Deep-Learning-Aided Intraframe Motion Correction for Low-Count Dynamic Brain PET

• Published in: IEEE transactions on radiation and plasma medical sciences Vol. 8; no. 1; pp. 53 - 63
• Main Authors: Reimers, Erik, Cheng, Ju-Chieh, Sossi, Vesna
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.01.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Brain; Deep learning; Deep learning (DL); Error reduction; Estimation; Head; Head movement; Motion compensation; Motion estimation; Motion simulation; Neural networks; Neuroimaging; Positron emission; Positron emission tomography; Spatial distribution; Spatial resolution; Structure-function relationships; Subframes; Temporal resolution
• ISSN: 2469-7311; 2469-7303
• DOI: 10.1109/TRPMS.2023.3333202

Data-driven intraframe motion correction of a dynamic brain PET scan (with each frame duration on the order of minutes) is often achieved through the co-registration of high-temporal-resolution (e.g., 1-s duration) subframes to estimate subject head motion. However, this conventional method of subframe co-registration may perform poorly during periods of low counts and/or drastic changes in the spatial tracer distribution over time. Here, we propose a deep learning (DL), U-Net-based convolutional neural network model which aids in the PET motion estimation to overcome these limitations. Unlike DL models for PET denoising, a nonstandard 2.5-D DL model was used which transforms the high-temporal-resolution subframes into nonquantitative DL subframes which allow for improved differentiation between noise and structural/functional landmarks and estimate a constant tracer distribution across time. When estimating motion during periods of drastic change in spatial distribution (within the first minute of the scan, ~1-s temporal resolution), the proposed DL method was found to reduce the expected magnitude of error (+/−) in the estimation for an artificially injected motion trace from 16 mm and 7° (conventional method) to 0.7 mm and 0.6° (DL method). During periods of low counts but a relatively constant spatial tracer distribution (60th min of the scan, ~1-s temporal resolution), an expected error was reduced from 0.5 mm and 0.7° (conventional method) to 0.3 mm and 0.4° (DL method). The use of the DL method was found to significantly improve the accuracy of an image-derived input function calculation when motion was present during the first minute of the scan.