RESUMEN
Proton magnetic resonance spectroscopy (1H-MRS) delivers information about the non-invasive metabolic landscape of brain pathologies. 1H-MRS is used in clinical setting in addition to MRI for diagnostic, prognostic and treatment response assessments, but the use of this radiological tool is not entirely widespread. The importance of developing automated analysis tools for 1H-MRS lies in the possibility of a straightforward application and simplified interpretation of metabolic and genetic data that allow for incorporation into the daily practice of a broad audience. Here, we report a prospective clinical imaging trial (DRKS00019855) which aimed to develop a novel MR-spectroscopy-based algorithm for in-depth characterization of brain lesions and prediction of molecular traits. Dimensional reduction of metabolic profiles demonstrated distinct patterns throughout pathologies. We combined a deep autoencoder and multi-layer linear discriminant models for voxel-wise prediction of the molecular profile based on MRS imaging. Molecular subtypes were predicted by an overall accuracy of 91.2% using a classifier score. Our study indicates a first step into combining the metabolic and molecular traits of lesions for advancing the pre-operative diagnostic workup of brain tumors and improve personalized tumor treatment.
RESUMEN
BACKGROUND: Chronic Obstructive Pulmonary Disease (COPD) is characterised by complex inflammatory, neuronal and fibrotic changes. Brain-derived Neurotrophic Factor (BDNF) is a key regulator of neuronal plasticity, whereas Transforming Growth Factor-ß1 (TGF-ß1) plays a crucial role in tissue repair and emphysema pathogenesis. Both mediators are stored in platelets and released from platelets in inflammatory conditions and during serum preparation. In patients with asthma, it was previously shown that elevated serum BDNF concentrations correlate with disease severity, whereas TGF-ß1 concentrations were normal. METHODS: In the present study, 63 patients with stable COPD (spirometric GOLD stages 2-4) and 17 age- and comorbidity-matched controls were studied. Lung function, smoking history, medication, platelet concentrations in peripheral blood and serum concentrations of BDNF, TGF-ß1 and Serotonin (5-HT) were assessed in all participants. RESULTS: Serum levels of both BDNF and TGF-ß1 (but not concentrations of platelets in peripheral blood) were significantly elevated in all stages of COPD as compared to controls. Highest BDNF concentrations were found in spirometric GOLD stage 3, whereas highest TGF-ß1 serum levels were found in spirometric GOLD stage 4. There were specific, stage-dependent correlations of these mediators with lung function parameters of the patients. CONCLUSIONS: Taken together, we show that, in contrast to asthma, COPD is characterised by elevated concentrations of both BDNF and TGF-ß1 in serum. The stage-dependent association with lung function supports the hypothesis that these platelet mediators may play a role in the pathogenesis of COPD.
