Computer Vision News - June 2022

50 Medical Imaging AI tool Hello again! In this article we are going to have another medical imaging tutorial creating a COVID predictor using chest X-rays! This month we will look at how Artificial Intelligence applied to the medical domain can have very significant impact. Since COVID-19 attacks the epithelial cells that line our respiratory tract, we can use X-rays to analyze the health of a patient’s lungs. X-ray is a very common modality in most hospitals over the world. Developing a semi-automated analysis system can save medical professionals valuable time and the lives of many patients. Let’s start by importing important metadata and modules. #Create the data for positive samples IMAGE_PATH = "/content/drive/My Drive/images" df = pd.read_csv('metadata.csv') print(df.shape) (372, 29) df.head() patientid offset ... other_notes Unnamed: 28 0 2 0.0 ... NaN NaN 1 2 3.0 ... NaN NaN [5 rows x 29 columns] Load Datasets Here I will load saved XRAY datasets where the training will happen: TARGET_DIR = "/content/drive/My Drive/Dataset/Train/Covid" if not os.path.exists(TARGET_DIR): os.mkdir(TARGET_DIR) #Copy COVID-19 images with view point PA from Downloaded directory to Target Directory cnt = 0 for(i,row) in df.iterrows(): if row["finding"] == "COVID-19" and row["view"] =="PA": Vision Transformers in Medical Computer Vision