3D-Printed Organ-Realistic Phantoms to Verify Quantitative SPECT/CT Accuracy for 177Lu-PSMA-617 Treatment Planning

Abstract

Background/Objectives: Accurate patient-specific dosimetry is essential for optimizing radiopharmaceutical therapy (RPT), but current tools lack validation in clinically realistic conditions. This work aimed to develop a workflow for designing and fabricating patient-derived, organ-realistic RPT phantoms and evaluate their feasibility for commissioning patient-specific RPT radioactivity quantification. Methods: We used computed tomographic (CT) and magnetic resonance (MR) imaging of representative patients, computer-aided design, and in-house 3D printing technology to design and fabricate anthropomorphic kidney and parotid phantoms with realistic organ spacing, anatomically correct orientation, and surrounding tissue heterogeneities. We evaluated the fabrication process via geometric verification (i.e., volume comparisons) and leak testing (i.e., dye penetration tests). Clinical feasibility testing involved injecting known radioactivities of ¹⁷⁷Lu-PSMA-617 into the parotid and kidney cortex phantom chambers and acquiring SPECT/CT images. MIM SurePlan MRT SPECTRA Quant software (v7.1.2) reconstructed the acquired SPECT projections into a quantitative SPECT image and we evaluated the accuracy by region-based comparison to the known injected radioactivities and determined recovery coefficients for each organ phantom. Results: Phantom fabrication costs totaled < USD 250 and required <84 h. Geometric verification showed a slight systematic expansion (<10%) from the representative patient anatomy and leak testing confirmed watertightness of fillable chambers. Quantitative SPECT imaging systematically underestimated the injected radioactivity (mean error: -17.0 MBq; -13.2%) with recovery coefficients ranging from 0.82 to 0.93 that were negatively correlated with the surface-area-to-volume ratio. Conclusions: Patient-derived, 3D-printed fillable phantoms are a feasible, cost-effective tool to support commissioning and quality assurance for patient-specific RPT dosimetry. The results of this work will support other centers and clinics implementing patient-specific RPT dosimetry by providing the tools needed to comprehensively evaluate accuracy in clinically relevant geometries. Looking forward, widespread accurate patient-specific RPT dosimetry will improve our understanding of RPT dose response and enable personalized RPT dosing to optimize patient outcomes.

Keywords: 177Lu; 3D printing; SPECT imaging; partial volume effect; quantitative imaging; radiopharmaceutical therapy.

Figure 1

Pictures of the finished kidney and parotid phantoms following leak evaluations via dye penetration testing. (A) Kidney dye penetration test with blue-dyed water in the medulla chambers and yellow-dyed water in the cortex chambers. (B) First-phase parotid phantom leak testing with red-dyed water in the bone chamber and blue-dyed water in the parotid chamber. (C) Second-phase parotid phantom leak testing with yellow-dyed water in the soft-tissue chambers and blue-dyed water in the parotid chambers.

Figure 2

Representative views of the quantitative single-photon emission computed tomography (SPECT) image (color wash) overlaid on the computed tomography (CT) image (grayscale) collected 96 h post injection. (A) Coronal view of full image acquisition. (B) Axial view of representative slice through the parotid chambers. (C) Axial view of representative slice through the kidney phantom. Colored contours indicate the left parotid (cyan), right parotid (magenta), left kidney cortex (green), and right kidney cortex (purple).

Figure 3

Scatter plots illustrate the sensitivity of the recovery coefficient to the (A) injected radioactivity, (B) region-of-interest volume, and (C) ratio of the region-of-interest surface area to its volume. Red solid lines show the fit line determined by standard linear least-squares analysis and characterized by the r-squared value displayed on each plot.

Figure 4

(A) Segmentation of nonpathological kidneys. Pink and blue lines outline the left and right kidneys, respectively. (B) Unprocessed left and right kidney three-dimensional (3D) parts created in Materialise Mimics. (C) Unprocessed 3D parts in Materialise 3-Matic. (D) Left and right kidney models following computer-aided design processing. (E) Left and right kidney models simulated in labeled base. Labels read Right, Left, Head, and Foot. (F) 3D-printed left and right kidneys with two chambers.

Figure 5

(A) Segmentation of nonpathological parotids (pink) and mandible (blue). (B) Segmentation of nonpathological sinuses (yellow), soft tissue (purple), and bone (orange). (C) Processed lower face computer-aided design model divided into two halves along the sagittal midline plane with masseter muscle (yellow) and chambers for separate bone, soft tissue, and parotid (blue) compartments; (D) side, (E) front, and (F) top-medial views of three-dimensional-printed right parotid model with three chambers for separate bone, soft-tissue, and parotid compartments. Note that only soft-tissue and parotid compartments had valves for on-demand filling.

Figure 6

Schematic diagram of the phantom setup during image acquisition. Not to scale.