Semantic similarity metrics for image registration

Czolbe, Steffen; Pegios, Paraskevas; Krause, Oswin; Feragen, Aasa

doi:10.1016/j.media.2023.102830

Cited by 12 publications

(2 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the effectiveness of the registration procedure for creating a distorted image of the original, it is rotated and translated as illustrated in Figure 3. Figure 3 Figure 3(d) and Figure 3(e) show the outcomes of a multimodal brain image registration [23], where image -1(magenta) is an MRI scanned image and image 2(green) is a CT scanned image.…”

Section: Resultsmentioning

confidence: 99%

An improvised coral reef optimization-based image registration using modified mutual information method

Samantaray

Panigrahi

Patra

2023

IJEECS

View full text Add to dashboard Cite

Computer visualisation and medical applications require image registration. It includes transforming collective picture data into the familiar coordinate scheme. Metaheuristic-based methods were developed to explain the issue and improve the efficiency and accuracy of conventional image registration techniques due to their limitations. We describe a hybrid medical image registration technique using bio-inspired meta-heuristic algorithms: Betteroffspring and multi-crossover strategies increase convergent time and solution quality with an improvised coral reef optimization with modified mutual information (ICOR-MMI) algorithm. This new optimization method (ICORMMI) proposes that coral reefs expand, compete for space, and reproduce. A linear weighted sum of image intensity and contour flow model intensity is added to the mutual information calculation. Including statistical and spatial image data improves image registration. The established technique has been tested and verified using multiple medical image data sets, some of which contain single-modality and mixed-modality images (CT, MRI). The registration validates the proposed model's accuracy and efficiency and shows posture's contribution by incorporating statistical and geographical image data. This strategy is adapted to the real-coding problem and tested for realtime issues. The ICOR-MMI algorithm-based hybrid approach outperforms current results in time efficiency and toughness.

show abstract

Section: Resultsmentioning

confidence: 99%

An improvised coral reef optimization-based image registration using modified mutual information method

Samantaray

Panigrahi

Patra

2023

IJEECS

View full text Add to dashboard Cite

show abstract

“…Most limits of classical registration are re-introduced. These issues are also present when the dissimilarity loss is learnt as in [2]. Most deep registration methods also use, as input tensor, the moving and fixed image concatenated in different channels.…”

Section: Introductionmentioning

confidence: 99%