The EPICURE study: a pilot prospective cohort study of heterogeneous and massive data integration in metastatic breast cancer patients.

BACKGROUND: Breast cancer is the most common cancer in women and the first cancer concerning mortality. Metastatic breast cancer remains a disease with a poor prognosis and about 30% of women diagnosed with an early stage will have a secondary progression. Metastatic breast cancer is an incurable disease despite significant therapeutic advances in both supportive cares and targeted specific therapies. In the management of a metastatic patient, each clinician follows a highly complex and strictly personal decision making process. It is based on a number of objective and subjective parameters which guides therapeutic choice in the most individualized or adapted manner. METHODS/DESIGN: The main objective is to integrate massive and heterogeneous data concerning the patient's environment, personal and familial history, clinical and biological data, imaging, histological results (with multi-omics data), and microbiota analysis. These characteristics are multiple and in dynamic interaction overtime. With the help of mathematical units with biological competences and scientific collaborations, our project is to improve the comprehension of treatment response, based on health clinical and molecular heterogeneous big data investigation. DISCUSSION: Our project is to prove feasibility of creation of a clinico-biological database prospectively by collecting epidemiological, socio-economic, clinical, biological, pathological, multi-omic data and to identify characteristics related to the overall survival status before treatment and within 15 years after treatment start from a cohort of 300 patients with a metastatic breast cancer treated in the institution. TRIAL REGISTRATION: ClinicalTrials.gov identifier (NCT number): NCT03958136 . Registration 21st of May, 2019; retrospectively registered.

Optimization of reconstruction and quantification of motion-corrected coronary PET-CT.

BACKGROUND: Coronary PET shows promise in the detection of high-risk atherosclerosis, but there remains a need to optimize imaging and reconstruction techniques. We investigated the impact of reconstruction parameters and cardiac motion-correction in 18F Sodium Fluoride (18F-NaF) PET. METHODS: Twenty-two patients underwent 18F-NaF PET within 22 days of an acute coronary syndrome. Optimal reconstruction parameters were determined in a subgroup of six patients. Motion-correction was performed on ECG-gated data of all patients with optimal reconstruction. Tracer uptake was quantified in culprit and reference lesions by computing signal-to-noise ratio (SNR) in diastolic, summed, and motion-corrected images. RESULTS: Reconstruction using 24 subsets, 4 iterations, point-spread-function modelling, time of flight, and 5-mm post-filtering provided the highest median SNR (31.5) compared to 4 iterations 0-mm (22.5), 8 iterations 0-mm (21.1), and 8 iterations 5-mm (25.6; all P < .05). Motion-correction improved SNR of culprit lesions (n = 33) (24.5[19.9-31.5]) compared to diastolic (15.7[12.4-18.1]; P < .001) and summed data (22.1[18.9-29.2]; P < .001). Motion-correction increased the SNR difference between culprit and reference lesions (10.9[6.3-12.6]) compared to diastolic (6.2[3.6-10.3]; P = .001) and summed data (7.1 [4.8-11.6]; P = .001). CONCLUSIONS: The number of iterations and extent of post-filtering has marked effects on coronary 18F-NaF PET quantification. Cardiac motion-correction improves discrimination between culprit and reference lesions.

Automatic determination of cardiovascular risk by CT attenuation correction maps in Rb-82 PET/CT.

BACKGROUND: We investigated fully automatic coronary artery calcium (CAC) scoring and cardiovascular disease (CVD) risk categorization from CT attenuation correction (CTAC) acquired at rest and stress during cardiac PET/CT and compared it with manual annotations in CTAC and with dedicated calcium scoring CT (CSCT). METHODS AND RESULTS: We included 133 consecutive patients undergoing myocardial perfusion 82Rb PET/CT with the acquisition of low-dose CTAC at rest and stress. Additionally, a dedicated CSCT was performed for all patients. Manual CAC annotations in CTAC and CSCT provided the reference standard. In CTAC, CAC was scored automatically using a previously developed machine learning algorithm. Patients were assigned to a CVD risk category based on their Agatston score (0, 1-10, 11-100, 101-400, >400). Agreement in CVD risk categorization between manual and automatic scoring in CTAC at rest and stress resulted in Cohen's linearly weighted κ of 0.85 and 0.89, respectively. The agreement between CSCT and CTAC at rest resulted in κ of 0.82 and 0.74, using manual and automatic scoring, respectively. For CTAC at stress, these were 0.79 and 0.70, respectively. CONCLUSION: Automatic CAC scoring from CTAC PET/CT may allow routine CVD risk assessment from the CTAC component of PET/CT without any additional radiation dose or scan time.

Erratum to: Automatic determination of cardiovascular risk by CT attenuation correction maps in Rb-82 PET/CT.

Regrettably an error was introduced in Table 3 during the article's production. The very first cell (row: Very low 0; column: Very low) should read '12' and not '21' as originally published.

Enhancing Cardiac PET by Motion Correction Techniques.

PURPOSE OF REVIEW: Cardiac positron emission tomography (PET) images often contain errors due to cardiac, respiratory, and patient motion during relatively long image acquisition. Advanced motion compensation techniques may improve PET spatial resolution, eliminate potential artifacts, and ultimately improve the research and clinical capabilities of PET. RECENT FINDINGS: Combined cardiac and respiratory gating has only recently been implemented in clinical PET systems. Considering that the gated image bins contain much lower counts than the original PET data, they need to be summed after correcting for motion, forming motion-corrected, high-count image volume. Furthermore, automated image registration techniques can be used to correct for motion between CT attenuation scan and PET acquisition. While motion correction methods are not yet widely used in clinical practice, approaches including dual-gated non-rigid motion correction and the incorporation of motion correction information into the reconstruction process have the potential to markedly improve cardiac PET imaging.

Quantitation of left ventricular ejection fraction reserve from early gated regadenoson stress Tc-99m high-efficiency SPECT.

BACKGROUND: Ejection fraction (EF) reserve has been found to be a useful adjunct for identifying high risk coronary artery disease in cardiac positron emission tomography (PET). We aimed to evaluate EF reserve obtained from technetium-99m sestamibi (Tc-99m) high-efficiency (HE) SPECT. METHODS: Fifty patients (mean age 69 years) undergoing regadenoson same-day rest (8-11 mCi)/stress (32-42 mCi) Tc-99m gated HE SPECT were enrolled. Stress imaging was started 1 minute after sequential intravenous regadenoson .4 mg and Tc-99m injections, and was composed of five 2 minutes supine gated acquisitions followed by two 4 minutes supine and upright images. Ischemic total perfusion deficit (ITPD) ≥5 % was considered as significant ischemia. RESULTS: Significantly lower mean EF reserve was obtained in the 5th and 9th minute after regadenoson bolus in patients with significant ischemia vs patients without (5th minute: -4.2 ± 4.6% vs 1.3 ± 6.6%, P = .006; 9th minute: -2.7 ± 4.8% vs 2.0 ± 6.6%, P = .03). CONCLUSIONS: Negative EF reserve obtained between 5th and 9th minutes of regadenoson stress demonstrated best concordance with significant ischemia and may be a promising tool for detection of transient ischemic functional changes with Tc-99m HE-SPECT.

Learn2Reg: Comprehensive Multi-Task Medical Image Registration Challenge, Dataset and Evaluation in the Era of Deep Learning.

Image registration is a fundamental medical image analysis task, and a wide variety of approaches have been proposed. However, only a few studies have comprehensively compared medical image registration approaches on a wide range of clinically relevant tasks. This limits the development of registration methods, the adoption of research advances into practice, and a fair benchmark across competing approaches. The Learn2Reg challenge addresses these limitations by providing a multi-task medical image registration data set for comprehensive characterisation of deformable registration algorithms. A continuous evaluation will be possible at https://learn2reg.grand-challenge.org. Learn2Reg covers a wide range of anatomies (brain, abdomen, and thorax), modalities (ultrasound, CT, MR), availability of annotations, as well as intra- and inter-patient registration evaluation. We established an easily accessible framework for training and validation of 3D registration methods, which enabled the compilation of results of over 65 individual method submissions from more than 20 unique teams. We used a complementary set of metrics, including robustness, accuracy, plausibility, and runtime, enabling unique insight into the current state-of-the-art of medical image registration. This paper describes datasets, tasks, evaluation methods and results of the challenge, as well as results of further analysis of transferability to new datasets, the importance of label supervision, and resulting bias. While no single approach worked best across all tasks, many methodological aspects could be identified that push the performance of medical image registration to new state-of-the-art performance. Furthermore, we demystified the common belief that conventional registration methods have to be much slower than deep-learning-based methods.

Deformable image registration with deep network priors: a study on longitudinal PET images.

Objective.This paper proposes a novel approach for the longitudinal registration of PET imaging acquired for the monitoring of patients with metastatic breast cancer. Unlike with other image analysis tasks, the use of deep learning (DL) has not significantly improved the performance of image registration. With this work, we propose a new registration approach to bridge the performance gap between conventional and DL-based methods: medical image registration method regularized by architecture (MIRRBA).Approach.MIRRBAis a subject-specific deformable registration method which relies on a deep pyramidal architecture to parametrize the deformation field. Diverging from the usual deep-learning paradigms,MIRRBAdoes not require a learning database, but only a pair of images to be registered that is used to optimize the network's parameters. We appliedMIRRBAon a private dataset of 110 whole-body PET images of patients with metastatic breast cancer. We used different architecture configurations to produce the deformation field and studied the results obtained. We also compared our method to several standard registration approaches: two conventional iterative registration methods (ANTs and Elastix) and two supervised DL-based models (LapIRN and Voxelmorph). Registration accuracy was evaluated using the Dice score, the target registration error, the average Hausdorff distance and the detection rate, while the realism of the registration obtained was evaluated using Jacobian's determinant. The ability of the different methods to shrink disappearing lesions was also computed with the disappearing rate.Main results.MIRRBA significantly improved all metrics when compared to DL-based approaches. The organ and lesion Dice scores of Voxelmorph improved by 6% and 52% respectively, while the ones of LapIRN increased by 5% and 65%. Regarding conventional approaches, MIRRBA presented comparable results showing the feasibility of our method.Significance.In this paper, we also demonstrate the regularizing power of deep architectures and present new elements to understand the role of the architecture in DL methods used for registration.

Influence of inputs for bone lesion segmentation in longitudinal 18F-FDG PET/CT imaging studies.

In metastatic breast cancer, bone metastases are prevalent and associated with multiple complications. Assessing their response to treatment is therefore crucial. Most deep learning methods segment or detect lesions on a single acquisition while only a few focus on longitudinal studies. In this work, 45 patients with baseline (BL) and follow-up (FU) images recruited in the context of the EPICUREseinmeta study were analyzed. The aim was to determine if a network trained for a particular timepoint can generalize well to another one, and to explore different improvement strategies. Four networks based on the same 3D U-Net framework to segment bone lesions on BL and FU images were trained with different strategies and compared. These four networks were trained 1) only with BL images 2) only with FU images 3) with both BL and FU images 4) only with FU images but with BL images and bone lesion segmentations registered as input channels. With the obtained segmentations, we computed the PET Bone Index (PBI) which assesses the bone metastases burden of patients and we analyzed its potential for treatment response evaluation. Dice scores of 0.53, 0.55, 0.59 and 0.62 were respectively obtained on FU acquisitions. The under-performance of the first and third networks may be explained by the lower SUV uptake due to treatment response in FU images compared to BL images. The fourth network gives better results than the second network showing that the addition of BL PET images and bone lesion segmentations as prior knowledge has its importance. With an AUC of 0.86, the difference of PBI between two acquisitions could be used to assess treatment response. Clinical relevance- To assess the response to treatment of bone metastases, it is crucial to detect and segment them on several acquisitions from a same patient. We proposed a completely automatic method to detect and segment these metastases on longitudinal 18F-FDG PET/CT images in the context of metastatic breast cancer. We also proposed an automatic PBI to quantitatively assess the evolution of the bone metastases burden of patient and to automatically evaluate their response to treatment.

Automatic Segmentation of Metastatic Breast Cancer Lesions on 18F-FDG PET/CT Longitudinal Acquisitions for Treatment Response Assessment.

Metastatic breast cancer patients receive lifelong medication and are regularly monitored for disease progression. The aim of this work was to (1) propose networks to segment breast cancer metastatic lesions on longitudinal whole-body PET/CT and (2) extract imaging biomarkers from the segmentations and evaluate their potential to determine treatment response. Baseline and follow-up PET/CT images of 60 patients from the EPICUREseinmeta study were used to train two deep-learning models to segment breast cancer metastatic lesions: One for baseline images and one for follow-up images. From the automatic segmentations, four imaging biomarkers were computed and evaluated: SULpeak, Total Lesion Glycolysis (TLG), PET Bone Index (PBI) and PET Liver Index (PLI). The first network obtained a mean Dice score of 0.66 on baseline acquisitions. The second network obtained a mean Dice score of 0.58 on follow-up acquisitions. SULpeak, with a 32% decrease between baseline and follow-up, was the biomarker best able to assess patients' response (sensitivity 87%, specificity 87%), followed by TLG (43% decrease, sensitivity 73%, specificity 81%) and PBI (8% decrease, sensitivity 69%, specificity 69%). Our networks constitute promising tools for the automatic segmentation of lesions in patients with metastatic breast cancer allowing treatment response assessment with several biomarkers.

Deep learning approaches for bone and bone lesion segmentation on 18FDG PET/CT imaging in the context of metastatic breast cancer.

18FDG PET/CT imaging is commonly used in diagnosis and follow-up of metastatic breast cancer, but its quantitative analysis is complicated by the number and location heterogeneity of metastatic lesions. Considering that bones are the most common location among metastatic sites, this work aims to compare different approaches to segment the bones and bone metastatic lesions in breast cancer.Two deep learning methods based on U-Net were developed and trained to segment either both bones and bone lesions or bone lesions alone on PET/CT images. These methods were cross-validated on 24 patients from the prospective EPICUREseinmeta metastatic breast cancer study and were evaluated using recall and precision to measure lesion detection, as well as the Dice score to assess bones and bone lesions segmentation accuracy.Results show that taking into account bone information in the training process allows to improve the precision of the lesions detection as well as the Dice score of the segmented lesions. Moreover, using the obtained bone and bone lesion masks, we were able to compute a PET bone index (PBI) inspired by the recognized Bone Scan Index (BSI). This automatically computed PBI globally agrees with the one calculated from ground truth delineations.Clinical relevance- We propose a completely automatic deep learning based method to detect and segment bones and bone lesions on 18FDG PET/CT in the context of metastatic breast cancer. We also introduce an automatic PET bone index which could be incorporated in the monitoring and decision process.

Combining Superpixels and Deep Learning Approaches to Segment Active Organs in Metastatic Breast Cancer PET Images.

Semi-automatic measurements are performed on 18FDG PET-CT images to monitor the evolution of metastatic sites in the clinical follow-up of metastatic breast cancer patients. Apart from being time-consuming and prone to subjective approximation, semi-automatic tools cannot make the difference between cancerous regions and active organs, presenting a high 18FDG uptake.In this work, we combine a deep learning-based approach with a superpixel segmentation method to segment the main active organs (brain, heart, bladder) from full-body PET images. In particular, we integrate a superpixel SLIC algorithm at different levels of a convolutional network. Results are compared with a deep learning segmentation network alone. The methods are cross-validated on full-body PET images of 36 patients and tested on the acquisitions of 24 patients from a different study center, in the context of the ongoing EPICUREseinmeta study. The similarity between the manually defined organ masks and the results is evaluated with the Dice score. Moreover, the amount of false positives is evaluated through the positive predictive value (PPV).According to the computed Dice scores, all approaches allow to accurately segment the target organs. However, the networks integrating superpixels are better suited to transfer knowledge across datasets acquired on multiple sites (domain adaptation) and are less likely to segment structures outside of the target organs, according to the PPV.Hence, combining deep learning with superpixels allows to segment organs presenting a high 18FDG uptake on PET images without selecting cancerous lesion, and thus improves the precision of the semi-automatic tools monitoring the evolution of breast cancer metastasis.Clinical relevance- We demonstrate the utility of combining deep learning and superpixel segmentation methods to accurately find the contours of active organs from metastatic breast cancer images, to different dataset distributions.

Molecular Imaging of Vulnerable Coronary Plaque: A Pathophysiologic Perspective.

Atherothrombotic events in coronary arteries are most often due to rupture of unstable plaque resulting in myocardial infarction. Radiolabeled molecular imaging tracers directed toward cellular targets that are unique to unstable plaque can serve as a powerful tool for identifying high-risk patients and for assessing the potential of new therapeutic approaches. Two commonly available radiopharmaceuticals-18F-FDG and 18F-NaF-have been used in clinical research for imaging coronary artery plaque, and ongoing clinical studies are testing whether there is an association between 18F-NaF uptake and future atherothrombotic events. Other, less available, tracers that target macrophages, endothelial cells, and apoptotic cells have also been tested in small groups of patients. Adoption of molecular imaging of coronary plaque into clinical practice will depend on overcoming major hurdles, ultimately including evidence that the detection of unstable plaque can change patient management and improve outcomes.

Motion-Corrected Imaging of the Aortic Valve with 18F-NaF PET/CT and PET/MRI: A Feasibility Study.

We investigated whether motion correction of gated 18F-fluoride PET/CT and PET/MRI of the aortic valve could improve PET quantitation and image quality. Methods: A diffeomorphic, mass-preserving, anatomy-guided registration algorithm was used to align the PET images from 4 cardiac gates, preserving all counts, and apply them to the PET/MRI and PET/CT data of 6 patients with aortic stenosis. Measured signal-to-noise ratios (SNRs) and target-to-background ratios (TBRs) were compared with the standard method of using only the diastolic gate. Results: High-intensity aortic valve 18F-fluoride uptake was observed in all patients. After motion correction, SNR and TBR increased compared with the median diastolic gate (SNR, 51.61 vs. 21.0; TBR, 2.85 vs. 2.22) and the median summed data (SNR, 51.61 vs. 34.10; TBR, 2.85 vs. 1.95) (P = 0.028 for all). Furthermore, noise decreased from 0.105 (median, diastolic) to 0.042 (median, motion-corrected) (P = 0.028). Conclusion: Motion correction of hybrid 18F-fluoride PET markedly improves SNR, resulting in improved image quality.

Automatic Valve Plane Localization in Myocardial Perfusion SPECT/CT by Machine Learning: Anatomic and Clinical Validation.

Precise definition of the mitral valve plane (VP) during segmentation of the left ventricle for SPECT myocardial perfusion imaging (MPI) quantification often requires manual adjustment, which affects the quantification of perfusion. We developed a machine learning approach using support vector machines (SVM) for automatic VP placement. Methods: A total of 392 consecutive patients undergoing 99mTc-tetrofosmin stress (5 min; mean ± SD, 350 ± 54 MBq) and rest (5 min; 1,024 ± 153 MBq) fast SPECT MPI attenuation corrected (AC) by CT and same-day coronary CT angiography were studied; included in the 392 patients were 48 patients who underwent invasive coronary angiography and had no known coronary artery disease. The left ventricle was segmented with standard clinical software (quantitative perfusion SPECT) by 2 experts, adjusting the VP if needed. Two-class SVM models were computed from the expert placements with 10-fold cross validation to separate the patients used for training and those used for validation. SVM probability estimates were used to compute the best VP position. Automatic VP localizations on AC and non-AC images were compared with expert placement on coronary CT angiography. Stress and rest total perfusion deficits and detection of per-vessel obstructive stenosis by invasive coronary angiography were also compared. Results: Bland-Altman 95% confidence intervals (CIs) for VP localization by SVM and experts for AC stress images (bias, 1; 95% CI, -5 to 7 mm) and AC rest images (bias, 1; 95% CI, -7 to 10 mm) were narrower than interexpert 95% CIs for AC stress images (bias, 0; 95% CI, -8 to 8 mm) and AC rest images (bias, 0; 95% CI, -10 to 10 mm) (P < 0.01). Bland-Altman 95% CIs for VP localization by SVM and experts for non-AC stress images (bias, 1; 95% CI, -4 to 6 mm) and non-AC rest images (bias, 2; 95% CI, -7 to 10 mm) were similar to interexpert 95% CIs for non-AC stress images (bias, 0; 95% CI, -6 to 5 mm) and non-AC rest images (bias, -1; 95% CI, -9 to 7 mm) (P was not significant [NS]). For regional detection of obstructive stenosis, ischemic total perfusion deficit areas under the receiver operating characteristic curve for the 2 experts (AUC, 0.79 [95% CI, 0.7-0.87]; AUC, 0.81 [95% CI, 0.73-0.89]) and the SVM (0.82 [0.74-0.9]) for AC data were the same (P = NS) and were higher than those for the unadjusted VP (0.63 [0.53-0.73]) (P < 0.01). Similarly, for non-AC data, areas under the receiver operating characteristic curve for the experts (AUC, 0.77 [95% CI, 0.69-0.89]; AUC, 0.8 [95% CI, 0.72-0.88]) and the SVM (0.79 [0.71-0.87]) were the same (P = NS) and were higher than those for the unadjusted VP (0.65 [0.56-0.75]) (P < 0.01). Conclusion: Machine learning with SVM allows automatic and accurate VP localization, decreasing user dependence in SPECT MPI quantification.

Normal Databases for the Relative Quantification of Myocardial Perfusion.

PURPOSE OF REVIEW: Myocardial perfusion imaging (MPI) with SPECT is performed clinically worldwide to detect and monitor coronary artery disease (CAD). MPI allows an objective quantification of myocardial perfusion at stress and rest. This established technique relies on normal databases to compare patient scans against reference normal limits. In this review, we aim to introduce the process of MPI quantification with normal databases and describe the associated perfusion quantitative measures that are used. RECENT FINDINGS: New equipment and new software reconstruction algorithms have been introduced which require the development of new normal limits. The appearance and regional count variations of normal MPI scan may differ between these new scanners and standard Anger cameras. Therefore, these new systems may require the determination of new normal limits to achieve optimal accuracy in relative myocardial perfusion quantification. Accurate diagnostic and prognostic results rivaling those obtained by expert readers can be obtained by this widely used technique. SUMMARY: Throughout this review, we emphasize the importance of the different normal databases and the need for specific databases relative to distinct imaging procedures. use of appropriate normal limits allows optimal quantification of MPI by taking into account subtle image differences due to the hardware and software used, and the population studied.

Epicardial adipose tissue volume but not density is an independent predictor for myocardial ischemia.

BACKGROUND: Epicardial adipose tissue (EAT) volume is associated with plaque formation and cardiovascular event risk, its density may reflect tissue composition and metabolic activity. OBJECTIVES: Global and regional associations between EAT volume and density, ischemia and coronary calcium were investigated using a novel automatic quantitative measurement software. METHODS: 71 patients with an intermediate pre-test probability for coronary artery disease and inducible ischemia by SPECT were matched to two same-gender controls (total of 213 patients, 90% male, age 60 ± 10 years). Non-contrast CT for assessment of EAT volume, density (in Hounsfield Unit [HU]) and coronary calcium score (CCS) was performed. RESULTS: Global EAT volume was significantly increased in ischemic patients compared to controls (96 ± 49 vs. 82 ± 36 cm(3), p = 0.04), density showed no significant difference (-75.6 ± 4.3 vs. -75.1 ± 4.1HU, p = 0.63). EAT volume and density differed significantly between coronary territories (LAD: 37 ± 18 cm(3), -77.8 ± 4.5HU; LCx: 16 ± 9 cm(3), -73.9 ± 4.1HU; RCA: 36 ± 17 cm(3), -71.7 ± 4.8HU, p < 0.001). For regional ischemia, only LCx territory showed a significantly higher EAT volume (18 ± 8 vs. 16 ± 9 cm(3), p = 0.048). Multivariable logistic regression revealed a significant association with ischemia for EAT volume (OR 2.09 (1.0; 4.3), p = 0.049) and CCS (OR 1.43 (1.1; 1.9), p = 0.006). EAT volume significantly improved discrimination of ischemia over CCS (Integrated Discrimination Improvement: 3.5%, 95%CI: 1.1-6.1%, p = 0.004). Hypertension was the only risk factor significantly influencing EAT volume and density (98 ± 48 vs. 78 ± 31 cm(3), p = 0.002, -76.0 ± 4.1 vs. -74.5 ± 4.1 HU, p = 0.01). CONCLUSIONS: EAT volume is associated with myocardial ischemia and improves the discriminative power for independent ischemia prediction over CCS. In hypertensive patients, EAT is characterized by lower density and higher volumes.

Demons versus Level-Set motion registration for coronary 18F-sodium fluoride PET.

Ruptured coronary atherosclerotic plaques commonly cause acute myocardial infarction. It has been recently shown that active microcalcification in the coronary arteries, one of the features that characterizes vulnerable plaques at risk of rupture, can be imaged using cardiac gated 18F-sodium fluoride (18F-NaF) PET. We have shown in previous work that a motion correction technique applied to cardiac-gated 18F-NaF PET images can enhance image quality and improve uptake estimates. In this study, we further investigated the applicability of different algorithms for registration of the coronary artery PET images. In particular, we aimed to compare demons vs. level-set nonlinear registration techniques applied for the correction of cardiac motion in coronary 18F-NaF PET. To this end, fifteen patients underwent 18F-NaF PET and prospective coronary CT angiography (CCTA). PET data were reconstructed in 10 ECG gated bins; subsequently these gated bins were registered using demons and level-set methods guided by the extracted coronary arteries from CCTA, to eliminate the effect of cardiac motion on PET images. Noise levels, target-to-background ratios (TBR) and global motion were compared to assess image quality. Compared to the reference standard of using only diastolic PET image (25% of the counts from PET acquisition), cardiac motion registration using either level-set or demons techniques almost halved image noise due to the use of counts from the full PET acquisition and increased TBR difference between 18F-NaF positive and negative lesions. The demons method produces smoother deformation fields, exhibiting no singularities (which reflects how physically plausible the registration deformation is), as compared to the level-set method, which presents between 4 and 8% of singularities, depending on the coronary artery considered. In conclusion, the demons method produces smoother motion fields as compared to the level-set method, with a motion that is physiologically plausible. Therefore, level-set technique will likely require additional post-processing steps. On the other hand, the observed TBR increases were the highest for the level-set technique. Further investigations of the optimal registration technique of this novel coronary PET imaging technique are warranted.