Synthetic imaging for research and education in nuclear medicine: Who’s afraid of the black box?

In conclusion, we recognize and appreciate the innovative contribution of the authors in addressing data scarcity through synthetic imaging. Their work opens exciting new avenues for nuclear medicine, yet it also underscores the necessity for further research to ensure that the integration of synthetic data into clinical practice is both ethically sound and clinically robust. Future studies should prioritize developing methodologies to improve model interpretability, safeguard patient privacy and ensure that generated images faithfully capture the full variability of real-world clinical cases. Only by addressing these challenges we can fully harness the potential of synthetic imaging while maintaining the highest standards of medical accuracy and ethical responsibility. Fei-Fei Li, a renowned computer scientist, recently stated: “Artificial intelligence is not a substitute for human intelligence; it is a tool to amplify human creativity and ingenuity”. We firmly believe that it is the duty of the scientific community to convoy the potential of artificial intelligence into creative and useful applications, avoiding to stumble into concealed traps.