Evolutionary Strategies Enable Systematic and Reliable Uncertainty Quantification: A Proof-of-Concept Pilot Study on Resting-State Functional MRI Language Lateralization

• Published in: Journal of imaging informatics in medicine
• Main Authors: Stember, Joseph N, Dishner, Katharine, Jenabi, Mehrnaz, Pasquini, Luca, K Peck, Kyung, Saha, Atin, Shah, Akash, O'Malley, Bernard, Ilica, Ahmet Turan, Kelly, Lori, Arevalo-Perez, Julio, Hatzoglou, Vaios, Holodny, Andrei, Shalu, Hrithwik
• Format: Journal Article
• Language: English
• Published: Switzerland 09.07.2024
• Subjects: Uncertainty quantification; Artificial intelligence; Deep neuroevolution; Image classification

Reliable and trustworthy artificial intelligence (AI), particularly in high-stake medical diagnoses, necessitates effective uncertainty quantification (UQ). Existing UQ methods using model ensembles often introduce invalid variability or computational complexity, rendering them impractical and ineff...