A Quantitative Comparison Between Human and Artificial Intelligence in the Detection of Focal Cortical Dysplasia.

Artificial intelligence (AI) is thought to improve lesion detection. However, a lack of knowledge about human performance prevents a comparative evaluation of AI and an accurate assessment of its impact on clinical decision-making. The objective of this work is to quantitatively evaluate the ability of humans to detect focal cortical dysplasia (FCD), compare it to state-of-the-art AI, and determine how it may aid diagnostics. We prospectively recorded the performance of readers in detecting FCDs using single points and 3-dimensional bounding boxes. We acquired predictions of 3 AI models for the same dataset and compared these to readers. Finally, we analyzed pairwise combinations of readers and models. Twenty-eight readers, including 20 nonexpert and 5 expert physicians, reviewed 180 cases: 146 subjects with FCD (median age: 25, interquartile range: 18) and 34 healthy control subjects (median age: 43, interquartile range: 19). Nonexpert readers detected 47% (95% confidence interval [CI]: 46, 49) of FCDs, whereas experts detected 68% (95% CI: 65, 71). The 3 AI models detected 32%, 51%, and 72% of FCDs, respectively. The latter, however, also predicted more than 13 false-positive clusters per subject on average. Human performance was improved in the presence of a transmantle sign (P < 0.001) and cortical thickening (P < 0.001). In contrast, AI models were sensitive to abnormal gyration (P < 0.01) or gray-white matter blurring (P < 0.01). Compared with single experts, expert-expert pairs detected 13% (95% CI: 9, 18) more FCDs (P < 0.001). All AI models increased expert detection rates by up to 19% (95% CI: 15, 24) (P < 0.001). Nonexpert+AI pairs could still outperform single experts by up to 13% (95% CI: 10, 17). This study pioneers the comparative evaluation of humans and AI for FCD lesion detection. It shows that AI and human predictions differ, especially for certain MRI features of FCD, and, thus, how AI may complement the diagnostic workup.

Copyright © 2024 Wolters Kluwer Health, Inc. All rights reserved.

Conflicts of interest and sources of funding: A.R. has received fees as a speaker from UCB Pharma and travel support from the Elisabeth und Helmut Uhl Stiftung. U.A. has received fees as a speaker for Siemens Healthineers and as clinical consultant for Bayer. A.R. lectures for Guerbet and Bayer, and is part of the Advisory Board for GE, Bracco, and Guerbet. R.S. has received personal fees as speaker or for serving on advisory boards from Angelini, Arvelle, Bial, Desitin, Eisai, Jazz Pharmaceuticals Germany GmbH, Janssen-Cilag GmbH, LivaNova, LivAssured B.V., Novartis, Precisis GmbH, Rapport Therapeutics, Tabuk Pharmaceuticals, UCB Pharma, UNEEG, and Zogenix. T.R. has received fees as a speaker from Eisai. None of the previously mentioned activities were related to the content of this manuscript. The remaining authors have nothing to declare. No external funding was received for this work.