Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210363730> ?p ?o ?g. }
- W4210363730 endingPage "2441" @default.
- W4210363730 startingPage "2427" @default.
- W4210363730 abstract "The traditional learning-based non-rigid registration methods for medical images are trained by an invariant smoothness regularization parameter, which cannot satisfy the registration accuracy and diffeomorphic property simultaneously. The diffeomorphic property reflects the credibility of the registration results.To improve the diffeomorphic property in 3D medical image registration, we propose a diffeomorphic cascaded network based on the compressed loss (CL), named LDVoxelMorph. The proposed network has several constituent U-Nets and is trained with deep supervision, which uses a different spatial smoothness regularization parameter in each constituent U-Nets for training. This cascade-variant smoothness regularization parameter can maintain the diffeomorphic property in top cascades with large displacement and achieve precise registration in bottom cascades. Besides, we develop the CL as a penalty for the velocity field, which can accurately limit the velocity field that causes the deformation field overlap after the velocity field integration.In our registration experiments, the dice scores of our method were 0.892 ± 0.040 on liver CT datasets SLIVER37 , 0.848 ± 0.044 on liver CT datasets LiTS38 , 0.689 ± 0.014 on brain MRI datasets LPBA38 , and the number of overlapping voxels of deformation field were 325, 159, and 0, respectively. Ablation study shows that the CL improves the diffeomorphic property more effectively than increases.Experiment results show that our method can achieve higher registration accuracy assessed by dice scores and overlapping voxels while maintaining the diffeomorphic property for large deformation." @default.
- W4210363730 created "2022-02-08" @default.
- W4210363730 creator A5024861014 @default.
- W4210363730 creator A5025710876 @default.
- W4210363730 creator A5033107823 @default.
- W4210363730 creator A5044668212 @default.
- W4210363730 creator A5051012442 @default.
- W4210363730 creator A5061444433 @default.
- W4210363730 creator A5086083381 @default.
- W4210363730 date "2022-02-17" @default.
- W4210363730 modified "2023-10-15" @default.
- W4210363730 title "LDVoxelMorph: A precise loss function and cascaded architecture for unsupervised diffeomorphic large displacement registration" @default.
- W4210363730 cites W1901129140 @default.
- W4210363730 cites W1903029394 @default.
- W4210363730 cites W1970928383 @default.
- W4210363730 cites W1987583435 @default.
- W4210363730 cites W2007153649 @default.
- W4210363730 cites W2049981393 @default.
- W4210363730 cites W2065646479 @default.
- W4210363730 cites W2071989139 @default.
- W4210363730 cites W2083099567 @default.
- W4210363730 cites W2110952843 @default.
- W4210363730 cites W2115167851 @default.
- W4210363730 cites W2118104180 @default.
- W4210363730 cites W2118961645 @default.
- W4210363730 cites W2119848633 @default.
- W4210363730 cites W2134236847 @default.
- W4210363730 cites W2153431772 @default.
- W4210363730 cites W2155298532 @default.
- W4210363730 cites W2170167891 @default.
- W4210363730 cites W2171490473 @default.
- W4210363730 cites W2284266414 @default.
- W4210363730 cites W2592929672 @default.
- W4210363730 cites W2883028377 @default.
- W4210363730 cites W2950568021 @default.
- W4210363730 cites W2959226257 @default.
- W4210363730 cites W2966108228 @default.
- W4210363730 cites W2996290406 @default.
- W4210363730 cites W3035201239 @default.
- W4210363730 cites W3098269293 @default.
- W4210363730 cites W3104164805 @default.
- W4210363730 cites W3164933060 @default.
- W4210363730 doi "https://doi.org/10.1002/mp.15515" @default.
- W4210363730 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35106787" @default.
- W4210363730 hasPublicationYear "2022" @default.
- W4210363730 type Work @default.
- W4210363730 citedByCount "1" @default.
- W4210363730 countsByYear W42103637302023 @default.
- W4210363730 crossrefType "journal-article" @default.
- W4210363730 hasAuthorship W4210363730A5024861014 @default.
- W4210363730 hasAuthorship W4210363730A5025710876 @default.
- W4210363730 hasAuthorship W4210363730A5033107823 @default.
- W4210363730 hasAuthorship W4210363730A5044668212 @default.
- W4210363730 hasAuthorship W4210363730A5051012442 @default.
- W4210363730 hasAuthorship W4210363730A5061444433 @default.
- W4210363730 hasAuthorship W4210363730A5086083381 @default.
- W4210363730 hasConcept C102634674 @default.
- W4210363730 hasConcept C11413529 @default.
- W4210363730 hasConcept C115961682 @default.
- W4210363730 hasConcept C134306372 @default.
- W4210363730 hasConcept C153180895 @default.
- W4210363730 hasConcept C154945302 @default.
- W4210363730 hasConcept C166704113 @default.
- W4210363730 hasConcept C2776135515 @default.
- W4210363730 hasConcept C31972630 @default.
- W4210363730 hasConcept C33923547 @default.
- W4210363730 hasConcept C41008148 @default.
- W4210363730 hasConcept C47556283 @default.
- W4210363730 hasConcept C54170458 @default.
- W4210363730 hasConceptScore W4210363730C102634674 @default.
- W4210363730 hasConceptScore W4210363730C11413529 @default.
- W4210363730 hasConceptScore W4210363730C115961682 @default.
- W4210363730 hasConceptScore W4210363730C134306372 @default.
- W4210363730 hasConceptScore W4210363730C153180895 @default.
- W4210363730 hasConceptScore W4210363730C154945302 @default.
- W4210363730 hasConceptScore W4210363730C166704113 @default.
- W4210363730 hasConceptScore W4210363730C2776135515 @default.
- W4210363730 hasConceptScore W4210363730C31972630 @default.
- W4210363730 hasConceptScore W4210363730C33923547 @default.
- W4210363730 hasConceptScore W4210363730C41008148 @default.
- W4210363730 hasConceptScore W4210363730C47556283 @default.
- W4210363730 hasConceptScore W4210363730C54170458 @default.
- W4210363730 hasFunder F4320321001 @default.
- W4210363730 hasIssue "4" @default.
- W4210363730 hasLocation W42103637301 @default.
- W4210363730 hasLocation W42103637302 @default.
- W4210363730 hasOpenAccess W4210363730 @default.
- W4210363730 hasPrimaryLocation W42103637301 @default.
- W4210363730 hasRelatedWork W2009466720 @default.
- W4210363730 hasRelatedWork W2011443206 @default.
- W4210363730 hasRelatedWork W2041698670 @default.
- W4210363730 hasRelatedWork W2114100766 @default.
- W4210363730 hasRelatedWork W2125070361 @default.
- W4210363730 hasRelatedWork W2160739731 @default.
- W4210363730 hasRelatedWork W2203553948 @default.
- W4210363730 hasRelatedWork W2685530223 @default.
- W4210363730 hasRelatedWork W3163375306 @default.
- W4210363730 hasRelatedWork W2494681155 @default.