Causality matters in medical imaging.

Journal: Nature communications
Published Date:

Abstract

Causal reasoning can shed new light on the major challenges in machine learning for medical imaging: scarcity of high-quality annotated data and mismatch between the development dataset and the target environment. A causal perspective on these issues allows decisions about data collection, annotation, preprocessing, and learning strategies to be made and scrutinized more transparently, while providing a detailed categorisation of potential biases and mitigation techniques. Along with worked clinical examples, we highlight the importance of establishing the causal relationship between images and their annotations, and offer step-by-step recommendations for future studies.

Authors

  • Daniel C Castro
  • Ian Walker
    2 Department of Computer and Electrical Engineering, Clemson University, Clemson, SC, USA.
  • Ben Glocker
    Kheiron Medical Technologies, London, UK.