. Simultaneous PET/MR scanners combine the high sensitivity of MR imaging with the functional imaging of PET. However, attenuation correction of breast PET/MR imaging is technically challenging. The purpose of this study is to establish a robust attenuation correction algorithm for breast PET/MR images that relies on deep learning (DL) to recreate the missing portions of the patient's anatomy (truncation completion), as well as to provide bone information for attenuation correction from only the PET data.. Data acquired from 23 female subjects with invasive breast cancer scanned withF-fluorodeoxyglucose PET/CT and PET/MR localized to the breast region were used for this study. Three DL models, U-Net with mean absolute error loss (DL) model, U-Net with mean squared error loss (DL) model, and U-Net with perceptual loss (DL) model, were trained to predict synthetic CT images (sCT) for PET attenuation correction (AC) given non-attenuation corrected (NAC) PETimages as inputs. The DL and Dixon-based sCT reconstructed PET images were compared against those reconstructed from CT images by calculating the percent error of the standardized uptake value (SUV) and conducting Wilcoxon signed rank statistical tests.. sCT images from the DLmodel, the DLmodel, and the DLmodel were similar in mean absolute error (MAE), peak-signal-to-noise ratio, and normalized cross-correlation. No significant difference in SUV was found between the PET images reconstructed using the DLand DLsCTs compared to the reference CT for AC in all tissue regions. All DL methods performed better than the Dixon-based method according to SUV analysis.. A 3D U-Net with MSE or perceptual loss model can be implemented into a reconstruction workflow, and the derived sCT images allow successful truncation completion and attenuation correction for breast PET/MR images.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1088/1361-6560/ad2126 | DOI Listing |
Rev Esp Med Nucl Imagen Mol (Engl Ed)
December 2024
Selcuk University Medical Faculty, Department of Nuclear Medicine, Konya, Turkey.
Introduction And Objectives: Tissue attenuation reduces the specificity of the myocardial perfusion imaging single photon emission tomography (SPECT), which leads reduced diagnostic accuracy. The aim of this study is to compare performances of non-attenuation corrected (NAC), computed tomography based-attenuation corrected (AC) and prone images for qualitative and semi-quantitative analysis of myocardial perfusion SPECT in diagnosis of coronary artery disease (CAD).
Materials And Methods: Eightysix patients in whom NAC, AC and prone images were obtained with SPECT at Selcuk University Faculty of Medicine, and whose coronary angiography/CT coronary angiography was completed within 3 months, were retrospectively studied.
Mol Neurobiol
December 2024
Guangxi Key Laboratory of Brain and Cognitive Neuroscience, Faculty of Basic Medical Sciences, Guilin Medical University, Guilin, 541199, Guangxi, China.
The neural mechanisms underlying the natural and maladaptive forgetting of established memory remain largely unknown. Brain disease states might hijack the physiological forgetting mechanisms, resulting in maladaptive forgetting such as accelerated forgetting that contributes to cognitive decline in various neurologic conditions including epilepsy. Based on the key role of the integrated stress response (ISR) in memory storage and maintenance, we determined whether the ISR underpins natural and accelerated forgetting.
View Article and Find Full Text PDFActa Neuropathol Commun
December 2024
Department of Pharmacology & Therapeutics, McGill University, McIntyre Medical Building, 3655 Promenade Sir William Osler Room 1210, Montreal, H3G 1Y6, Canada.
The combination of amyloid beta and tau pathologies leads to tau-mediated neurodegeneration in Alzheimer's disease. However, the relative contributions of amyloid beta and tau peptide accumulation to the manifestation of the pathological phenotype in the early stages, before the overt deposition of plaques and tangles, are still unclear. We investigated the longitudinal pathological effects of combining human-like amyloidosis and tauopathy in a novel transgenic rat model, coded McGill-R-APPxhTau.
View Article and Find Full Text PDFMol Neurobiol
December 2024
Joint Laboratory for Research & Treatment of Spinal Cord Injury in Spinal Deformity, Laboratory for Clinical Medicine, Capital Medical University, Fengtai District, Beijing, 100069, China.
Distraction spinal cord injury (DSCI) is a severe complication following scoliosis correction surgery, for which there are currently no effective clinical treatments. This study aims to evaluate the inhibitory effects of rutin, a natural product, on inflammation in DSCI and to investigate the underlying mechanisms. In vitro, microglial cells were exposed directly to rutin to assess its ability to inhibit lipopolysaccharide (LPS)-induced inflammation.
View Article and Find Full Text PDFNat Hum Behav
December 2024
Department of Computational Biology, University of Lausanne, Lausanne, Switzerland.
Although the use of short self-report measures is common practice in biobank initiatives, such a phenotyping strategy is inherently prone to reporting errors. To explore challenges related to self-report errors, we first derived a reporting error score in the UK Biobank (UKBB; n = 73,127), capturing inconsistent self-reporting in time-invariant phenotypes across multiple measurement occasions. We then performed genome-wide scans on the reporting error score, applied downstream analyses (linkage disequilibrium score regression and Mendelian randomization) and compared its properties to the UKBB participation propensity.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!