Deep learning-based attenuation map generation for myocardial perfusion SPECT

• Published in: European journal of nuclear medicine and molecular imaging Vol. 47; no. 10; pp. 2383 - 2395
• Main Authors: Shi, Luyao, Onofrey, John A., Liu, Hui, Liu, Yi-Hwa, Liu, Chi
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.09.2020; Springer Nature B.V
• Subjects: Artificial neural networks; Attenuation; Cardiology; Computed tomography; Deep Learning; Emission analysis; Humans; Image Processing, Computer-Assisted; Image reconstruction; Imaging; Machine learning; Medical imaging; Medicine; Medicine & Public Health; Myocardium; Neural networks; Nuclear Medicine; Oncology; Original Article; Orthopedics; Perfusion; Photon emission; Photopeak; Radiation dosage; Radiology; Scanners; Scanning; Single photon emission computed tomography; Tomography; Tomography, Emission-Computed, Single-Photon; Tomography, X-Ray Computed; Training; Ventricle; Deep learning; Myocardial perfusion imaging; SPECT; Synthetic attenuation map

Purpose Attenuation correction using CT transmission scanning increases the accuracy of single-photon emission computed tomography (SPECT) and enables quantitative analysis. Current existing SPECT-only systems normally do not support transmission scanning and therefore scans on these systems are sus...