Markerless motion estimation for motion-compensated clinical brain imaging

Validation and Evaluation of a Vendor-Provided Head Motion Correction Algorithm on the uMI Panorama PET/CT System

Brain PET imaging often faces challenges from head motion (HM), which can introduce artifacts and reduce image resolution, crucial in clinical settings for accurate treatment planning, diagnosis, and monitoring. United Imaging Healthcare has developed NeuroFocus, an HM correction (HMC) algorithm for the uMI Panorama PET/CT system, using a data-driven, statistics-based approach. The HMC algorithm automatically detects HM using a centroid-of-distribution technique, requiring no parameter adjustments. This study aimed to validate NeuroFocus and assess the prevalence of HM in clinical short-duration 18F-FDG scans. Methods: The study involved 317 patients undergoing brain PET scans, divided into 2 groups: 15 for HMC validation and 302 for evaluation. Validation involved patients undergoing 2 consecutive 3-min single-bed-position brain 18F-FDG scans-one with instructions to remain still and another with instructions to move substantially. The evaluation examined 302 clinical single-bed-position brain scans for patients with various neurologic diagnoses. Motion was categorized as small or large on the basis of a 5% SUV change in the frontal lobe after HMC. Percentage differences in SUVmean were reported across 11 brain regions. Results: The validation group displayed a large negative difference (-10.1%), with variation of 5.2% between no-HM and HM scans. After HMC, this difference decreased dramatically (-0.8%), with less variation (3.2%), indicating effective HMC application. In the evaluation group, 38 of 302 patients experienced large HM, showing a 10.9% ± 8.9% SUV increase after HMC, whereas most exhibited minimal uptake changes (0.1% ± 1.3%). The HMC algorithm not only enhanced the image resolution and contrast but also aided in disease identification and reduced the need for repeat scans, potentially optimizing clinical workflows. Conclusion: The study confirmed the effectiveness of NeuroFocus in managing HM in short clinical 18F-FDG studies on the uMI Panorama PET/CT system. It found that approximately 12% of scans required HMC, establishing HMC as a reliable tool for clinical brain 18F-FDG studies.

Clinical application of AI-based PET images in oncological patients

Based on the advantages of revealing the functional status and molecular expression of tumor cells, positron emission tomography (PET) imaging has been performed in numerous types of malignant diseases for diagnosis and monitoring. However, insufficient image quality, the lack of a convincing evaluation tool and intra- and interobserver variation in human work are well-known limitations of nuclear medicine imaging and restrict its clinical application. Artificial intelligence (AI) has gained increasing interest in the field of medical imaging due to its powerful information collection and interpretation ability. The combination of AI and PET imaging potentially provides great assistance to physicians managing patients. Radiomics, an important branch of AI applied in medical imaging, can extract hundreds of abstract mathematical features of images for further analysis. In this review, an overview of the applications of AI in PET imaging is provided, focusing on image enhancement, tumor detection, response and prognosis prediction and correlation analyses with pathology or specific gene mutations in several types of tumors. Our aim is to describe recent clinical applications of AI-based PET imaging in malignant diseases and to focus on the description of possible future developments.

An objective evaluation method for head motion estimation in PET-Motion corrected centroid-of-distribution

Head motion presents a continuing problem in brain PET studies. A wealth of motion correction (MC) algorithms had been proposed in the past, including both hardware-based methods and data-driven methods. However, in most real brain PET studies, in the absence of ground truth or gold standard of motion information, it is challenging to objectively evaluate MC quality. For MC evaluation, image-domain metrics, e.g., standardized uptake value (SUV) change before and after MC are commonly used, but this measure lacks objectivity because 1) other factors, e.g., attenuation correction, scatter correction and parameters used in the reconstruction, will confound MC effectiveness; 2) SUV only reflects final image quality, and it cannot precisely inform when an MC method performed well or poorly during the scan time period; 3) SUV is tracer-dependent and head motion may cause increases or decreases in SUV for different tracers, so evaluating MC effectiveness is complicated. Here, we present a new algorithm, i.e., motion corrected centroid-of-distribution (MCCOD) to perform objective quality control for measured or estimated rigid motion information. MCCOD is a three-dimensional surrogate trace of the center of tracer distribution after performing rigid MC using the existing motion information. MCCOD is used to inform whether the motion information is accurate, using the PET raw data only, i.e., without PET image reconstruction, where inaccurate motion information typically leads to abrupt changes in the MCCOD trace. MCCOD was validated using simulation studies and was tested on real studies acquired from both time-of-flight (TOF) and non-TOF scanners. A deep learning-based brain mask segmentation was implemented, which is shown to be necessary for non-TOF MCCOD generation. MCCOD is shown to be effective in detecting abrupt translation motion errors in slowly varying tracer distribution caused by the motion tracking hardware and can be used to compare different motion estimation methods as well as to improve existing motion information.

Supervised Deep Learning for Head Motion Correction in PET

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.

Brain PET motion correction using 3D face-shape model: the first clinical study

OBJECTIVE

Head motions during brain PET scan cause degradation of brain images, but head fixation or external-maker attachment become burdensome on patients. Therefore, we have developed a motion correction method that uses a 3D face-shape model generated by a range-sensing camera (Kinect) and by CT images. We have successfully corrected the PET images of a moving mannequin-head phantom containing radioactivity. Here, we conducted a volunteer study to verify the effectiveness of our method for clinical data.

METHODS

Eight healthy men volunteers aged 22-45 years underwent a 10-min head-fixed PET scan as a standard of truth in this study, which was started 45 min after ¹⁸F-fluorodeoxyglucose (285 ± 23 MBq) injection, and followed by a 15-min head-moving PET scan with the developed Kinect based motion-tracking system. First, selecting a motion-less period of the head-moving PET scan provided a reference PET image. Second, CT images separately obtained on the same day were registered to the reference PET image, and create a 3D face-shape model, then, to which Kinect-based 3D face-shape model matched. This matching parameter was used for spatial calibration between the Kinect and the PET system. This calibration parameter and the motion-tracking of the 3D face shape by Kinect comprised our motion correction method. The head-moving PET with motion correction was compared with the head-fixed PET images visually and by standard uptake value ratios (SUVRs) in the seven volume-of-interest regions. To confirm the spatial calibration accuracy, a test-retest experiment was performed by repeating the head-moving PET with motion correction twice where the volunteer's pose and the sensor's position were different.

RESULTS

No difference was identified visually and statistically in SUVRs between the head-moving PET images with motion correction and the head-fixed PET images. One of the small nuclei, the inferior colliculus, was identified in the head-fixed PET images and in the head-moving PET images with motion correction, but not in those without motion correction. In the test-retest experiment, the SUVRs were well correlated (determinant coefficient, r² = 0.995).

CONCLUSION

Our motion correction method provided good accuracy for the volunteer data which suggested it is useable in clinical settings.

Adaptive data-driven motion detection and optimized correction for brain PET

Head motion during PET scans causes image quality degradation, decreased concentration in regions with high uptake and incorrect outcome measures from kinetic analysis of dynamic datasets. Previously, we proposed a data-driven method, center of tracer distribution (COD), to detect head motion without an external motion tracking device. There, motion was detected using one dimension of the COD trace with a semiautomatic detection algorithm, requiring multiple user defined parameters and manual intervention. In this study, we developed a new data-driven motion detection algorithm, which is automatic, self-adaptive to noise level, does not require user-defined parameters and uses all three dimensions of the COD trace (3DCOD). 3DCOD was first validated and tested using 30 simulation studies (¹⁸F-FDG, N = 15; ¹¹C-raclopride (RAC), N = 15) with large motion. The proposed motion correction method was tested on 22 real human datasets, with 20 acquired from a high resolution research tomograph (HRRT) scanner (¹⁸F-FDG, N = 10; ¹¹C-RAC, N = 10) and 2 acquired from the Siemens Biograph mCT scanner. Real-time hardware-based motion tracking information (Vicra) was available for all real studies and was used as the gold standard. 3DCOD was compared to Vicra, no motion correction (NMC), one-direction COD (our previous method called 1DCOD) and two conventional frame-based image registration (FIR) algorithms, i.e., FIR1 (based on predefined frames reconstructed with attenuation correction) and FIR2 (without attenuation correction) for both simulation and real studies. For the simulation studies, 3DCOD yielded -2.3 ± 1.4% (mean ± standard deviation across all subjects and 11 brain regions) error in region of interest (ROI) uptake for ¹⁸F-FDG (-3.4 ± 1.7% for ¹¹C-RAC across all subjects and 2 regions) as compared to Vicra (perfect correction) while NMC, FIR1, FIR2 and 1DCOD yielded -25.4 ± 11.1% (-34.5 ± 16.1% for ¹¹C- RAC), -13.4 ± 3.5% (-16.1 ± 4.6%), -5.7 ± 3.6% (-8.0 ± 4.5%) and -2.6 ± 1.5% (-5.1 ± 2.7%), respectively. For real HRRT studies, 3DCOD yielded -0.3 ± 2.8% difference for ¹⁸F-FDG (-0.4 ± 3.2% for ¹¹C-RAC) as compared to Vicra while NMC, FIR1, FIR2 and 1DCOD yielded -14.9 ± 9.0% (-24.5 ± 14.6%), -3.6 ± 4.9% (-13.4 ± 14.3%), -0.6 ± 3.4% (-6.7 ± 5.3%) and -1.5 ± 4.2% (-2.2 ± 4.1%), respectively. In summary, the proposed motion correction method yielded comparable performance to the hardware-based motion tracking method for multiple tracers, including very challenging cases with large frequent head motion, in studies performed on a non-TOF scanner.

Marker-less and calibration-less motion correction method for brain PET

Marker-less head motion correction methods have been well-studied; however, no reports discussing potential issues in positional calibration between a PET system and an external sensor remain limited. In this study, we develop a method for positional calibration between the PET system and an external range sensor to achieve practical head motion correction. The basic concept of the developed method involves using the subject's face model as a marker not only for head motion detection but also for the system positional calibration. The face model of the subject, which can be obtained easily using the range sensor, can also be calculated from a computed tomography (CT) image of the same subject. The CT image, which is acquired separately for attenuation correction in PET, has the same coordinates as the PET image because of the appropriate matching algorithm between CT and PET images. The proposed method was implemented in the helmet-type PET and the motion correction accuracy was assessed quantitatively using a mannequin head. The phantom experiments demonstrated the performance of the developed motion correction method; high-resolution images with no trace of the applied motion were obtained as if no motion was provided. Statistical analysis supported the visual assessment results in terms of the spatial resolution, contrast recovery; uniformity, and the results implied that motion with correction slightly improved image quality compared with the motionless case. The tolerance of the developed method against potential tracking errors had a minimum 10% difference in the amplitude of the rotation angle.

Perspectives of brain imaging with PET systems

In this partial review and partial attempt at vision of what may be the future of dedicated brain PET scanners, the key implementations of the PET technique, we postulate that we are still on a development path and there is still a lot to be done in order to develop optimal brain imagers. Optimized for particular imaging tasks and protocols, and also mobile, that can be used outside the PET center, in addition to the expected improvements in sensitivity and resolution. For this multi-application concept to be more practical, flexible, adaptable designs are preferred. This task is greatly facilitated by the improved TOF performance that allows for more open, adjustable, limited angular coverage geometries without creating image artifacts. As achieving uniform very high resolution in the whole body is not practical due to technological limits and high costs, hybrid systems using a moderate-resolution total body scanner (such as J-PET) combined with a very high performing brain imager could be a very attractive approach. As well, as using magnification inserts in the total body or long-axial length imagers to visualize selected targets with higher resolution. In addition, multigamma imagers combining PET with Compton imaging should be developed to enable multitracer imaging.

Rigid motion tracking using moments of inertia in TOF-PET brain studies

A data-driven method is proposed for rigid motion estimation directly from time-of-flight (TOF)-positron emission tomography (PET) emission data. Rigid motion parameters (translations and rotations) are estimated from the first and second moments of the emission data masked in a spherical volume. The accuracy of the method is analyzed on 3D analytical simulations of the PET-SORTEO brain phantom, and subsequently tested on¹⁸F-FDG as well as¹¹C-PIB brain datasets acquired on a TOF-PET/CT scanner. The estimated inertia-based motion is later compared to rigid motion parameters obtained by directly registering the short frame backprojections. We find that the method provides sub mm/degree accuracies for the estimated rigid motion parameters for counts corresponding to typical 0.5 s, 1 s, and 2 s¹⁸F-FDG brain scans, with the current TOF resolutions clinically available. The method provides robust motion estimation for different types of patient motion, most notably for a continuous patient motion case where conventional frame-based approaches which rely on little to no intra-frame motion of short time intervals could fail. The method relies on the detection of stable eigenvectors for accurate motion estimation, and a monitoring of this condition can reveal time-frames where the motion estimation is less accurate, such as in dynamic PET studies.

Motion estimation and correction in SPECT, PET and CT

Patient motion impacts single photon emission computed tomography (SPECT), positron emission tomography (PET) and X-ray computed tomography (CT) by giving rise to projection data inconsistencies that can manifest as reconstruction artifacts, thereby degrading image quality and compromising accurate image interpretation and quantification. Methods to estimate and correct for patient motion in SPECT, PET and CT have attracted considerable research effort over several decades. The aims of this effort have been two-fold: to estimate relevant motion fields characterizing the various forms of voluntary and involuntary motion; and to apply these motion fields within a modified reconstruction framework to obtain motion-corrected images. The aims of this review are to outline the motion problem in medical imaging and to critically review published methods for estimating and correcting for the relevant motion fields in clinical and preclinical SPECT, PET and CT. Despite many similarities in how motion is handled between these modalities, utility and applications vary based on differences in temporal and spatial resolution. Technical feasibility has been demonstrated in each modality for both rigid and non-rigid motion, but clinical feasibility remains an important target. There is considerable scope for further developments in motion estimation and correction, and particularly in data-driven methods that will aid clinical utility. State-of-the-art machine learning methods may have a unique role to play in this context.

Conditional Generative Adversarial Networks Aided Motion Correction of Dynamic 18F-FDG PET Brain Studies

This work set out to develop a motion-correction approach aided by conditional generative adversarial network (cGAN) methodology that allows reliable, data-driven determination of involuntary subject motion during dynamic ¹⁸F-FDG brain studies. Methods: Ten healthy volunteers (5 men/5 women; mean age ± SD, 27 ± 7 y; weight, 70 ± 10 kg) underwent a test–retest ¹⁸F-FDG PET/MRI examination of the brain (n = 20). The imaging protocol consisted of a 60-min PET list-mode acquisition contemporaneously acquired with MRI, including MR navigators and a 3-dimensional time-of-flight MR angiography sequence. Arterial blood samples were collected as a reference standard representing the arterial input function (AIF). Training of the cGAN was performed using 70% of the total datasets (n = 16, randomly chosen), which was corrected for motion using MR navigators. The resulting cGAN mappings (between individual frames and the reference frame [55–60 min after injection]) were then applied to the test dataset (remaining 30%, n = 6), producing artificially generated low-noise images from early high-noise PET frames. These low-noise images were then coregistered to the reference frame, yielding 3-dimensional motion vectors. Performance of cGAN-aided motion correction was assessed by comparing the image-derived input function (IDIF) extracted from a cGAN-aided motion-corrected dynamic sequence with the AIF based on the areas under the curves (AUCs). Moreover, clinical relevance was assessed through direct comparison of the average cerebral metabolic rates of glucose (CMRGlc) values in gray matter calculated using the AIF and the IDIF. Results: The absolute percentage difference between AUCs derived using the motion-corrected IDIF and the AIF was (1.2% + 0.9%). The gray matter CMRGlc values determined using these 2 input functions differed by less than 5% (2.4% + 1.7%). Conclusion: A fully automated data-driven motion-compensation approach was established and tested for ¹⁸F-FDG PET brain imaging. cGAN-aided motion correction enables the translation of noninvasive clinical absolute quantification from PET/MR to PET/CT by allowing the accurate determination of motion vectors from the PET data itself.

Data-Driven Motion Detection and Event-by-Event Correction for Brain PET: Comparison with Vicra

Head motion degrades image quality and causes erroneous parameter estimates in tracer kinetic modeling in brain PET studies. Existing motion correction methods include frame-based image registration (FIR) and correction using real-time hardware-based motion tracking (HMT) information. However, FIR cannot correct for motion within 1 predefined scan period, and HMT is not readily available in the clinic since it typically requires attaching a tracking device to the patient. In this study, we propose a motion correction framework with a data-driven algorithm, that is, using the PET raw data itself, to address these limitations. Methods: We propose a data-driven algorithm, centroid of distribution (COD), to detect head motion. In COD, the central coordinates of the line of response of all events are averaged over 1-s intervals to generate a COD trace. A point-to-point change in the COD trace in 1 direction that exceeded a user-defined threshold was defined as a time point of head motion, which was followed by manually adding additional motion time points. All the frames defined by such time points were reconstructed without attenuation correction and rigidly registered to a reference frame. The resulting transformation matrices were then used to perform the final motion-compensated reconstruction. We applied the new COD framework to 23 human dynamic datasets, all containing large head motion, with ¹⁸F-FDG (n = 13) and ¹¹C-UCB-J ((R)-1-((3-(¹¹C-methyl-¹¹C)pyridin-4-yl)methyl)-4-(3,4,5-trifluorophenyl)pyrrolidin-2-one) (n = 10) and compared its performance with FIR and with HMT using Vicra (an optical HMT device), which can be considered the gold standard. Results: The COD method yielded a 1.0% ± 3.2% (mean ± SD across all subjects and 12 gray matter regions) SUV difference for ¹⁸F-FDG (3.7% ± 5.4% for ¹¹C-UCB-J) compared with HMT, whereas no motion correction (NMC) and FIR yielded -15.7% ± 12.2% (-20.5% ± 15.8%) and -4.7% ± 6.9% (-6.2% ± 11.0%), respectively. For ¹⁸F-FDG dynamic studies, COD yielded differences of 3.6% ± 10.9% in K _i value as compared with HMT, whereas NMC and FIR yielded -18.0% ± 39.2% and -2.6% ± 19.8%, respectively. For ¹¹C-UCB-J, COD yielded 3.7% ± 5.2% differences in V _T compared with HMT, whereas NMC and FIR yielded -20.0% ± 12.5% and -5.3% ± 9.4%, respectively. Conclusion: The proposed COD-based data-driven motion correction method outperformed FIR and achieved comparable or even better performance than the Vicra HMT method in both static and dynamic studies.

MRI-Driven PET Image Optimization for Neurological Applications

Positron emission tomography (PET) and magnetic resonance imaging (MRI) are established imaging modalities for the study of neurological disorders, such as epilepsy, dementia, psychiatric disorders and so on. Since these two available modalities vary in imaging principle and physical performance, each technique has its own advantages and disadvantages over the other. To acquire the mutual complementary information and reinforce each other, there is a need for the fusion of PET and MRI. This combined dual-modality (either sequential or simultaneous) could generate preferable soft tissue contrast of brain tissue, flexible acquisition parameters, and minimized exposure to radiation. The most unique superiority of PET/MRI is mainly manifested in MRI-based improvement for the inherent limitations of PET, such as motion artifacts, partial volume effect (PVE) and invasive procedure in quantitative analysis. Head motion during scanning significantly deteriorates the effective resolution of PET image, especially for the dynamic scan with lengthy time. Hybrid PET/MRI device can offer motion correction (MC) for PET data through MRI information acquired simultaneously. Regarding the PVE associated with limited spatial resolution, the process and reconstruction of PET data can be further optimized by using acquired MRI either sequentially or simultaneously. The quantitative analysis of dynamic PET data mainly relies upon an invasive arterial blood sampling procedure to acquire arterial input function (AIF). An image-derived input function (IDIF) method without the need of arterial cannulization, can serve as a potential alternative estimation of AIF. Compared with using PET data only, combining anatomical or functional information from MRI for improving the accuracy in IDIF approach has been demonstrated. Yet, due to the interference and inherent disparity between the two modalities, these methods for optimizing PET image based on MRI still have many technical challenges. This review discussed upon the most recent progress, current challenges and future directions of MRI-driven PET data optimization for neurological applications, with either sequential or simultaneous acquisition approach.