VesselGPT: autoregressive modeling of vascular geometry

Autores
Feldman, Paula Adi; Sinnona, Martín; Delrieux, Claudio Augusto; Siless, Viviana; Iarusi, Emmanuel
Año de publicación
2025
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Anatomical trees are critical for clinical diagnosis and treatment planning, yet their complex and diverse geometry make accurate representation a significant challenge. Motivated by the latest advances in large language models, we introduce an autoregressive method for synthesizing anatomical trees. Our approach first embeds vessel structures into a learned discrete vocabulary using a VQ-VAE architecture, then models their generation autoregressively with a GPT-2 model. This method effectively captures intricate geometries and branching patterns, enabling realistic vascular tree synthesis. Comprehensive qualitative and quantitative evaluations reveal that our technique achieves high-fidelity tree reconstruction with compact discrete representations. Moreover, our B-spline representation of vessel cross-sections preserves critical morphological details that are often overlooked in previous’ methods parameterizations. To the best of our knowledge, this work is the first to generate blood vessels in an autoregressive manner.
Fil: Feldman, Paula Adi. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Sinnona, Martín. Universidad Torcuato Di Tella; Argentina
Fil: Delrieux, Claudio Augusto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Ciencias e Ingeniería de la Computación. Universidad Nacional del Sur. Departamento de Ciencias e Ingeniería de la Computación. Instituto de Ciencias e Ingeniería de la Computación; Argentina. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina
Fil: Siless, Viviana. Universidad Torcuato Di Tella; Argentina
Fil: Iarusi, Emmanuel. Universidad Torcuato Di Tella; Argentina
Materia
Vascular 3D model
Generative modeling
Neural Networks
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/290137
Acceder
id CONICETDig_dc391a2c52eeb836a4bfb8e7101ae29b
oai_identifier_str oai:ri.conicet.gov.ar:11336/290137
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling VesselGPT: autoregressive modeling of vascular geometryFeldman, Paula AdiSinnona, MartínDelrieux, Claudio AugustoSiless, VivianaIarusi, EmmanuelVascular 3D modelGenerative modelingNeural Networkshttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1Anatomical trees are critical for clinical diagnosis and treatment planning, yet their complex and diverse geometry make accurate representation a significant challenge. Motivated by the latest advances in large language models, we introduce an autoregressive method for synthesizing anatomical trees. Our approach first embeds vessel structures into a learned discrete vocabulary using a VQ-VAE architecture, then models their generation autoregressively with a GPT-2 model. This method effectively captures intricate geometries and branching patterns, enabling realistic vascular tree synthesis. Comprehensive qualitative and quantitative evaluations reveal that our technique achieves high-fidelity tree reconstruction with compact discrete representations. Moreover, our B-spline representation of vessel cross-sections preserves critical morphological details that are often overlooked in previous’ methods parameterizations. To the best of our knowledge, this work is the first to generate blood vessels in an autoregressive manner.Fil: Feldman, Paula Adi. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFil: Sinnona, Martín. Universidad Torcuato Di Tella; ArgentinaFil: Delrieux, Claudio Augusto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Ciencias e Ingeniería de la Computación. Universidad Nacional del Sur. Departamento de Ciencias e Ingeniería de la Computación. Instituto de Ciencias e Ingeniería de la Computación; Argentina. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; ArgentinaFil: Siless, Viviana. Universidad Torcuato Di Tella; ArgentinaFil: Iarusi, Emmanuel. Universidad Torcuato Di Tella; ArgentinaSpringer2025-09info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/290137Feldman, Paula Adi; Sinnona, Martín; Delrieux, Claudio Augusto; Siless, Viviana; Iarusi, Emmanuel; VesselGPT: autoregressive modeling of vascular geometry; Springer; Lecture Notes in Computer Science; 1597; 9-2025; 662-6720302-9743CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://link.springer.com/10.1007/978-3-032-05325-1_63info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-032-05325-1_63info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2026-08-25T15:36:14Zoai:ri.conicet.gov.ar:11336/290137instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982026-08-25 15:36:14.984CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv VesselGPT: autoregressive modeling of vascular geometry
title VesselGPT: autoregressive modeling of vascular geometry
spellingShingle VesselGPT: autoregressive modeling of vascular geometry
Feldman, Paula Adi
Vascular 3D model
Generative modeling
Neural Networks
title_short VesselGPT: autoregressive modeling of vascular geometry
title_full VesselGPT: autoregressive modeling of vascular geometry
title_fullStr VesselGPT: autoregressive modeling of vascular geometry
title_full_unstemmed VesselGPT: autoregressive modeling of vascular geometry
title_sort VesselGPT: autoregressive modeling of vascular geometry
dc.creator.none.fl_str_mv Feldman, Paula Adi
Sinnona, Martín
Delrieux, Claudio Augusto
Siless, Viviana
Iarusi, Emmanuel
author Feldman, Paula Adi
author_facet Feldman, Paula Adi
Sinnona, Martín
Delrieux, Claudio Augusto
Siless, Viviana
Iarusi, Emmanuel
author_role author
author2 Sinnona, Martín
Delrieux, Claudio Augusto
Siless, Viviana
Iarusi, Emmanuel
author2_role author
author
author
author
dc.subject.none.fl_str_mv Vascular 3D model
Generative modeling
Neural Networks
topic Vascular 3D model
Generative modeling
Neural Networks
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv Anatomical trees are critical for clinical diagnosis and treatment planning, yet their complex and diverse geometry make accurate representation a significant challenge. Motivated by the latest advances in large language models, we introduce an autoregressive method for synthesizing anatomical trees. Our approach first embeds vessel structures into a learned discrete vocabulary using a VQ-VAE architecture, then models their generation autoregressively with a GPT-2 model. This method effectively captures intricate geometries and branching patterns, enabling realistic vascular tree synthesis. Comprehensive qualitative and quantitative evaluations reveal that our technique achieves high-fidelity tree reconstruction with compact discrete representations. Moreover, our B-spline representation of vessel cross-sections preserves critical morphological details that are often overlooked in previous’ methods parameterizations. To the best of our knowledge, this work is the first to generate blood vessels in an autoregressive manner.
Fil: Feldman, Paula Adi. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Sinnona, Martín. Universidad Torcuato Di Tella; Argentina
Fil: Delrieux, Claudio Augusto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Ciencias e Ingeniería de la Computación. Universidad Nacional del Sur. Departamento de Ciencias e Ingeniería de la Computación. Instituto de Ciencias e Ingeniería de la Computación; Argentina. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina
Fil: Siless, Viviana. Universidad Torcuato Di Tella; Argentina
Fil: Iarusi, Emmanuel. Universidad Torcuato Di Tella; Argentina
description Anatomical trees are critical for clinical diagnosis and treatment planning, yet their complex and diverse geometry make accurate representation a significant challenge. Motivated by the latest advances in large language models, we introduce an autoregressive method for synthesizing anatomical trees. Our approach first embeds vessel structures into a learned discrete vocabulary using a VQ-VAE architecture, then models their generation autoregressively with a GPT-2 model. This method effectively captures intricate geometries and branching patterns, enabling realistic vascular tree synthesis. Comprehensive qualitative and quantitative evaluations reveal that our technique achieves high-fidelity tree reconstruction with compact discrete representations. Moreover, our B-spline representation of vessel cross-sections preserves critical morphological details that are often overlooked in previous’ methods parameterizations. To the best of our knowledge, this work is the first to generate blood vessels in an autoregressive manner.
publishDate 2025
dc.date.none.fl_str_mv 2025-09
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/290137
Feldman, Paula Adi; Sinnona, Martín; Delrieux, Claudio Augusto; Siless, Viviana; Iarusi, Emmanuel; VesselGPT: autoregressive modeling of vascular geometry; Springer; Lecture Notes in Computer Science; 1597; 9-2025; 662-672
0302-9743
CONICET Digital
CONICET
url http://hdl.handle.net/11336/290137
identifier_str_mv Feldman, Paula Adi; Sinnona, Martín; Delrieux, Claudio Augusto; Siless, Viviana; Iarusi, Emmanuel; VesselGPT: autoregressive modeling of vascular geometry; Springer; Lecture Notes in Computer Science; 1597; 9-2025; 662-672
0302-9743
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://link.springer.com/10.1007/978-3-032-05325-1_63
info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-032-05325-1_63
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1874775542972022784
score 13.265058

Publicaciones similares