Background: Deep learning has the potential to augment the use of chest radiography in clinical radiology, but challenges include poor generalizability, spectrum bias, and difficulty comparing across studies.Purpose: To develop and evaluate deep learning models for chest radiograph interpretation by using radiologist-adjudicated reference standards.
Materials and Methods:Deep learning models were developed to detect four findings (pneumothorax, opacity, nodule or mass, and fracture) on frontal chest radiographs. This retrospective study used two data sets. Data set 1 (DS1) consisted of 759 611 images from a multicity hospital network and ChestX-ray14 is a publicly available data set with 112 120 images. Natural language processing and expert review of a subset of images provided labels for 657 954 training images. Test sets consisted of 1818 and 1962 images from DS1 and ChestX-ray14, respectively. Reference standards were defined by radiologist-adjudicated image review. Performance was evaluated by area under the receiver operating characteristic curve analysis, sensitivity, specificity, and positive predictive value. Four radiologists reviewed test set images for performance comparison. Inverse probability weighting was applied to DS1 to account for positive radiograph enrichment and estimate population-level performance.
BackgroundAccumulation of aberrant proteins to form Lewy bodies (LBs) is a hallmark of Parkinson's disease (PD). Ubiquitination-mediated degradation of aberrant, misfolded proteins is critical for maintaining normal cell function. Emerging evidence suggests that oxidative/nitrosative stress compromises the precisely-regulated network of ubiquitination in PD, particularly affecting parkin E3 ligase activity, and contributes to the accumulation of toxic proteins and neuronal cell death.ResultsTo gain insight into the mechanism whereby cell stress alters parkin-mediated ubiquitination and LB formation, we investigated the effect of oxidative stress. We found significant increases in oxidation (sulfonation) and subsequent aggregation of parkin in SH-SY5Y cells exposed to the mitochondrial complex I inhibitor 1-methyl-4-phenlypyridinium (MPP+), representing an in vitro cell-based PD model. Exposure of these cells to direct oxidation via pathological doses of H2O2 induced a vicious cycle of increased followed by decreased parkin E3 ligase activity, similar to that previously reported following S-nitrosylation of parkin. Pre-incubation with catalase attenuated H2O2 accumulation, parkin sulfonation, and parkin aggregation. Mass spectrometry (MS) analysis revealed that H2O2 reacted with specific cysteine residues of parkin, resulting in sulfination/sulfonation in regions of the protein similar to those affected by parkin mutations in hereditary forms of PD. Immunohistochemistry or gel electrophoresis revealed an increase in aggregated parkin in rats and primates exposed to mitochondrial complex I inhibitors, as well as in postmortem human brain from patients with PD with LBs.ConclusionThese findings show that oxidative stress alters parkin E3 ligase activity, leading to dysfunction of the ubiquitin-proteasome system and potentially contributing to LB formation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.