Detecting Spurious Correlations With Sanity Tests for Artificial Intelligence Guided Radiology Systems

• Published in: Frontiers in digital health Vol. 3; p. 671015
• Main Authors: Mahmood, Usman, Shrestha, Robik, Bates, David D B, Mannelli, Lorenzo, Corrias, Giuseppe, Erdi, Yusuf Emre, Kanan, Christopher
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Media S.A 03.08.2021
• Subjects: artificial intelligence; bias; computed tomography; deep learning; Digital Health; spurious correlations; validation; computed tomography; deep learning; spurious correlations; artificial intelligence; validation; bias
• ISSN: 2673-253X; 2673-253X
• DOI: 10.3389/fdgth.2021.671015

Artificial intelligence (AI) has been successful at solving numerous problems in machine perception. In radiology, AI systems are rapidly evolving and show progress in guiding treatment decisions, diagnosing, localizing disease on medical images, and improving radiologists' efficiency. A critical component to deploying AI in radiology is to gain confidence in a developed system's efficacy and safety. The current gold standard approach is to conduct an analytical validation of performance on a generalization dataset from one or more institutions, followed by a clinical validation study of the system's efficacy during deployment. Clinical validation studies are time-consuming, and best practices dictate limited re-use of analytical validation data, so it is ideal to know ahead of time if a system is likely to fail analytical or clinical validation. In this paper, we describe a series of sanity tests to identify when a system performs well on development data for the wrong reasons. We illustrate the sanity tests' value by designing a deep learning system to classify pancreatic cancer seen in computed tomography scans.