2026-04-17T07:46:25Zhttps://recercat.cat/oai/request

oai:recercat.cat:2445/2194422025-12-05T09:43:11Zcom_2072_1057col_2072_478778col_2072_478917

00925njm 22002777a 4500 dc Heredia Lidón, Álvaro author García Mascarel, Christian author Echeverry, Luis Miguel author Herrera Escartín, Daniel author Fortea Ormaechea, Juan author Pomarol-Clotet, Edith author Fatjó-Vilas Mestre, Mar author Martínez Abadías, Neus, 1978- author Sevillano, Xavier author 2025-03-04T15:23:11Z 2025-03-04T15:23:11Z 2024 As shape alterations in three-dimensional biological structures are as- sociated 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. Intel·ligència artificial Marcadors bioquímics Artificial intelligence Biochemical markers Landmark anything: multi-view consensus convolutional networks applied to the 3D landmarking of Anatomical Structures