Your browser doesn't support javascript.
loading
Improving Vessel Segmentation with Multi-Task Learning and Auxiliary Data Available Only During Model Training.
Sobotka, Daniel; Herold, Alexander; Perkonigg, Matthias; Beer, Lucian; Bastati, Nina; Sablatnig, Alina; Ba-Ssalamah, Ahmed; Langs, Georg.
Afiliación
  • Sobotka D; Computational Imaging Research Lab, Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria.
  • Herold A; Division of General and Paediatric Radiology, Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria.
  • Perkonigg M; Computational Imaging Research Lab, Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria; Department of Medical Statistics, Informatics and Health Economics, Medical University of Innsbruck, Innsbruck, Austria.
  • Beer L; Division of General and Paediatric Radiology, Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria.
  • Bastati N; Division of General and Paediatric Radiology, Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria.
  • Sablatnig A; Computational Imaging Research Lab, Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria.
  • Ba-Ssalamah A; Division of General and Paediatric Radiology, Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria.
  • Langs G; Computational Imaging Research Lab, Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria. Electronic address: georg.langs@meduniwien.ac.at.
Comput Med Imaging Graph ; 114: 102369, 2024 06.
Article en En | MEDLINE | ID: mdl-38518411
ABSTRACT
Liver vessel segmentation in magnetic resonance imaging data is important for the computational analysis of vascular remodeling, associated with a wide spectrum of diffuse liver diseases. Existing approaches rely on contrast enhanced imaging data, but the necessary dedicated imaging sequences are not uniformly acquired. Images without contrast enhancement are acquired more frequently, but vessel segmentation is challenging, and requires large-scale annotated data. We propose a multi-task learning framework to segment vessels in liver MRI without contrast. It exploits auxiliary contrast enhanced MRI data available only during training to reduce the need for annotated training examples. Our approach draws on paired native and contrast enhanced data with and without vessel annotations for model training. Results show that auxiliary data improves the accuracy of vessel segmentation, even if they are not available during inference. The advantage is most pronounced if only few annotations are available for training, since the feature representation benefits from the shared task structure. A validation of this approach to augment a model for brain tumor segmentation confirms its benefits across different domains. An auxiliary informative imaging modality can augment expert annotations even if it is only available during training.
Asunto(s)
Palabras clave

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Neoplasias Encefálicas / Redes Neurales de la Computación Límite: Humans Idioma: En Revista: Comput Med Imaging Graph Asunto de la revista: DIAGNOSTICO POR IMAGEM Año: 2024 Tipo del documento: Article País de afiliación: Austria Pais de publicación: Estados Unidos

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Neoplasias Encefálicas / Redes Neurales de la Computación Límite: Humans Idioma: En Revista: Comput Med Imaging Graph Asunto de la revista: DIAGNOSTICO POR IMAGEM Año: 2024 Tipo del documento: Article País de afiliación: Austria Pais de publicación: Estados Unidos