On the Interpretability of Artificial Intelligence in Radiology: Challenges and Opportunities.

By Mauricio Reyes, Raphael Meier, Sérgio Pereira, Carlos A. Silva, F. Dahlweid, H. von Tengg-Kobligk, Ronald M. Summers, Roland Wiest. Radiology: Artificial Intelligence, 2020

425 citations recorded by the source corpus.

As artificial intelligence (AI) systems begin to make their way into clinical radiology practice, it is crucial to assure that they function correctly and that they gain the trust of experts. Toward this goal, approaches to make AI "interpretable" have gained attention to enhance the understanding of a machine learning algorithm, despite its complexity. This article aims to provide insights into the current state of the art of interpretability methods for radiology AI. This review discusses radiologists' opinions on the topic and suggests trends and challenges that need to be addressed to effectively streamline interpretability methods in clinical practice. Supplemental material is available for this article. © RSNA, 2020 See also the commentary by Gastounioti and Kontos in this issue.

Subfields: Artificial Intelligence, Health Informatics, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/4a8692d75d9bb1bbc2b84cddc52521d6a03461d4

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

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

AI in health and medicine (2022, background): “In addition to building trust among users, enhanced explainability will allow developers to check models more thoroughly for errors and verify to what degree AI decision-making mirrors expert human approaches 102 .”
Assessing the (Un)Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imaging (2020, background): “Although there is no study that corroborates these findings with medical images [49], there are several works that have demonstrated serious issues with many saliency methods.”
Surgical data science – from concepts toward clinical translation (2020, background): “In fact, the complexity of neural network architectures with typically millions of parameters poses a difficulty for humans to understand how these models reach their conclusions (Reyes et al., 2020).”
Transformers in Medical Imaging: A Survey (2022, background): “This black-box nature of ViTs has hindered their deployment in clinical practice since, in areas such as medical applications, it is imperative to identify the limitations and potential failure cases of designed systems, where interpretability plays a fundamental role [393].”
Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities (2021, methodology): “It is one of the most raised challenges in the literature of XAI [1, 31, 10, 32, 9, 41, 33, 26, 43, 42, 2, 34, 8, 44, 35, 36, 37, 18, 45, 38, 39, 40, 46].”
Explainable artificial intelligence (XAI) in deep learning-based medical image analysis (2021, methodology): “LIME uses the simpler model to learn the mapping between the perturbed input data and the change in output.”