Deep Learning-Based Generation of Synthetic CT from MR Images for Craniosynostosis Planning

• Santos Mayo, C. ^[1] ; Cubero, L. ^[1] ; Aguado del Hoyo, A. ^[2] ; Ochandiano, S. ^[2] ; Pascau, J. ^[1]
  1. [1] Universidad Carlos III de Madrid

     Universidad Carlos III de Madrid

     Madrid, España

     
  2. [2] Hospital General Universitario Gregorio Marañón

     Hospital General Universitario Gregorio Marañón

     Madrid, España

     
• Localización: CASEIB 2023. Libro de Actas del XLI Congreso Anual de la Sociedad Española de Ingeniería Biomédica: Contribuyendo a la salud basada en valor / coord. por Joaquín Roca González, Dolores Ojados González, Juan Suardíaz Muro, 2023, ISBN 978-84-17853-76-1, págs. 39-42
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • Craniosynostosis is a rare congenital defect caused by the premature fusion of one or more cranial sutures. This untimely cranial ossification hinders correct brain development. Its clinical diagnosis and treatment planning usually rely on Computed Tomography (CT), a potentially harmful imaging technique for young infants. It is with the intent of avoiding the use of ionizing radiation in this clinical pipeline that this work studies how feasible it is to resort to alternative non-detrimental imaging techniques such as Magnetic Resonance Imaging (MRI). We evaluate the performance of neural network generators trained on Generative Adversarial Networks in the MRI-to-CT translation task. We train nine generative models on 25 paired MR-CT medical scans, and validate and test their performance on 8 and 4 paired images, respectively. The results are promising both from qualitative and quantitative standpoints, particularly those of the models trained directly on 3D data. Results demonstrate ...