A bipartite graph approach to retrieve similar 3D models with different resolution and types of cardiomyopathies

Página do item simplificado
dc.contributor.authorLeila Bergamasco
dc.contributor.authorLIMA, K.R.P.S.
dc.contributor.authorROCHITTE, C. E.
dc.contributor.authorNUNES, F. L. S.
dc.contributor.authorOrcidhttps://orcid.org/0000-0002-8001-8053
dc.date.accessioned2022-03-01T06:04:53Z
dc.date.available2022-03-01T06:04:53Z
dc.date.issued2022-05-01
dc.description.abstractThree-dimensional (3D) model retrieval uses content-based image retrieval (CBIR) techniques to search for the most similar 3D objects in a dataset, usually considering their geometry and organization in a feature vector. Feature vectors from different objects were compared to establish their similarities. Although this type of comparison typically uses metric distances, such metrics present limitations when the vector lengths are different. Signal-based descriptors are a promising approach for extracting features from 3D objects, but they generate feature vectors with different lengths. Thus, new methods for measuring the similarity are required. This study proposes an approach to 3D model retrieval as a network flow problem using bipartite graphs. The approach was applied to support the diagnosis of cardiomyopathies, considering 3D objects reconstructed from cardiac images of the left ventricle. We achieved an AUC value of 0.93 under the best retrieval scenario. The results also indicate that modeling a 3D model retrieval technique as a network flow problem using graphs can provide a promising manner to compare 3D objects with different shapes and sizes. This strategy, coupled with personal patient data, achieves better results than methods using classical comparison approaches.
dc.description.volume193
dc.identifier.doi10.1016/j.eswa.2021.116422
dc.identifier.issn0957-4174
dc.identifier.urihttps://repositorio.fei.edu.br/handle/FEI/4419
dc.relation.ispartofExpert Systems with Applications
dc.rightsAcesso Restrito
dc.subject.otherlanguage3D model retrieval
dc.subject.otherlanguageCardiomyopathies
dc.subject.otherlanguageComputer-aided diagnosis
dc.subject.otherlanguageNetwork flows
dc.subject.otherlanguageSimilarity comparison methods
dc.subject.otherlanguageSPHARM
dc.titleA bipartite graph approach to retrieve similar 3D models with different resolution and types of cardiomyopathies
dc.typeArtigo
fei.scopus.citations1
fei.scopus.eid2-s2.0-85122709210
fei.scopus.subject3D model retrieval
fei.scopus.subject3D object
fei.scopus.subjectBipartite graphs
fei.scopus.subjectCardiomyopathy
fei.scopus.subjectComparison methods
fei.scopus.subjectFeatures vector
fei.scopus.subjectNetwork flow problems
fei.scopus.subjectNetworks flows
fei.scopus.subjectSimilarity comparison method
fei.scopus.subjectSPHARM
fei.scopus.updated2024-05-01
fei.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85122709210&origin=inward
Arquivos
Coleções
Artigos