), Mutual Information (MI), Correlation Ratio (CR), Normalized Correlation Ratio (NCR), and Least Square Error (LSE). Results: Mean of Dice Coefficient were: COSA = 0.7495196, NMI = 0.7479508, MI = 0.7473333, Jaccard Index = 0.7392522, CR = 0.7358384, NC = 0.7358043, Atrophy Measure = 0.7300867, LSE = 0.7299367, Single Atlas =0.6830223. Conclusion: Results show that COSA performs better than the existing multiple Atlas-based models.

show abstract

Section: Figure 1: the Four Main Lobar Sections Of Human Brainmentioning

confidence: 99%