Landmark anything: Multi-view consensus convolutional networks applied to the 3D landmarking of anatomical structures

As shape alterations in three-dimensional biological structures are associated to numerous pathological processes, quantitative shape analysis for obtaining phenotypic biomarkers of diagnostic potential has become a prominent research area. In this context, the automatic detection of landmarks on 3D...

Descripción completa

Detalles Bibliográficos
Autores: Heredia Lidón, Álvaro, García-Mascarell, Christian, Echeverry Quiceno, Luis Miguel, Herrera Escartín, Daniel, Fortea, Juan, Pomarol-Clotet, Edith, Fatjó-Vilas, Mar, Martínez-Abadías, Neus, Sevillano, Xavier
Tipo de recurso: artículo
Fecha de publicación:2024
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:20.500.14342/5501
Acceso en línea:http://hdl.handle.net/20.500.14342/5501
https://doi.org/:10.3233/FAIA240438
Access Level:acceso abierto
Palabra clave:Automatic 3D landmarking
Multi-view convolutional networks
Face
Upper respiratory airways
Hippocampus
Biomakers
004
61
62
Descripción
Sumario:As shape alterations in three-dimensional biological structures are associated to numerous pathological processes, quantitative shape analysis for obtaining phenotypic biomarkers of diagnostic potential has become a prominent research area. In this context, the automatic detection of landmarks on 3D anatomical structures is crucial for developing high-throughput phenotyping tools. This study evaluates the performance of multi-view consensus convolutional networks – originally developed for facial landmarking– in automatically detecting landmarks on three different 3D anatomical structures: the face, the upper respiratory airways and the brain hippocampi. Leveraging magnetic resonance imaging datasets, we trained multiple models and assessed their accuracy against manual annotations, while analyzing the impact of different network hyperparameters on the results.