Quantitative susceptibility mapping in the brain reflects spatial expression of genes involved in iron homeostasis and myelination.

Quantitative susceptibility mapping (QSM) is an MRI modality used to non-invasively measure iron content in the brain. Iron exhibits a specific anatomically varying pattern of accumulation in the brain across individuals. The highest regions of accumulation are the deep grey nuclei, where iron is stored in paramagnetic molecule ferritin. This form of iron is considered to be what largely contributes to the signal measured by QSM in the deep grey nuclei. It is also known that QSM is affected by diamagnetic myelin contents. Here, we investigate spatial gene expression of iron and myelin related genes, as measured by the Allen Human Brain Atlas, in relation to QSM images of age-matched subjects. We performed multiple linear regressions between gene expression and the average QSM signal within 34 distinct deep grey nuclei regions. Our results show a positive correlation (p < .05, corrected) between expression of ferritin and the QSM signal in deep grey nuclei regions. We repeated the analysis for other genes that encode proteins thought to be involved in the transport and storage of iron in the brain, as well as myelination. In addition to ferritin, our findings demonstrate a positive correlation (p < .05, corrected) between the expression of ferroportin, transferrin, divalent metal transporter 1, several gene markers of myelinating oligodendrocytes, and the QSM signal in deep grey nuclei regions. Our results suggest that the QSM signal reflects both the storage and active transport of iron in the deep grey nuclei regions of the brain.

A deep-learning pipeline for the diagnosis and discrimination of viral, non-viral and COVID-19 pneumonia from chest X-ray images.

Common lung diseases are first diagnosed using chest X-rays. Here, we show that a fully automated deep-learning pipeline for the standardization of chest X-ray images, for the visualization of lesions and for disease diagnosis can identify viral pneumonia caused by coronavirus disease 2019 (COVID-19) and assess its severity, and can also discriminate between viral pneumonia caused by COVID-19 and other types of pneumonia. The deep-learning system was developed using a heterogeneous multicentre dataset of 145,202 images, and tested retrospectively and prospectively with thousands of additional images across four patient cohorts and multiple countries. The system generalized across settings, discriminating between viral pneumonia, other types of pneumonia and the absence of disease with areas under the receiver operating characteristic curve (AUCs) of 0.94-0.98; between severe and non-severe COVID-19 with an AUC of 0.87; and between COVID-19 pneumonia and other viral or non-viral pneumonia with AUCs of 0.87-0.97. In an independent set of 440 chest X-rays, the system performed comparably to senior radiologists and improved the performance of junior radiologists. Automated deep-learning systems for the assessment of pneumonia could facilitate early intervention and provide support for clinical decision-making.