Initial Experience With Low-Dose 18F-Fluorodeoxyglucose Positron Emission Tomography/Magnetic Resonance Imaging With Deep Learning Enhancement.
Initial Experience With Low-Dose 18F-Fluorodeoxyglucose Positron Emission Tomography/Magnetic Resonance Imaging With Deep Learning Enhancement.
复制标题
DOI:
10.1097/rct.0000000000001174
复制
发表时间:
2021-07-01
影响因子:
1.3
通讯作者:
McMillan AB
中科院分区:
文献类型:
--
作者:
Park CJ;Chen W;Pirasteh A;Kim DH;Perlman SB;Robbins JB;McMillan AB
To demonstrate the utility of deep-learning-enhancement (DLE) to achieve diagnostic quality low-dose PET/MR. Twenty subjects with known Crohn disease underwent simultaneous PET/MR imaging after intravenous administration of approximately 185 MBq of 18F-fluorodeoxyglucose (FDG). Five image sets were generated: (1) standard-of-care (reference), (2) low-dose (i.e. using 20% of PET counts), (3) DLE-enhanced low-dose using PET data as input, (4) DLE-enhanced low-dose using PET and MR data as input, and (5) DLE-enhanced using no PET counts. Image sets were evaluated by both quantitative metrics and qualitatively by expert readers. Although low-dose images (series 2) and images with no PET data input (series 5) were non-diagnostic, DLE enhancement of the low-dose images (series 3 and 4) achieved diagnostic quality images that scored more favorable than the reference (series 1), both qualitatively and quantitatively. DLE enhancement has the potential to enable a 90% reduction of radiotracer while achieving diagnostic quality images.