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. 3
- Kontaxakis, G. 4
-
1
Universidad Carlos III de Madrid
info
- 2 Instituto de Salud Carlos III, Madrid
-
3
Universidad Complutense de Madrid
info
-
4
Universidad Politécnica de Madrid
info
- Joaquín Roca González (coord.)
- Dolores Ojados González (coord.)
- Juan Suardíaz Muro (coord.)
Editorial: Universidad Politécnica de Cartagena
ISBN: 978-84-17853-76-1
Año de publicación: 2023
Páginas: 31-34
Congreso: Congreso Anual de la Sociedad Española de Ingeniería Biomédica. CASEIB (41. 2023. Cartagena)
Tipo: Aportación congreso
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 ...