Korean J Radiol.
2023 Nov;24(11):1061-1080. 10.3348/kjr.2023.0393.
Overcoming the Challenges in the Development and Implementation of Artificial Intelligence in Radiology: A Comprehensive Review of Solutions Beyond Supervised Learning
- Affiliations
-
- 1Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
- 2Department of Convergence Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
- 3Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
- 4Laboratory for Biosignal Analysis and Perioperative Outcome Research, Biomedical Engineering Center, Asan Institute of Lifesciences, Asan Medical Center, Seoul, Republic of Korea
- 5Department of Orthopedic Surgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
- KMID: 2547235
- DOI: http://doi.org/10.3348/kjr.2023.0393
Abstract
- Artificial intelligence (AI) in radiology is a rapidly developing field with several prospective clinical studies demonstrating its benefits in clinical practice. In 2022, the Korean Society of Radiology held a forum to discuss the challenges and drawbacks in AI development and implementation. Various barriers hinder the successful application and widespread adoption of AI in radiology, such as limited annotated data, data privacy and security, data heterogeneity, imbalanced data, model interpretability, overfitting, and integration with clinical workflows. In this review, some of the various possible solutions to these challenges are presented and discussed; these include training with longitudinal and multimodal datasets, dense training with multitask learning and multimodal learning, self-supervised contrastive learning, various image modifications and syntheses using generative models, explainable AI, causal learning, federated learning with large data models, and digital twins.
- Full Text Links
-
- Actions
-
Cited
- CITED
-
- Close
- Share
-
- Similar articles
-
- Clinical Implementation of Deep Learning in ThoracicRadiology: Potential Applications and Challenges
- The principles of artificial intelligence and its applications in dentistry
- The Latest Trends in the Use of Deep Learning in Radiology Illustrated Through the Stages of Deep Learning Algorithm Development
- Understanding and Application of Multi-Task Learning in Medical Artificial Intelligence
- Deep Learning in Upper Gastrointestinal Disorders: Status and Future Perspectives
