Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285390149> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4285390149 abstract "Purpose: Image registration is the process of aligning images, and it is a fundamental task in medical image analysis. While many tasks in the field of image analysis, such as image segmentation, are handled almost entirely with deep learning and exceed the accuracy of conventional algorithms, currently available deformable image registration methods are often still conventional. Deep learning methods for medical image registration have recently reached the accuracy of conventional algorithms. However, they are often based on a weakly supervised learning scheme using multilabel image segmentations during training. The creation of such detailed annotations is very time-consuming. Approach: We propose a weakly supervised learning scheme for deformable image registration. By calculating the loss function based on only bounding box labels, we are able to train an image registration network for large displacement deformations without using densely labeled images. We evaluate our model on interpatient three-dimensional abdominal CT and MRI images. Results: The results show an improvement of ∼10% (for CT images) and 20% (for MRI images) in comparison to the unsupervised method. When taking into account the reduced annotation effort, the performance also exceeds the performance of weakly supervised training using detailed image segmentations. Conclusion: We show that the performance of image registration methods can be enhanced with little annotation effort using our proposed method." @default.
- W4285390149 created "2022-07-14" @default.
- W4285390149 creator A5001739049 @default.
- W4285390149 creator A5003572402 @default.
- W4285390149 creator A5061216655 @default.
- W4285390149 creator A5064304390 @default.
- W4285390149 creator A5068574576 @default.
- W4285390149 date "2022-07-14" @default.
- W4285390149 modified "2023-09-28" @default.
- W4285390149 title "Learning-based three-dimensional registration with weak bounding box supervision" @default.
- W4285390149 cites W2107956652 @default.
- W4285390149 cites W2109315631 @default.
- W4285390149 cites W2133287637 @default.
- W4285390149 cites W2142445683 @default.
- W4285390149 cites W2159971808 @default.
- W4285390149 cites W2166737644 @default.
- W4285390149 cites W2396622801 @default.
- W4285390149 cites W2413073178 @default.
- W4285390149 cites W2891590469 @default.
- W4285390149 cites W2898403737 @default.
- W4285390149 cites W2974771924 @default.
- W4285390149 cites W3002569343 @default.
- W4285390149 cites W3012258198 @default.
- W4285390149 cites W3027820480 @default.
- W4285390149 cites W3112701542 @default.
- W4285390149 cites W3199192502 @default.
- W4285390149 doi "https://doi.org/10.1117/1.jmi.9.4.044001" @default.
- W4285390149 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35847178" @default.
- W4285390149 hasPublicationYear "2022" @default.
- W4285390149 type Work @default.
- W4285390149 citedByCount "0" @default.
- W4285390149 crossrefType "journal-article" @default.
- W4285390149 hasAuthorship W4285390149A5001739049 @default.
- W4285390149 hasAuthorship W4285390149A5003572402 @default.
- W4285390149 hasAuthorship W4285390149A5061216655 @default.
- W4285390149 hasAuthorship W4285390149A5064304390 @default.
- W4285390149 hasAuthorship W4285390149A5068574576 @default.
- W4285390149 hasConcept C108583219 @default.
- W4285390149 hasConcept C111919701 @default.
- W4285390149 hasConcept C115961682 @default.
- W4285390149 hasConcept C147037132 @default.
- W4285390149 hasConcept C153180895 @default.
- W4285390149 hasConcept C154945302 @default.
- W4285390149 hasConcept C166704113 @default.
- W4285390149 hasConcept C31601959 @default.
- W4285390149 hasConcept C31972630 @default.
- W4285390149 hasConcept C41008148 @default.
- W4285390149 hasConcept C63584917 @default.
- W4285390149 hasConcept C71924100 @default.
- W4285390149 hasConcept C89600930 @default.
- W4285390149 hasConcept C98045186 @default.
- W4285390149 hasConceptScore W4285390149C108583219 @default.
- W4285390149 hasConceptScore W4285390149C111919701 @default.
- W4285390149 hasConceptScore W4285390149C115961682 @default.
- W4285390149 hasConceptScore W4285390149C147037132 @default.
- W4285390149 hasConceptScore W4285390149C153180895 @default.
- W4285390149 hasConceptScore W4285390149C154945302 @default.
- W4285390149 hasConceptScore W4285390149C166704113 @default.
- W4285390149 hasConceptScore W4285390149C31601959 @default.
- W4285390149 hasConceptScore W4285390149C31972630 @default.
- W4285390149 hasConceptScore W4285390149C41008148 @default.
- W4285390149 hasConceptScore W4285390149C63584917 @default.
- W4285390149 hasConceptScore W4285390149C71924100 @default.
- W4285390149 hasConceptScore W4285390149C89600930 @default.
- W4285390149 hasConceptScore W4285390149C98045186 @default.
- W4285390149 hasIssue "04" @default.
- W4285390149 hasLocation W42853901491 @default.
- W4285390149 hasLocation W42853901492 @default.
- W4285390149 hasOpenAccess W4285390149 @default.
- W4285390149 hasPrimaryLocation W42853901491 @default.
- W4285390149 hasRelatedWork W2082098299 @default.
- W4285390149 hasRelatedWork W2156863789 @default.
- W4285390149 hasRelatedWork W2369744843 @default.
- W4285390149 hasRelatedWork W2392187754 @default.
- W4285390149 hasRelatedWork W3020283531 @default.
- W4285390149 hasRelatedWork W3158600517 @default.
- W4285390149 hasRelatedWork W4224223242 @default.
- W4285390149 hasRelatedWork W4225923497 @default.
- W4285390149 hasRelatedWork W4285390149 @default.
- W4285390149 hasRelatedWork W4292829955 @default.
- W4285390149 hasVolume "9" @default.
- W4285390149 isParatext "false" @default.
- W4285390149 isRetracted "false" @default.
- W4285390149 workType "article" @default.