Pneumonia detection based on RSNA dataset and anchor-free deep learning detector.

Pneumonia is a highly lethal disease, and research on its treatment and early screening tools has received extensive attention from researchers. Due to the maturity and cost reduction of chest X-ray technology, and with the development of artificial intelligence technology, pneumonia identification based on deep learning and chest X-ray has attracted attention from all over the world. Although the feature extraction capability of deep learning is strong, existing deep learning object detection frameworks are based on pre-defined anchors, which require a lot of tuning and experience to guarantee their excellent results in the face of new applications or data. To avoid the influence of anchor settings in pneumonia detection, this paper proposes an anchor-free object detection framework and RSNA dataset based on pneumonia detection. First, a data enhancement scheme is used to preprocess the chest X-ray images; second, an anchor-free object detection framework is used for pneumonia detection, which contains a feature pyramid, two-branch detection head, and focal loss. The average precision of 51.5 obtained by Intersection over Union (IoU) calculation shows that the pneumonia detection results obtained in this paper can surpass the existing classical object detection framework, providing an idea for future research and exploration.

Enhanced electrochemical performance of Li2.72Na0.31MnPO4CO3 as a cathode material in "water-in-salt" electrolytes.

A carbonophosphate compound of Li2.72Na0.31MnPO4CO3 was synthesized via ion exchange. The initial discharge capacity of Li2.72Na0.31MnPO4CO3 in 15 molal (or 15 m) LiTFSI was 110 mA h g-1 at 2 mA cm-2 (∼0.5C). Due to the decomposition of Li2.72Na0.31MnPO4CO3, the capacity retention degraded to 64% after 100 cycles.

Cathode Properties of Na3FePO4CO3 Prepared by the Mechanical Ball Milling Method for Na-ion Batteries.

The carbonophosphate Na3FePO4CO3 was synthesized by the mechanical ball milling method for the first time. The composition of the obtained sample with a higher amount of Fe2+ was Na2.66Fe2+0.66Fe3+0.34PO4CO3 as confirmed by Mössbauer analysis, owing to the good airtight properties of this method. The obtained samples in an organic electrolyte delivered an initial discharge capacity of 124 mAh/g at room temperature, and a larger discharge capacity of 159 mAh/g (1.66 Na+/mole) at 60 °C. With 17 m NaClO4 aqueous electrolyte, a discharge capacity of 161 mAh/g (1.69 Na+/mole) was delivered because of the high ionic conductivity of the concentrated aqueous electrolyte. During the charge-discharge process, the formation of Fe4+ after charging up to 4.5 V and the return of Fe2+ after discharging down to 1.5 V were detected by ex-situ X-ray absorption near edge structure (XANES) analysis.