Pre-clinical imaging with artificial intelligence and digital twins

Introduction: Pre-clinical molecular imaging is crucial for drug and radiopharmaceutical development. There remain ethical challenges associated with reduction, refinement and replacement across animal imaging; where possible.

Methods: In murine imaging, there have been a number of approaches adopted to enhance ethical compliance, including using algorithmic approaches to animal modelling. Digital twins have been used to create a virtual model of mice. There is an opportunity to exploit deep learning approaches in digital twin development to enhance capabilities.

Results: Generative adversarial networks produce generated images that sufficiently resemble reality that they could be adapted to create digital twins. Specific genetic mouse models have greater homogeneity making them more receptive to modelling and suitable specifically for digital twin simulation.

Conclusions: There are potential benefits of digital twins in pre-clinical imaging including improved outcomes, fewer animal studies, shorter development timelines and lower costs.