Patient-specific AI for generation of 3D dosimetry imaging from two 2D-planar measurements

2025-10-24

AI Summary

This study addresses the longstanding bottleneck in nuclear medicine—3D dosimetric imaging relying either on costly SPECT acquisitions or suffering from low accuracy due to 2D planar projections. We propose the first patient-specific AI framework capable of reconstructing high-fidelity 3D radiopharmaceutical distribution maps from only two anterior/posterior (AP/PA) planar images. Methodologically, we innovatively integrate a diffusion model with a 3D U-Net architecture and incorporate an anatomy-guided reinforcement learning strategy to optimize generative fidelity. Evaluated on synthetic data, our method achieves an SSIM of 0.89; on clinical data, it attains an SSIM of 0.73—5% higher than prior methods—against half-hour-delayed SPECT (the clinical gold standard), alongside a 20% reduction in MAE. It further demonstrates superior organ segmentation and anatomical structure recovery. To our knowledge, this is the first work enabling rapid, low-cost, SPECT-free, patient-specific 3D dosimetry reconstruction, establishing a new paradigm for dynamic dose monitoring.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Calibration & Uncertainty Quantification
• Planning, Routing, and Scheduling: Planning with Language Models

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: Agentic search

Abstract

In this work we explored the use of patient specific reinforced learning to generate 3D activity maps from two 2D planar images (anterior and posterior). The solution of this problem remains unachievable using conventional methodologies and is of particular interest for dosimetry in nuclear medicine where approaches for post-therapy distribution of radiopharmaceuticals such as 177Lu-PSMA are typically done via either expensive and long 3D SPECT acquisitions or fast, yet only 2D, planar scintigraphy. Being able to generate 3D activity maps from planar scintigraphy opens the gate for new dosimetry applications removing the need for SPECT and facilitating multi-time point dosimetry studies. Our solution comprises the generation of a patient specific dataset with possible 3D uptake maps of the radiopharmaceuticals withing the anatomy of the individual followed by an AI approach (we explored both the use of 3DUnet and diffusion models) able to generate 3D activity maps from 2D planar images. We have validated our method both in simulation and real planar acquisitions. We observed enhanced results using patient specific reinforcement learning (~20% reduction on MAE and ~5% increase in SSIM) and better organ delineation and patient anatomy especially when combining diffusion models with patient specific training yielding a SSIM=0.89 compared to the ground truth for simulations and 0.73 when compared to a SPECT acquisition performed half an hour after the planar. We believe that our methodology can set a change of paradigm for nuclear medicine dosimetry allowing for 3D quantification using only planar scintigraphy without the need of expensive and time-consuming SPECT leveraging the pre-therapy information of the patients.

Problem

• Generating 3D dosimetry imaging from two 2D planar measurements
• Overcoming limitations of expensive SPECT and 2D scintigraphy in nuclear medicine
• Enabling 3D radiopharmaceutical distribution mapping using patient-specific AI models

Innovation

• Patient-specific AI generates 3D dosimetry from 2D images
• Combines diffusion models with patient-specific training datasets
• Enables 3D quantification without expensive SPECT scans