Segmentation-Free Estimation of Aortic Diameters from MRI Using Deep Learning

Accurate and reproducible measurements of the aortic diameters are crucial for the diagnosis of cardiovascular diseases and for therapeutic decision making. Currently, these measurements are manually performed by healthcare professionals, being time consuming, highly variable, and suffering from lac...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Aguerreberry, Axel, de la Rosa, Ezequiel, Lalande, Alain, Fernández, Elmer Andrés
Formato: Artículo
Lenguaje:Español
Publicado: 2020
Materias:
R Medicina (General)
Acceso en línea:http://pa.bibdigital.ucc.edu.ar/3330/1/DC_Agueberry_de%20la%20Rosa_Lalande.pdf
Aporte de:
Producción Académica Universidad Católica de Córdoba (UCCor) de Universidad Católica de Córdoba
id I38-R144-3330
record_format dspace
spelling I38-R144-33302025-09-18T13:56:18Z http://pa.bibdigital.ucc.edu.ar/3330/ Segmentation-Free Estimation of Aortic Diameters from MRI Using Deep Learning Aguerreberry, Axel de la Rosa, Ezequiel Lalande, Alain Fernández, Elmer Andrés R Medicina (General) Accurate and reproducible measurements of the aortic diameters are crucial for the diagnosis of cardiovascular diseases and for therapeutic decision making. Currently, these measurements are manually performed by healthcare professionals, being time consuming, highly variable, and suffering from lack of reproducibility. In this work we propose a supervised deep-learning method for the direct estimation of aortic diameters. The approach is devised and tested over 100 magnetic resonance angiography scans without contrast agent. All data was expert-annotated at six aortic locations typically used in clinical practice. Our approach makes use of a 3D+2D convolutional neural network (CNN) that takes as input a 3D scan and outputs the aortic diameter at a given location. In a 5-fold cross-validation comparison against a fully 3D CNN and against a 3D multiresolution CNN, our approach was consistently superior in predicting the aortic diameters. Overall, the 3D+2D CNN achieved a mean absolute error between 2.2–2.4 mm depending on the considered aortic location. These errors are less than 1 mm higher than the inter-observer variability. Thus, suggesting that our method makes predictions almost reaching the expert’s performance. We conclude that the work allows to further explore automatic algorithms for direct estimation of anatomical structures without the necessity of a segmentation step. It also opens possibilities for the automation of cardiovascular measurements in clinical settings. 2020-10-04 info:eu-repo/semantics/article info:eu-repo/semantics/closedAccess application/pdf spa http://pa.bibdigital.ucc.edu.ar/3330/1/DC_Agueberry_de%20la%20Rosa_Lalande.pdf Aguerreberry, Axel, de la Rosa, Ezequiel, Lalande, Alain and Fernández, Elmer Andrés ORCID: https://orcid.org/0000-0002-4711-8634 <https://orcid.org/0000-0002-4711-8634> (2020) Segmentation-Free Estimation of Aortic Diameters from MRI Using Deep Learning. In: 11th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2020 held in Conjunction with MICCAI 2020, Lima, Perú. https://link.springer.com/chapter/10.1007/978-3-030-68107-4_17 info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-030-68107-4_17
institution Universidad Católica de Córdoba
institution_str I-38
repository_str R-144
collection Producción Académica Universidad Católica de Córdoba (UCCor)
language Español
orig_language_str_mv spa
topic R Medicina (General)
spellingShingle R Medicina (General)
Aguerreberry, Axel
de la Rosa, Ezequiel
Lalande, Alain
Fernández, Elmer Andrés
Segmentation-Free Estimation of Aortic Diameters from MRI Using Deep Learning
topic_facet R Medicina (General)
description Accurate and reproducible measurements of the aortic diameters are crucial for the diagnosis of cardiovascular diseases and for therapeutic decision making. Currently, these measurements are manually performed by healthcare professionals, being time consuming, highly variable, and suffering from lack of reproducibility. In this work we propose a supervised deep-learning method for the direct estimation of aortic diameters. The approach is devised and tested over 100 magnetic resonance angiography scans without contrast agent. All data was expert-annotated at six aortic locations typically used in clinical practice. Our approach makes use of a 3D+2D convolutional neural network (CNN) that takes as input a 3D scan and outputs the aortic diameter at a given location. In a 5-fold cross-validation comparison against a fully 3D CNN and against a 3D multiresolution CNN, our approach was consistently superior in predicting the aortic diameters. Overall, the 3D+2D CNN achieved a mean absolute error between 2.2–2.4 mm depending on the considered aortic location. These errors are less than 1 mm higher than the inter-observer variability. Thus, suggesting that our method makes predictions almost reaching the expert’s performance. We conclude that the work allows to further explore automatic algorithms for direct estimation of anatomical structures without the necessity of a segmentation step. It also opens possibilities for the automation of cardiovascular measurements in clinical settings.
format Artículo
author Aguerreberry, Axel
de la Rosa, Ezequiel
Lalande, Alain
Fernández, Elmer Andrés
author_facet Aguerreberry, Axel
de la Rosa, Ezequiel
Lalande, Alain
Fernández, Elmer Andrés
author_sort Aguerreberry, Axel
title Segmentation-Free Estimation of Aortic Diameters from MRI Using Deep Learning
title_short Segmentation-Free Estimation of Aortic Diameters from MRI Using Deep Learning
title_full Segmentation-Free Estimation of Aortic Diameters from MRI Using Deep Learning
title_fullStr Segmentation-Free Estimation of Aortic Diameters from MRI Using Deep Learning
title_full_unstemmed Segmentation-Free Estimation of Aortic Diameters from MRI Using Deep Learning
title_sort segmentation-free estimation of aortic diameters from mri using deep learning
publishDate 2020
url http://pa.bibdigital.ucc.edu.ar/3330/1/DC_Agueberry_de%20la%20Rosa_Lalande.pdf
work_keys_str_mv AT aguerreberryaxel segmentationfreeestimationofaorticdiametersfrommriusingdeeplearning
AT delarosaezequiel segmentationfreeestimationofaorticdiametersfrommriusingdeeplearning
AT lalandealain segmentationfreeestimationofaorticdiametersfrommriusingdeeplearning
AT fernandezelmerandres segmentationfreeestimationofaorticdiametersfrommriusingdeeplearning
_version_ 1846022699535564800

Ejemplares similares