Deep learning-guided attenuation and scatter correction of 99mTc-MAA SPECT images: towards quantitative analysis in 90Y-SIRT

Abstract Purpose This study aimed to develop deep learning (DL) models for CT-free attenuation correction and Monte Carlo-based scatter correction in 99m Tc-macroagregated albumin ( 99m Tc-MAA) SPECT imaging, with the goal of enhancing quantitative accuracy for improved treatment planning and pre-therapy dosimetry in 90 Y-selctive internal radiation therapy (SIRT). Materials and methods Data from 222 patients who underwent 99m Tc-MAA SPECT imaging prior to 90 Y-SIRT were included in this study. Uncorrected SPECT images (without attenuation and/or scatter correction) were used as input to a modified 3D shifted-window UNet Transformer (Swin UNETR) architecture. Three separate models were trained to predict attenuation corrected (AC), scatter corrected (SC), and joint attenuation and scatter corrected (ASC) SPECT images. The dataset was split into a training set (~ 80%) and an independent test set (~ 20%). Model training was performed using a five-fold cross-validation framework, with final evaluation conducted on the blind test set. To clinically assess model performance, 3D voxel-wise dosimetry was performed on the test set using the local energy deposition method, assuming 99m Tc-MAA as a surrogate for 90 Y distribution. Quantitative evaluation included organ- and voxel-level metrics, along with Gamma analysis using three combinations of distance-to-agreement (DTA, mm) and dose-difference (DD, %) criteria. Results The average (± SD) of the voxel-wise mean error (ME) was ≤ 0.003 Gy for all tasks. The Relative Error (RE (%)) for AC, SC, and ASC tasks were 4.64 ± 7.52%, 8.99 ± 26.35%, and 16.45 ± 25.83%, respectively. Voxel-level Gamma evaluations within the whole body using three different criteria sets, including “DTA: 4.79 mm, DD: 1%”; “DTA: 10 mm, DD: 5%”; and “DTA: 15 mm, DD: 10%” yielded pass rates of over 99.60%. The mean absolute error (MAE) for lesions, normal liver and lungs across all tasks were 3.16 ± 3.39, 0.35 ± 0.36, 0.41 ± 0.47 Gy for AC, 1.97 ± 2.79, 0.19 ± 0.16, 0.22 ± 0.20 Gy, for SC and 5.16 ± 7.10, 0.45 ± 0.51, and 0.34 ± 0.37 Gy for ASC, respectively. Conclusion Multiple models were developed for key SPECT quantification tasks, with potential value in clinical setting lacking reliable CT data or sufficient computational resources for Monte Carlo simulations. The models look promising for potential clinical translation and integration into commercial reconstruction software.