# EigenRank by Committee: A Data Subset Selection and Failure Prediction paradigm for Robust Deep Learning based Medical Image Segmentation

## TL;DR

EigenRank is a novel algorithm that improves medical image segmentation by selecting optimal training data subsets and predicting segmentation failures, enhancing robustness and clinical applicability of deep learning models.

## Contribution

The paper introduces EigenRank, a new method leveraging Von Neumann information for data subset selection and failure prediction in deep learning-based medical image segmentation.

## Key findings

- EigenRank outperforms random subset selection in segmentation accuracy.
- EigenRank effectively predicts cases likely to fail segmentation.
- The method enhances robustness and reliability of medical image segmentation models.

## 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.