Zero-Echo-Time and Dixon Deep Pseudo-CT (ZeDD CT): Direct Generation of Pseudo-CT Images for Pelvic PET/MRI Attenuation Correction Using Deep Convolutional Neural Networks with Multiparametric MRI

• Published in: Journal of Nuclear Medicine Vol. 59; no. 5; pp. 852 - 858
• Main Authors: Leynes, Andrew P, Yang, Jaewon, Wiesinger, Florian, Kaushik, Sandeep S, Shanbhag, Dattesh D, Seo, Youngho, Hope, Thomas A, Larson, Peder E Z
• Format: Journal Article
• Language: English
• Published: United States Society of Nuclear Medicine 01.05.2018
• Subjects: Accuracy; Artificial neural networks; Attenuation; Bone lesions; Bones; Computed tomography; Error analysis; Error correction; Image acquisition; Lesions; Machine learning; Magnetic resonance imaging; Medical imaging; Neural networks; NMR; Nuclear magnetic resonance; Patients; Physics/Instrumentation; Positron emission; Tomography; multiparametric MRI; deep learning; synthetic CT; MRAC; convolutional neural networks

Accurate quantification of uptake on PET images depends on accurate attenuation correction in reconstruction. Current MR-based attenuation correction methods for body PET use a fat and water map derived from a 2-echo Dixon MRI sequence in which bone is neglected. Ultrashort-echo-time or zero-echo-ti...