{
  "id": "2210.09909",
  "version": "v1",
  "published": "2022-10-18T14:49:44.000Z",
  "updated": "2022-10-18T14:49:44.000Z",
  "title": "Uncertainty estimation for out-of-distribution detection in computational histopathology",
  "authors": [
    "Lea Goetz"
  ],
  "comment": "8 pages, 3 figures",
  "categories": [
    "cs.CV",
    "cs.LG"
  ],
  "abstract": "In computational histopathology algorithms now outperform humans on a range of tasks, but to date none are employed for automated diagnoses in the clinic. Before algorithms can be involved in such high-stakes decisions they need to \"know when they don't know\", i.e., they need to estimate their predictive uncertainty. This allows them to defer potentially erroneous predictions to a human pathologist, thus increasing their safety. Here, we evaluate the predictive performance and calibration of several uncertainty estimation methods on clinical histopathology data. We show that a distance-aware uncertainty estimation method outperforms commonly used approaches, such as Monte Carlo dropout and deep ensembles. However, we observe a drop in predictive performance and calibration on novel samples across all uncertainty estimation methods tested. We also investigate the use of uncertainty thresholding to reject out-of-distribution samples for selective prediction. We demonstrate the limitations of this approach and suggest areas for future research.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-10-18T14:49:44.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "out-of-distribution detection",
      "distance-aware uncertainty estimation method outperforms",
      "predictive performance",
      "computational histopathology algorithms",
      "monte carlo dropout"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 8,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}