TY - GEN
T1 - Landmark Anything
T2 - 26th International Conference of the Catalan Association for Artificial Intelligence, CCIA 2024
AU - Heredia-Lidón, Álvaro
AU - García-Mascarell, Christian
AU - Echeverry-Quiceno, Luis Miguel
AU - Herrera-Escartín, Daniel
AU - Fortea, Juan
AU - Pomarol-Clotet, Edith
AU - Fatjó-Vilas, Mar
AU - Martínez-Abadías, Neus
AU - Sevillano, Xavier
N1 - Publisher Copyright:
© 2024 The Authors.
PY - 2024/9/25
Y1 - 2024/9/25
N2 - 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.
AB - 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.
KW - Automatic 3D landmarking
KW - biomarkers
KW - face
KW - hippocampus
KW - multi-view convolutional networks
KW - upper respiratory airways
UR - https://www.scopus.com/pages/publications/85217070536
UR - http://hdl.handle.net/20.500.14342/5501
U2 - 10.3233/FAIA240438
DO - 10.3233/FAIA240438
M3 - Conference contribution
AN - SCOPUS:85217070536
T3 - Frontiers in Artificial Intelligence and Applications
SP - 209
EP - 212
BT - Artificial Intelligence Research and Development - Proceedings of the 26th International Conference of the Catalan Association for Artificial Intelligence
A2 - Alsinet, Teresa
A2 - Vilasis--Cardona, Xavier
A2 - Garcia-Costa, Daniel
A2 - Alvarez-Garcia, Elena
PB - IOS Press BV
Y2 - 2 October 2024 through 4 October 2024
ER -