{
  "id": "1711.05775",
  "version": "v1",
  "published": "2017-11-15T19:52:27.000Z",
  "updated": "2017-11-15T19:52:27.000Z",
  "title": "End-to-end Training for Whole Image Breast Cancer Diagnosis using An All Convolutional Design",
  "authors": [
    "Li Shen"
  ],
  "comment": "Accepted poster at NIPS 2017 Workshop on Machine Learning for Health (https://ml4health.github.io/2017/)",
  "categories": [
    "cs.CV"
  ],
  "abstract": "We develop an end-to-end training algorithm for whole-image breast cancer diagnosis based on mammograms. It requires lesion annotations only at the first stage of training. After that, a whole image classifier can be trained using only image level labels. This greatly reduced the reliance on lesion annotations. Our approach is implemented using an all convolutional design that is simple yet provides superior performance in comparison with the previous methods. On DDSM, our best single-model achieves a per-image AUC score of 0.88 and three-model averaging increases the score to 0.91. On INbreast, our best single-model achieves a per-image AUC score of 0.96. Using DDSM as benchmark, our models compare favorably with the current state-of-the-art. We also demonstrate that a whole image model trained on DDSM can be easily transferred to INbreast without using its lesion annotations and using only a small amount of training data. Code availability: https://github.com/lishen/end2end-all-conv",
  "revisions": [
    {
      "version": "v1",
      "updated": "2017-11-15T19:52:27.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "convolutional design",
      "end-to-end training",
      "per-image auc score",
      "lesion annotations",
      "best single-model achieves"
    ],
    "tags": [
      "github project"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}