Medical imaging uses images of internal tissues of the human body or a part of the human body in a non-invasive manner for clinical diagnoses or treatment plans36. Medical images (e.g., X-data and CT-data) are usually acquired using computed radiography and are typically stored in the Digital Imaging and Communications in Medicine (DICOM) format37. X-data are two-dimensional grayscale images, and CT-data are three-dimensional data, consisting of slices of the data in the z axis direction of a two-dimensional grayscale image. Machine learning methods are playing increasingly important roles in medical image analysis, especially DL methods. DL uses multiple non-linear transformations to create a mapping relationship between the input data and output labels38. The objective of this study was to annotate lesion areas in medical images with high accuracy. Therefore, we developed a pseudo-coloring method, which is a technique that helps enhance medical images for physicians to isolate relevant tissues and groups different tissues together39. We converted the original grayscale images to color images using the open-source image processing tools Open Source Computer Vision Library (OpenCV) and Pillow. Examples of the pseudo-color images are shown in Fig. 1a. We developed a platform that uses a client-server architecture to annotate the potential lesion areas of COVID-19 on the CXR and CT images. The platform can be deployed on a private cloud for security and local sharing. All the images were annotated by two experienced radiologists (one was a 5th-year radiologist and the other was a 3rd-year radiologist) in the Youan Hospital. If there was disagreement about a result, a senior radiologist and a respiratory doctor made the final decision to ensure the precision of the annotation process. The details of the annotation pipeline are shown in Supplementary Fig. 1.
Fig. 1 Demonstrations of data preprocessing methods including pseudo-coloring and dimension normalization.
a Pseudo-coloring for abnormal examples in the CXR and CT images. The original grayscale images were transformed into color images using the pseudo-coloring method and were annotated by the experts. The scale bar on the right is the range of pixel values of the image data. b Dimension normalization to reduce the dimensions in the CT images. The number of CT images were first resampled to a multiple of three and then divided into three groups. Followed by the 1 × 1 convolution layers to reduce the dimensions of the data.