캐글 SIIM-FISABIO-RSNA COVID-19 Detection - Study image의 특징

• Studies either contain a single image (the majority) or multiple images (up to 9)
• All of the images within the studies are also found in the image level dataset
• If a study contains multiple images, a maximum of one image and a minimum of zero images will have bounding boxes even though all of the images exist in the image level dataset.
• There are 2 typical scenarios that occur when multiple images are in a study:
  1. The images are nearly identical (relatively common - differences are blurriness/sharpness/lighting/rotation)(see the example(s) a & c below)
  2. The images are different from each other (relatively uncommon)(see the example b below)
• The images often have something wrong with them. This defect usually falls into one of the following categories
  • poor quality, blurry, too-sharp, perspective transform, cropped poorly, exposure/brightness, skew, etc.