{
  "fetched_at": "2026-10-25T04:35:10Z",
  "source_url": "https://www.kaggle.com/competitions/congenital-heart-disease/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Images of each type of congenital heart disease are classified in different folders, and the folder names are the types of heart disease.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "The data sets provided in this competition are divided into four types: normal group, atrial septal defect group (ASD), ventricular septal defect group (VSD), and patent ductus arteriosus (PDA) group.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "This competition uses ROC as the evaluation indicator.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": " - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "The purpose of this competition is to develop a more detailed medical image classification model. Because the diagnosis of congenital heart disease mainly relies on cardiac ultrasound examination, the accuracy of cardiac ultrasound is related to the level of ultrasound doctors. In underdeveloped regions, children with congenital heart disease often miss diagnosis. In the diagnosis guide, chest x-ray has a supporting role in diagnosis. We plan to use CXR to assist in the screening of congenital heart disease in underdeveloped regions, but this requires deep learning models to better pay attention to the details around the heart, and it is best to enhance doctors' confidence in the model through attention heat maps.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}