FRODO: Free rejection of out-of-distribution samples: application to chest x-ray analysisDownload PDF

Apr 16, 2019 (edited Jun 14, 2019)MIDL 2019 Conference Abstract SubmissionReaders: Everyone
  • Keywords: deep learning, out-of-distribution
  • TL;DR: We have proposed an unsupervised method to find out-of-distribution images in a chest x-ray application and achieved 0.99 AUC.
  • Abstract: In this work, we propose a method to reject out-of-distribution samples which can be adapted to any network architecture and requires no additional training data. Publicly available chest x-ray data (38,353 images) is used to train a standard ResNet-50 model to detect emphysema. Feature activations of intermediate layers are used as descriptors defining the training data distribution. A novel metric, FRODO, is measured by using the Mahalanobis distance of a new test sample to the training data distribution. The method is tested using a held-out test dataset of 21,176 chest x-rays (in-distribution) and a set of 14,821 out-of-distribution x-ray images of incorrect orientation or anatomy. In classifying test samples as in or out-of distribution, our method achieves an AUC score of 0.99.
  • Code Of Conduct: I have read and accept the code of conduct.
  • Remove If Rejected: Remove submission from public view if paper is rejected.
3 Replies