Decentralized collaborative multi-institutional PET attenuation and scatter correction using federated deep learning

Abstract

Purpose Attenuation correction and scatter compensation (AC/SC) are two main steps toward quantitative PET imaging, which remain challenging in PET-only and PET/MRI systems. These can be effectively tackled via deep learning (DL) methods. However, trustworthy, and generalizable DL models commonly require well-curated, heterogeneous, and large datasets from multiple clinical centers. At the same time, owing to legal/ethical issues and privacy concerns, forming a large collective, centralized dataset poses significant challenges. In this work, we aimed to develop a DL-based model in a multicenter setting without direct sharing of data using federated learning (FL) for AC/SC of PET images. Methods Non-attenuation/scatter corrected and CT-based attenuation/scatter corrected (CT-ASC) 18F-FDG PET images of 300 patients were enrolled in this study. The dataset consisted of 6 different centers, each with 50 patients, with scanner, image acquisition, and reconstruction protocols varying across the centers. CT-based ASC PET images served as the standard reference. All images were reviewed to include high-quality and artifact-free PET images. Both corrected and uncorrected PET images were converted to standardized uptake values (SUVs). We used a modified nested U-Net utilizing residual U-block in a U-shape architecture. We evaluated two FL models, namely sequential (FL-SQ) and parallel (FL-PL) and compared their performance with the baseline centralized (CZ) learning model wherein the data were pooled to one server, as well as center-based (CB) models where for each center the model was built and evaluated separately. Data from each center were divided to contribute to training (30 patients), validation (10 patients), and test sets (10 patients). Final evaluations and reports were performed on 60 patients (10 patients from each center). Results In terms of percent SUV absolute relative error (ARE%), both FL-SQ (CI:12.21–14.81%) and FL-PL (CI:11.82–13.84%) models demonstrated excellent agreement with the centralized framework (CI:10.32–12.00%), while FL-based algorithms improved model performance by over 11% compared to CB training strategy (CI: 22.34–26.10%). Furthermore, the Mann–Whitney test between different strategies revealed no significant differences between CZ and FL-based algorithms (p-value > 0.05) in center-categorized mode. At the same time, a significant difference was observed between the different training approaches on the overall dataset (p-value < 0.05). In addition, voxel-wise comparison, with respect to reference CT-ASC, exhibited similar performance for images predicted by CZ (R2 = 0.94), FL-SQ (R2 = 0.93), and FL-PL (R2 = 0.92), while CB model achieved a far lower coefficient of determination (R2 = 0.74). Despite the strong correlations between CZ and FL-based methods compared to reference CT-ASC, a slight underestimation of predicted voxel values was observed. Conclusion Deep learning-based models provide promising results toward quantitative PET image reconstruction. Specifically, we developed two FL models and compared their performance with center-based and centralized models. The proposed FL-based models achieved higher performance compared to center-based models, comparable with centralized models. Our work provided strong empirical evidence that the FL framework can fully benefit from the generalizability and robustness of DL models used for AC/SC in PET, while obviating the need for the direct sharing of datasets between clinical imaging centers.

Artificial Intelligence–Driven Single-Shot PET Image Artifact Detection and Disentanglement

“…As such, attenuation and scatter correction (ASC) is crucial toward quantitative PET. [7][8][9][10][11][12][13][14][15] Quantitatively accurate and visually interpretable PET image generation requires CT or MRI integration into scanners for ASC. [7][8][9][10][11][12][13][14][15] In clinical setting, an unenhanced low-dose CT is commonly acquired on PET/CT scanners for ASC, even though a diagnostic CT scan with injection of contrast agent is sometimes utilized for the same purpose.…”

“…[7][8][9][10][11][12][13][14][15] Quantitatively accurate and visually interpretable PET image generation requires CT or MRI integration into scanners for ASC. [7][8][9][10][11][12][13][14][15] In clinical setting, an unenhanced low-dose CT is commonly acquired on PET/CT scanners for ASC, even though a diagnostic CT scan with injection of contrast agent is sometimes utilized for the same purpose. 7,8,[11][12][13][14] Eliminating this CT scan may potentially benefit patients who require multiple follow-up PET/CT examinations, particularly the pediatric population, for which even a small decrease in the cumulative radiation dose would be valuable.…”

“…[7][8][9][10][11][12][13][14][15] In clinical setting, an unenhanced low-dose CT is commonly acquired on PET/CT scanners for ASC, even though a diagnostic CT scan with injection of contrast agent is sometimes utilized for the same purpose. 7,8,[11][12][13][14] Eliminating this CT scan may potentially benefit patients who require multiple follow-up PET/CT examinations, particularly the pediatric population, for which even a small decrease in the cumulative radiation dose would be valuable. 11,14,16 In addition to conventional ASC algorithms implemented on PET/MRI systems and standalone PET scanners, deep learning (DL) algorithms have been recently proposed for tackling this issue.…”

“…7,8,[11][12][13][14] Eliminating this CT scan may potentially benefit patients who require multiple follow-up PET/CT examinations, particularly the pediatric population, for which even a small decrease in the cumulative radiation dose would be valuable. 11,14,16 In addition to conventional ASC algorithms implemented on PET/MRI systems and standalone PET scanners, deep learning (DL) algorithms have been recently proposed for tackling this issue. 7,8,[11][12][13][14][16][17][18][19] Overall, various DL-based methods have been proposed for ASC of PET images, 19 such as pseudo-CT synthesis from either MRI or noncorrected PET images, 20 scatter map prediction from emission data, 21 and direct ASC PET image generation from non-ASC-corrected images.…”

“…11,14,16 In addition to conventional ASC algorithms implemented on PET/MRI systems and standalone PET scanners, deep learning (DL) algorithms have been recently proposed for tackling this issue. 7,8,[11][12][13][14][16][17][18][19] Overall, various DL-based methods have been proposed for ASC of PET images, 19 such as pseudo-CT synthesis from either MRI or noncorrected PET images, 20 scatter map prediction from emission data, 21 and direct ASC PET image generation from non-ASC-corrected images. 11 Highly intense radiopharmaceutical accumulation could result in halo or photopenic artifacts, making it challenging to interpret adjacent organs.…”