We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Radiology, explicability and AI: closing the gap.
- Authors
López-Úbeda, Pilar; Martín-Noguerol, Teodoro; Luna, Antonio
- Abstract
The article discusses the potential benefits and challenges of integrating artificial intelligence (AI) into radiology departments. AI has the potential to automate routine tasks, improve workflow, and enhance patient care in radiology. However, there are obstacles to the widespread adoption of AI, including the lack of annotated data, technical validation, and integration. Additionally, the "black box" effect of AI, where the internal workings of the system are not transparent, is a concern for physicians and patients. The use of explainable artificial intelligence (XAI) aims to address this issue by making AI algorithms more understandable and transparent. XAI techniques can provide visual or natural language explanations of the AI system's predictions, allowing radiologists to evaluate and trust the recommendations. Furthermore, explainability helps identify instances where the system performs poorly, promoting quality assurance and improvement. The article emphasizes the need for multidisciplinary collaboration between engineers and radiologists to incorporate XAI into AI models and avoid blindly accepting machine results.
- Subjects
ARTIFICIAL intelligence; RADIOLOGY; RADIOLOGIC technologists; NATURAL languages; RADIOLOGISTS; QUALITY assurance
- Publication
European Radiology, 2023, Vol 33, Issue 12, p9466
- ISSN
0938-7994
- Publication type
Article
- DOI
10.1007/s00330-023-09902-8