Causality matters in medical imaging

By Daniel Coelho de Castro, Ian Walker, Ben Glocker. Nature Communications, 2019

462 citations recorded by the source corpus.

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. Scarcity of high-quality annotated data and mismatch between the development dataset and the target environment are two of the main challenges in developing predictive tools from medical imaging. In this Perspective, the authors show how causal reasoning can shed new light on these challenges.

Subfields: Artificial Intelligence, Health Informatics

View Paper: https://www.semanticscholar.org/paper/425b4de3e54b8a80147c12f2a4a8fe3f88c2a5b6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Health Informatics

Citations in the corpus

In Search of Lost Domain Generalization (2020, result): “As another example, systems trained on medical data collected in one hospital do not generalize to other health centers [Castro et al., 2019, AlBadawy et al., 2018, Perone et al., 2019, Heaven, 2020].”
Surgical data science – from concepts toward clinical translation (2020, background): “This situation poses a challenge particularly for healthcare applications, as real-world test data, after the model is deployed for clinical use, will typically not have ground-truth annotation, making its assessment difficult (Castro et al., 2020).”
Algorithm fairness in artificial intelligence for medicine and healthcare (2023, methodology): “116,129.”
Explainable, trustworthy, and ethical machine learning for healthcare: A survey (2021, background): “Moreover, Castro et al. emphasized the need of causal relationship between images and their annotations [27].”
Harnessing multimodal data integration to advance precision oncology (2021, background): “Truly causal models are a frontier of AI research, and in the future such models will be highly valuable in this field 141 .”
Deep Learning for Medical Anomaly Detection – A Survey (2020, background): “is often confused with association [125], [126], [127].”
D’ya Like DAGs? A Survey on Structure Learning and Causal Discovery (2021, background): “It is important for a broad range of applications, including policy making [136], medical imaging [30], advertisement [22], the development of medical treatments [191], the evaluation of evidence within legal frameworks [184, 223], social science [81, 94, 254], biology [242], and many others.”
Multimodal data fusion for cancer biomarker discovery with deep learning (2023, background): “But, owing to ethical restrictions and the labour intensity to annotate clinical images, most studies have only limited access to large cohorts that contain ground-truth-labelled data 27 .”
Explainable artificial intelligence (XAI) in deep learning-based medical image analysis (2021, background): “Castro et al. (2020) describe how causal reasoning may be useful to assess such as biases in the data. van Amsterdam et al. (2019) show an example of eliminating bias using causality, yielding unbiased prediction of prognosis for patients with lung cancer.”