Synthetic Data in Radiological Imaging: Current State and Future Outlook

TL;DR

Synthetic data in radiology can address data scarcity issues for AI development, offering benefits like reduced costs and privacy preservation, but requires further research to fully realize its potential.

Contribution

The paper reviews current research trends, techniques, and evaluation methods for synthetic radiological data, highlighting its advantages and challenges.

Findings

Synthetic data can mitigate privacy and cost issues in radiology AI.

Various techniques exist for generating synthetic radiological images.

Evaluation methods for synthetic data are still evolving.

Abstract

A key challenge for the development and deployment of artificial intelligence (AI) solutions in radiology is solving the associated data limitations. Obtaining sufficient and representative patient datasets with appropriate annotations may be burdensome due to high acquisition cost, safety limitations, patient privacy restrictions or low disease prevalence rates. In silico data offers a number of potential advantages to patient data, such as diminished patient harm, reduced cost, simplified data acquisition, scalability, improved quality assurance testing, and a mitigation approach to data imbalances. We summarize key research trends and practical uses for synthetically generated data for radiological applications of AI. Specifically, we discuss different types of techniques for generating synthetic examples, their main application areas, and related quality control assessment issues. We also discuss current approaches for evaluating synthetic imaging data. Overall, synthetic data holds great promise in addressing current data availability gaps, but additional work is needed before its full potential is realized.