Head motion correction is an essential component of brain PET imaging, in which even motion of small magnitude can greatly degrade image quality and introduce artifacts. Building upon previous work, we propose a new head motion correction framework taking fast reconstructions as input. The main characteristics of the proposed method are: (i) the adoption of a high-resolution short-frame fast reconstruction workflow; (ii) the development of a novel encoder for PET data representation extraction; and (iii) the implementation of data augmentation techniques. Ablation studies are conducted to assess the individual contributions of each of these design choices. Furthermore, multi-subject studies are conducted on an 18F-FPEB dataset, and the method performance is qualitatively and quantitatively evaluated by MOLAR reconstruction study and corresponding brain Region of Interest (ROI) Standard Uptake Values (SUV) evaluation. Additionally, we also compared our method with a conventional intensity-based registration method. Our results demonstrate that the proposed method outperforms other methods on all subjects, and can accurately estimate motion for subjects out of the training set. All code is publicly available on GitHub: https://github.com/OnofreyLab/dl-hmc_fast_recon_miccai2023.

Head movement is a major limitation in brain positron emission tomography (PET) imaging, which results in image artifacts and quantification errors. Head motion correction plays a critical role in quantitative image analysis and diagnosis of nervous system diseases. However, to date, there is no approach that can track head motion continuously without using an external device. Here, we develop a deep learning-based algorithm to predict rigid motion for brain PET by lever-aging existing dynamic PET scans with gold-standard motion measurements from external Polaris Vicra tracking. We propose a novel Deep Learning for Head Motion Correction (DL-HMC) methodology that consists of three components: (i) PET input data encoder layers; (ii) regression layers to estimate the six rigid motion transformation parameters; and (iii) feature-wise transformation (FWT) layers to condition the network to tracer time-activity. The input of DL-HMC is sampled pairs of one-second 3D cloud representations of the PET data and the output is the prediction of six rigid transformation motion parameters. We trained this network in a supervised manner using the Vicra motion tracking information as gold-standard. We quantitatively evaluate DL-HMC by comparing to gold-standard Vicra measurements and qualitatively evaluate the reconstructed images as well as perform region of interest standard uptake value (SUV) measurements. An algorithm ablation study was performed to determine the contributions of each of our DL-HMC design choices to network performance. Our results demonstrate accurate motion prediction performance for brain PET using a data-driven registration approach without external motion tracking hardware. All code is publicly available on GitHub: https://github.com/OnofreyLab/dl-hmc_miccai2022.

Cardiac motion frequently reduces the interpretability of PET images. This study utilized a prototype data-driven motion correction (DDMC) algorithm to generate corrected images and compare DDMC images with non-corrected images (NMC) to evaluate image quality and change of perfusion defect size and severity.
Rest and stress images with NMC and DDMC from 40 consecutive patients with motion were rated by 2 blinded investigators on a 4-point visual ordinal scale (0: minimal motion; 1: mild motion; 2: moderate motion; 3: severe motion/uninterpretable). Motion was also quantified using Dwell Fraction, which is the fraction of time the motion vector shows the heart to be within 6 mm of the corrected position and was derived from listmode data of NMC images.
Minimal motion was seen in 15% of patients, while 40%, 30%, and 15% of patients had mild moderate and severe motion, respectively. All corrected images showed an improvement in quality and were interpretable after processing. This was confirmed by a significant correlation (Spearman\'s correlation coefficient 0.626, P < .001) between machine measurement of motion quantification and physician interpretation.
The novel DDMC algorithm improved quality of cardiac PET images with motion. Correlation between machine measurement of motion quantification and physician interpretation was significant.

Head motion during brain PET imaging can significantly degrade the quality of the reconstructed image, leading to reduced diagnostic value and inaccurate quantitation. A fully data-driven motion correction approach was recently demonstrated to produce highly accurate motion estimates (<1 mm) with high temporal resolution (≥1 Hz), which can then be used for a motion-corrected reconstruction. This can be applied retrospectively with no impact on the clinical image acquisition protocol. We present a reader-based evaluation and an atlas-based quantitative analysis of this motion correction approach within a clinical cohort. Methods: Clinical patient data were collected over 2019-2020 and processed retrospectively. Motion was estimated using image-based registration on reconstructions of ultrashort frames (0.6-1.8 s), after which list-mode reconstructions that were fully motion-corrected were performed. Two readers graded the motion-corrected and uncorrected reconstructions. An atlas-based quantitative analysis was performed. Paired Wilcoxon tests were used to test for significant differences in reader scores and SUVs between reconstructions. The Levene test was used to determine whether motion correction had a greater impact on quantitation in the presence of motion than when motion was low. Results: Fifty standard clinical 18F-FDG brain PET datasets (age range, 13-83 y; mean ± SD, 59 ± 20 y; 27 women) from 3 scanners were collected. The reader study showed a significantly different, diagnostically relevant improvement by motion correction when motion was present (P = 0.02) and no impact in low-motion cases. Eight percent of all datasets improved from diagnostically unacceptable to acceptable. The atlas-based analysis demonstrated a significant difference between the motion-corrected and uncorrected reconstructions in cases of high motion for 7 of 8 regions of interest (P < 0.05). Conclusion: The proposed approach to data-driven motion estimation and correction demonstrated a clinically significant impact on brain PET image reconstruction.

Standard clinical reconstructions usually require several minutes to complete, and this time is mostly independent of the duration of the data being reconstructed. Applications such as data-driven motion estimation, which require many short frames over the duration of the scan, become unfeasible with such long reconstruction times. In this work, we present an infrastructure whereby ultra-fast list-mode reconstructions of very short frames (≤1 s) are performed. With this infrastructure, it is possible to have a dynamic series of frames that can be used for various applications, such as data-driven motion estimation, whole-body surveys, quick reconstructions of gated data to select the optimal gate for a given attenuation map, and, if the infrastructure runs simultaneously with the scan, real-time display of the reconstructed data during the scan and automated alerts for patient motion. Methods: A fast ray-tracing time-of-flight projector was implemented and parallelized. The reconstruction parameters were optimized to allow for fast performance: only a few iterations are performed, without point-spread-function modeling, and scatter correction is not used. The resulting reconstructions are thus not quantitative but are acceptable for motion estimation and visualization purposes. Data-driven motion can be estimated using image registration, with the resultant motion data being used in a fully motion-corrected list-mode reconstruction. Results: The infrastructure provided images that can be used for visualization and gating purposes and for motion estimation using image registration. Several case studies are presented, including data-driven motion estimation and correction for brain studies, abdominal studies in which respiratory and cardiac motion is visible, and a whole-body survey. Conclusion: The presented infrastructure provides the capability to quickly create a series of very short frames for PET data that can be used in a variety of applications.

PET imaging has been, and continues to be, an evolving diagnostic technology. In recent years, the modernizing digital landscape has opened new opportunities for data-driven innovation. One such facet has been data-driven motion correction (DDMC) in PET. As both research and industry propel this technology forward, we can recognize prospects and opportunities for further development. The concept of clinical practicality is supported by DDMC approaches-it is what sets them apart from traditional hardware-driven motion correction strategies that have largely not gained acceptance in routine diagnostic PET; the ease of use of DDMC may help propel acceptance of motion correction solutions in clinical practice. As we reflect on the present field, we should consider that DDMC can be made even more practical, and likely more impactful, if further developed to fit within a real-time acquisition framework. This vision for development is not new, but has been made more feasible with contemporary electronics, and has begun to be revisited in contemporary literature. The opportunities for development lie on a new forefront of innovation where medical physics integrates with engineering, data science, and modern computing capacities. Real-time DDMC is a systems integration challenge, and achieving it will require cooperation between hardware and software developers, and likely academia and industry. While challenges for development do exist, it is likely that we will see real-time DDMC come to fruition in the coming years. This effort may establish groundwork for developing similar innovations in the emerging digital innovation age.