Digital twins in nuclear medicine: A proposition of a modular pipeline for dosimetry protocol optimization in molecular radiotherapy

<b>Introduction:</b> Digital twins (DTs) are emerging tools for simulating and optimizing therapeutic protocols in personalized nuclear medicine. In this paper, we present a modular pipeline for constructing patient-specific DTs aimed at assessing and improving dosimetry protocols in PRRT such as <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mmultiscripts><mml:mrow><mml:mi>L</mml:mi></mml:mrow> <mml:mprescripts></mml:mprescripts> <mml:none></mml:none> <mml:mrow><mml:mn>177</mml:mn></mml:mrow> </mml:mmultiscripts> <mml:mi>u</mml:mi> <mml:mo>-</mml:mo> <mml:mi>P</mml:mi> <mml:mi>S</mml:mi> <mml:mi>M</mml:mi> <mml:mi>A</mml:mi></mml:math> therapy. <b>Materials & Methods:</b> The pipeline integrates three components: (i) an anatomical DT, generated by registering patient CT scans with an anthropomorphic model; (ii) a functional DT, based on a physiologically-based pharmacokinetic (PBPK) model created in SimBiology; and (iii) a virtual clinical trial module using GATE to simulate particle transport, image simulation, and absorbed dose distribution. Validation metrics include SSIM and DICE for registration quality, and MSE for PBPK model fitting with clinical quantification data. <b>Results</b> The anatomical DT module has been successfully implemented and validated on clinical data, demonstrating its ability to generate realistic, patient-morphed phantom for image-based dosimetry. The modular design allows for individual validation and reuse of each component, enabling stepwise development and integration. This architecture offers a strong foundation for evaluating dosimetry protocols and allowing multi-center standardization efforts in the future. <b>Conclusion:</b> This pipeline introduces a modular and adaptable DT framework to support protocol optimization in radionuclide therapy. As validation progresses, it holds strong potential for future use as a predictive tool for absorbed dose estimation prior to therapy, enabling safer and more effective personalized treatment planning.