RESUMO
Dynamic 2-[18F] fluoro-2-deoxy-D-glucose positron emission tomography (dFDG-PET) for human brain imaging has considerable clinical potential, yet its utilization remains limited. A key challenge in the quantitative analysis of dFDG-PET is characterizing a patient-specific blood input function, traditionally reliant on invasive arterial blood sampling. This research introduces a novel approach employing non-invasive deep learning model-based computations from the internal carotid arteries (ICA) with partial volume (PV) corrections, thereby eliminating the need for invasive arterial sampling. We present an end-to-end pipeline incorporating a 3D U-Net based ICA-net for ICA segmentation, alongside a Recurrent Neural Network (RNN) based MCIF-net for the derivation of a model-corrected blood input function (MCIF) with PV corrections. The developed 3D U-Net and RNN was trained and validated using a 5-fold cross-validation approach on 50 human brain FDG PET datasets. The ICA-net achieved an average Dice score of 82.18% and an Intersection over Union of 68.54% across all tested scans. Furthermore, the MCIF-net exhibited a minimal root mean squared error of 0.0052. The application of this pipeline to ground truth data for dFDG-PET brain scans resulted in the precise localization of seizure onset regions, which contributed to a successful clinical outcome, with the patient achieving a seizure-free state after treatment. These results underscore the efficacy of the ICA-net and MCIF-net deep learning pipeline in learning the ICA structure's distribution and automating MCIF computation with PV corrections. This advancement marks a significant leap in non-invasive neuroimaging.
RESUMO
BACKGROUND: The use of expanded criteria donor kidneys (ECD) had been associated with worse outcomes. Whole gene expression of pre-implantation allograft biopsies from deceased donor kidneys (DDKs) was evaluated to compare the effect of pulsatile pump preservation (PPP) vs. cold storage preservation (CSP) on standard and ECD kidneys. METHODOLOGY/PRINCIPAL FINDINGS: 99 pre-implantation DDK biopsies were studied using gene expression with GeneChips. Kidneys transplant recipients were followed post transplantation for 35.8 months (rangeâ=â24-62). The PPP group included 60 biopsies (cold ischemia time (CIT)â=â1,367+/-509 minutes) and the CSP group included 39 biopsies (CITâ=â1,022+/-485 minutes) (P<0.001). Donor age (42.0±14.6 vs. 34.1±14.2 years, Pâ=â0.009) and the percentage of ECD kidneys (PPPâ=â35% vs. CSPâ=â12.8%, Pâ=â0.012) were significantly different between groups. A two-sample t-test was performed, and probe sets having a P<0.001 were considered significant. Probe set level linear models were fit using cold ischemia time and CSP/PPP as independent variables to determine significant probe sets (P<0.001) between groups after adjusting for cold ischemia time. Thus, 43 significant genes were identified (P<0.001). Over-expression of genes associated with inflammation (CD86, CD209, CLEC4, EGFR2, TFF3, among others) was observed in the CSP group. Cell-to-cell signaling and interaction, and antigen presentation were the most important pathways with genes significantly over-expressed in CSP kidneys. When the analysis was restricted to ECD kidneys, genes involved in inflammation were also differentially up-regulated in ECD kidneys undergoing CSP. However, graft survival at the end of the study was similar between groups (Pâ=â0.2). Moreover, the incidence of delayed graft function was not significant between groups. CONCLUSIONS/SIGNIFICANCE: Inflammation was the most important up-regulated pattern associated with pre-implantation biopsies undergoing CSP even when the PPP group has a larger number of ECD kidneys. No significant difference was observed in delayed graft function incidence and graft function post-transplantation. These findings support the use of PPP in ECD donor kidneys.