AI in multimodality imaging

AI is experiencing a boom, a culmination of decades of research and breakthroughs driven by advancements in computing power, algorithms and data availability. The convergence of these factors, combined with the recognition of the potential of AI to augment human capabilities, have propelled the field into the forefront of technological innovation. In particular, AI is […]AI is experiencing a boom, a culmination of decades of research and breakthroughs driven by advancements in computing power, algorithms and data availability. The convergence of these factors, combined with the recognition of the potential of AI to augment human capabilities, have propelled the field into the forefront of technological innovation. In particular, AI is one of the most talked about topics in healthcare today, and for good reason – AI has the potential to transform how we provide care and improve patient outcomes. It is impacting all branches of medicine, with clinical adoption in radiotherapy and radiology already a reality. Furthermore, its ability to identify and learn complex patterns and relationships across multiple data sources presents even greater potential when applied to imaging data from multiple modalities compared to a single modality’s data alone. However, the recent increase in the adoption and implementation of AI in radiotherapy and radiology has not been matched by that in nuclear medicine, which may, in part, be due to the lower patient numbers seen by nuclear medicine departments. This limits the potential of AI to unlock insights at the functional molecular level present in the data uniquely generated by nuclear medicine studies. It also diminishes the opportunity to benefit from the potential clinical improvements in AI’s impact that could arise from the advances in deep learning (DL) with artificial neural networks (ANN) when applied to functional molecular and anatomical imaging data in combination.

The content on this page is provided by the individuals concerned and does not represent the views or opinions of RAD Magazine.