Image optimization for low-dose <sup>18</sup>F-FDG breast PET/MRI using deep learning: a pilot study.
Authors
Affiliations (8)
Affiliations (8)
- Department of Radiology, University of Wisconsin School of Medicine and Public Health, 600 Highland Avenue, Madison, WI, 53792, USA.
- GE HealthCare, Chicago, IL, USA.
- Department of Medical Physics, University of Wisconsin School of Medicine and Public Health, 1111 Highland Avenue, Madison, WI, 53705, USA.
- University of Wisconsin Carbone Cancer Center, 600 Highland Avenue, Madison, WI, 53792, USA.
- Department of Biostatistics and Medical Informatics, University of Wisconsin School of Medicine and Public Health, 610 Walnut Street, Madison, WI, 53726, USA.
- Department of Radiology, University of Wisconsin School of Medicine and Public Health, 600 Highland Avenue, Madison, WI, 53792, USA. [email protected].
- Department of Medical Physics, University of Wisconsin School of Medicine and Public Health, 1111 Highland Avenue, Madison, WI, 53705, USA. [email protected].
- University of Wisconsin Carbone Cancer Center, 600 Highland Avenue, Madison, WI, 53792, USA. [email protected].
Abstract
Positron emission tomography with magnetic resonance imaging (PET/MRI) provides noninvasive molecular characterization of breast cancer and has the potential to improve diagnostic accuracy, staging, treatment response assessment, and guide personalized care. Reducing the radiation dose from 2-deoxy-2-[<sup>18</sup>F]fluoro-D-glucose (<sup>18</sup>F-FDG) to a level similar to digital mammography while maintaining image quality may facilitate clinical utilization. This study was performed to evaluate diagnostic image quality and lesion conspicuity of low-dose <sup>18</sup>F-FDG breast PET/MRI using denoising and to evaluate the effect of denoising on radiotracer uptake semi-quantification. This pilot study was a secondary analysis of a single-institution prospective study of <sup>18</sup>F-FDG breast PET/MRI for 23 women with primary invasive breast cancer. Random undersampling of the PET data from a 30-min simultaneous prone <sup>18</sup>F-FDG breast PET/MRI was used to produce simulated low-dose (SLD) images approximating 90% reduced injected activity (37 MBq). A deep learning-based, denoising (DN) algorithm was then applied. SLD and DN datasets were evaluated by three readers for image quality and lesion conspicuity and were compared to full-dose images to assess clinical acceptability. Image noise was quantified by liver SUV<sub>standard deviation</sub>. <sup>18</sup>F-FDG uptake (SUV<sub>max</sub> and SUV<sub>mean</sub>) was measured in tumor and normal breast tissue and compared between datasets. Wilcoxon signed rank test, repeated measures analysis of variance, and Bland-Altman analyses were performed. Compared to SLD, DN datasets scored better for artifacts, perceived signal-to-noise ratio, image sharpness/resolution, and overall image quality (p < 0.001). Compared to full-dose images, DN scored better than SLD for diagnostic image quality (p < 0.001) and lesion conspicuity (p = 0.002). For diagnostic image quality, DN was equivalent or slightly inferior to full-dose images in 89.9% (62/69) of reads. Readers preferred DN (76.8%; 53/69) to SLD (4.3%; 3/69), and both were preferred equally in 10.1% (7/69) of reads. Compared to SLD, quantitative image noise was less in DN images (p < 0.0001). Agreement was excellent between all datasets for tumor SUV<sub>max</sub> and SUV<sub>mean</sub>. Acceptable image quality may be achieved with low-dose <sup>18</sup>F-FDG breast PET/MRI using denoising, which warrants further prospective validation.