EigenRank by Committee: A Data Subset Selection and Failure Prediction paradigm for Robust Deep Learning based Medical Image Segmentation
arXiv:1908.06337 · doi:10.1016/j.media.2020.101834
Abstract
Translation of fully automated deep learning based medical image segmentation technologies to clinical workflows face two main algorithmic challenges. The first, is the collection and archival of large quantities of manually annotated ground truth data for both training and validation. The second is the relative inability of the majority of deep learning based segmentation techniques to alert physicians to a likely segmentation failure. Here we propose a novel algorithm, named `Eigenrank' which addresses both of these challenges. Eigenrank can select for manual labeling, a subset of medical images from a large database, such that a U-Net trained on this subset is superior to one trained on a randomly selected subset of the same size. Eigenrank can also be used to pick out, cases in a large database, where deep learning segmentation will fail. We present our algorithm, followed by results and a discussion of how Eigenrank exploits the Von Neumann information to perform both data subset selection and failure prediction for medical image segmentation using deep learning.
References in corpus (14)
- TensorFlow: A system for large-scale machine learning
- Explaining and Harnessing Adversarial Examples
- Road Extraction by Deep Residual U-Net
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
- Domain-adversarial neural networks to address the appearance variability of histopathology images
- Learning Confidence for Out-of-Distribution Detection in Neural Networks
- Stability
- Leveraging Uncertainty Estimates for Predicting Segmentation Quality
- apricot: Submodular selection for data summarization in Python
- Almost-everywhere algorithmic stability and generalization error
- Deep Active Learning for Axon-Myelin Segmentation on Histology Data
- Annotation-cost Minimization for Medical Image Segmentation using Suggestive Mixed Supervision Fully Convolutional Networks
- A Strategy of MR Brain Tissue Images' Suggestive Annotation Based on Modified U-Net
- Extreme Augmentation : Can deep learning based medical image segmentation be trained using a single manually delineated scan?