Deep Learning methodologies for direct image reconstruction and integrated attenuation correction in brain PET/MRI

• Díaz Serrano, P. ^[1] ; Ortuño Fisac, J. E. ^[2] ; López Santiago, J ^[1] ; Panetsos Petrova, F. ^[4] ; Kontaxakis, G. ^[3]
  1. [1] Universidad Carlos III de Madrid

     Universidad Carlos III de Madrid

     Madrid, España

     
  2. [2] Instituto de Salud Carlos III

     Instituto de Salud Carlos III

     Madrid, España

     
  3. [3] Universidad Politécnica de Madrid

     Universidad Politécnica de Madrid

     Madrid, España

     
  4. [4] Universidad Complutense , Madrid

  Mostrar afiliaciones +
• 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. 31-34
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • This study proposes the ATTDeepPET model, a novel deep learning architecture crafted specifically for advancing positron emission tomography (PET) image reconstruction in PET/MR scanners. By incorporating magnetic resonance (MR) images into its learning process, ATTDeepPET addresses the persistent challenges associated with attenuation effects in PET/MR scanners, eliminating the need for simulated transmission scans. ATTDeepPET's performance is assessed alongside the deep learning model DeepPET, as well as established methods such as FBP, ML-EM, and ML-EMR for comparison. The findings reveal noteworthy achievements since ATTDeepPET accomplishes competitive image quality compared to FBP, MLEM, and ML-EMR when applied to brain phantoms while also demonstrating a reduction in reconstruction times. Nevertheless, when dealing with real PET images, ATTDeepPET does exhibit some performance variability, underscoring the increased complexity of real-set scenarios and the importance of employing ...