{
  "fetched_at": "2026-10-19T08:55:53Z",
  "source_url": "https://www.kaggle.com/competitions/breast-cancer-us-classification-ml-4-im-2025-2026/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The training set contains two folders, corresponding to the \"benign\" and \"malignant\" classes of interest. This folder separation provides information regarding the label of each study (which is also the target of our predictions).\n\nEach breast ultrasound study is referred to with a numerical *Id* (e.g. \"benign (25)\") and has a corresponding lesion segmentation (e.g. \"benign (25)_mask\"). Each study has at least one corresponding segmentation file, containing the mask of a lesion.\nHowever, there are studies with more than one segmented lesion, and each segmentation mask is reported in a different file (e.g. \"benign (25)_mask\" and \"benign (25)_mask_1\"). In these cases, all the lesions belonging to the same study share the same class (e.g. both lesions of study \"benign (25)\" are benign). \nStudies and masks are provided in *png* format.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "This academic competition has the aim to support students through the *Machine Learning for Imaging Data* course at the University School for Advanced Studies IUSS Pavia.\n\nThe target of the copmetition is to implement a model able to automatically discriminate *malignant* from *benign* lesions in breast ultrasound (US) studies.\n\nThe dataset and rules of submission are briefly described in the corresponding sections of this hosting page.\nHere is a handy link to Kaggle's [competition documentation](https://www.kaggle.com/docs/competitions), which includes, among other things, instructions on [submitting predictions](https://www.kaggle.com/docs/competitions#making-a-submission).\n\nGood luck and have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "User submissions are evaluated by comparing their Submission CSV to the ground truth Solution CSV with respect to the <a href=\"https://it.wikipedia.org/wiki/Area_Under_the_Curve\" target=\"blank\">Area Under the ROC Curve</a> (AUC) metric.\n<br><br>\nThe Submission CSV file must contain a prediction score or probability for each classified study, corresponding to the probability of that lesion(s) to belong to class \"Malignant\" or \"Benign\".\n<br><br>\nIt is expected that the probability to belong to class \"Benign\" ranges from 0 to 0.5, and that the probability to belong to class \"Malignant\" ranges from 0.5 to 1 (p &lt; 0.5 -&gt; \"Benign\", p &gt; 0.5 -&gt; \"Malignant\").",
      "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
    }
  ]
}