Deep learning for classification and localization of COVID-19 markers in point-of-care lung ultrasound

In this paper, we proposed a novel technique in order to detect the COVID-19 markers. Here, we are consider the dataset of lung ultrasonography (LUS) videos. Next the videos are converted into frame format. Spatial transform network is used for the score prediction. Some Deep Learning (DL) methods have been illustrated to reach this goal, including ground truth labeling, semantic segmentation. 

Use labeled ground truth as training data for machine learning and deep learning models, such as object detectors or semantic segmentation networks. To automate the labeling of ground truth data, you can use a built-in automation algorithm or develop your own algorithm.

 A semantic segmentation network classifies every pixel in an image, resulting in an image that is segmented by class. The proposed method results gives better classification results when compared with existing approaches.

Keywords: Lung Ultrasonography (LUS), Deep Learning (DL), Frame format.