Combining Sparse and Dense Features to Improve Multi-Modal Registration for Brain DTI Images

• Published in: Entropy (Basel, Switzerland) Vol. 22; no. 11; p. 1299
• Main Authors: Moldovanu, Simona, Toporaș, Lenuta Pană, Biswas, Anjan, Moraru, Luminita
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 14.11.2020; MDPI
• Subjects: Accuracy; Algorithms; Anisotropy; Brain; Computing costs; Datasets; Entropy; Error analysis; Feature extraction; fiducial registration error; histogram-oriented gradients; Histograms; Image acquisition; Image registration; Linear transformations; Magnetic resonance imaging; Medical diagnosis; Medical imaging; mutual information; Operators (mathematics); Optimization; Pixels; Registration; Robustness (mathematics); sparse and dense features; Stroke; Target recognition; Tensors; mutual information; histogram-oriented gradients; sparse and dense features; image registration; fiducial registration error

A new solution to overcome the constraints of multimodality medical intra-subject image registration is proposed, using the mutual information (MI) of image histogram-oriented gradients as a new matching criterion. We present a rigid, multi-modal image registration algorithm based on linear transfor...