Machine learning redefines precision cancer therapy using smart radiopharmaceuticals

JMIR Publications released a feature News and Perspectives story on technological advances in oncology. Authored by JMIR Correspondent Benedette Cuffari, "AI-Designed Radiopharmaceuticals: How Machine Learning Is Redefining Precision Cancer Therapy" reports on the integration of deep learning and generative AI in radiopharmaceutical medicine, its impact on accelerating drug design, and how personalized dosimetry can improve patient outcomes.

AI-powered drug discovery 

While radiopharmaceutical therapy is highly effective for some types of cancer, it remains time- and resource-intensive to develop. Deep learning and generative AI models can rapidly identify novel targets, predict chemical interactions, and engineer stable drug candidates. Cuffari speaks with Sofia Michopoulou, PhD, a medical physics expert leading Nuclear Medicine Physics at University Hospital Southampton, who notes that AI-driven computer simulations can "identify the most promising pharmaceutical candidates earlier, reduce the current volume of preclinical work, and make early-phase evaluation more focused and efficient".

Personalized dosimetry and digital twins 

AI models also optimize dosimetry-the calculation of radiation absorbed by tissues to maximize tumor damage while sparing healthy organs. 3D convolutional neural networks analyze medical images to predict biodistribution, while machine learning can also generate patient-specific digital twins for advanced, individualized treatment planning, writes Cuffari.

Barriers to clinical adoption 

Despite these advances, translation to the clinic is hindered by a lack of standardized, high-quality datasets to train AI models. While techniques like federated learning can protect patient confidentiality across hospital sites, extensive foundational experimental research is still required to ensure models generalize appropriately.