Artificial Intelligence Algorithms Need to Be Explainable—or Do They?
Tyler Bradshaw, Melissa D. McCradden, Abhinav K. Jha, Joyita Dutta, Babak Saboury, Eliot L. Siegel, Arman Rahmim
Abstract
With the growing role of artificial intelligence (AI) in radiology, there is concern over the black-box nature of modern AI algorithms. Users of AI often have no way of knowing how or why an algorithm arrived at a prediction, which makes it difficult for a user to appraise or critique the quality of
Topics & Concepts
Computer scienceArtificial intelligenceQuality (philosophy)Black boxMachine learningAlgorithmData scienceEpistemologyPhilosophyArtificial Intelligence in Healthcare and EducationRadiomics and Machine Learning in Medical ImagingMedical Imaging and Analysis