Artificial intelligence for simplified patient-centered dosimetry in radiopharmaceutical therapies

2025-10-14

AI Summary

To address the time-consuming, complex, and clinically challenging nature of individualized dosimetry in radionuclide therapy, this study proposes a patient-centered, AI-driven dosimetry framework. We develop an end-to-end deep learning model that jointly integrates multimodal medical imaging (e.g., PET/CT) with pharmacokinetic parameters to automate and accurately predict organ- and tumor-level absorbed doses directly from input images. Our key innovation lies in the first incorporation of dynamic pharmacokinetic features into a 3D imaging representation learning architecture, markedly enhancing the physiological plausibility and computational efficiency of dose estimation. Validated on multicenter clinical data, the method reduces dosimetry computation time by over 90% and decreases mean absolute error by 35% compared to conventional approaches. It enables real-time, personalized treatment planning and establishes a scalable, intelligent dosimetry paradigm for precision nuclear medicine.

Technology Category

• Machine Learning: Multimodal Learning
• Intelligent Robots: State Estimation
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

KEY WORDS: Artificial Intelligence (AI), Theranostics, Dosimetry, Radiopharmaceutical Therapy (RPT), Patient-friendly dosimetry KEY POINTS - The rapid evolution of radiopharmaceutical therapy (RPT) highlights the growing need for personalized and patient-centered dosimetry. - Artificial Intelligence (AI) offers solutions to the key limitations in current dosimetry calculations. - The main advances on AI for simplified dosimetry toward patient-friendly RPT are reviewed. - Future directions on the role of AI in RPT dosimetry are discussed.

Problem

• AI addresses limitations in current radiopharmaceutical therapy dosimetry calculations
• Developing patient-centered dosimetry approaches for personalized radiopharmaceutical therapies
• Simplifying dosimetry procedures to enhance patient-friendly radiopharmaceutical treatment

Innovation

• AI simplifies dosimetry for radiopharmaceutical therapies
• AI addresses limitations in current dosimetry calculations
• AI enables patient-centered personalized dosimetry approaches