Positron Emission Tomography Data Research Articles

The incremental value of PET perfusion imaging over coronary CT angiography in predicting outcome. A study using machine learning

Abstract Funding Acknowledgements Type of funding sources: Public Institution(s). Main funding source(s): Academy of Finland, Turku University Hospital Background Coronary computed tomography angiography (CTA) and myocardial perfusion imaging (MPI) are powerful non-invasive tools to evaluate the patients with suspected coronary artery disease (CAD). Purpose The goal of this study was to evaluate the incremental value of these imaging methods in predicting short- and long-term cardiac events using machine learning (ML) approaches. Methods 2411 patients with clinically suspected CAD underwent coronary CTA and subsequent positron emission tomography (PET) MPI. Following our local routine, if obstructive CAD cannot be ruled-out by coronary CTA, PET MPI using 15O-water is performed. The incremental prognostic value of PET imaging was tested using several ML models of which XGBoost models consistently outperformed others and were chosen for further analyses. XGBoost models were trained by using clinical data from medical records and coronary imaging findings: one set of models used all the available variables, while a second set of models used only clinical and CTA-based variables. Differences in the performances of the models were then used to assess the incremental value of PET perfusion variables in outcome prediction. Results After the removal of incomplete data entries, data from 2284 patients was retained for further analysis. During 8-year follow-up period 210 patients had a major cardiac event (these endpoints correspond to 59 myocardial infarctions, 35 unstable angina pectoris, and 116 deaths). The PET perfusion imaging data improved the predictive power of CTA during the first 4 years of observation time. After that, no significant difference in the predictive power was observed between the considered sets of XGBoost models, which either included or did not include PET perfusion data in the input variables. The highest area under the receiver operating characteristic curve (AUC) was at the observation time of 2 years (0.81, 95% CI 0.805–0.823) when PET data were included. The corresponding AUC when PET data were not included was at the observation time of 2 years (0.79, 95% CI 0.785–0.802). Conclusions Based on ML approach PET perfusion imaging improves the power in predicting cardiac events over anatomical CTA imaging for the first 4 years. The results illustrate the differences and complementary nature of anatomic and perfusion information in predicting outcome of patients with suspected CAD.

Comparison of automated quantification of amyloid deposition between PMOD and Heuron

Several programs are widely used for clinical and research purposes to automatically quantify the degree of amyloid deposition in the brain using positron emission tomography (PET) images. Given that very few studies have investigated the use of Heuron, a PET image quantification software approved for clinical use, this study aimed to compare amyloid deposition values quantified from 18F-flutemetamol PET images using PMOD and Heuron. Amyloid PET data obtained from 408 patients were analysed using each quantitative program; moreover, the standardized uptake value ratios (SUVRs) of target areas were obtained by dividing the standardized uptake value (SUV) of the target region by the SUV of cerebellar grey matter as a reference. Compared with PMOD, Heuron yielded significantly higher SUVRs for all target areas (paired sample t-test, p < 0.001), except for the PC/PCC (p = 0.986). However, the Bland–Altman plot analysis indicated that the two quantitative methods may be used interchangeably. Moreover, receiver operating characteristic curve analysis revealed no significant between-method difference in the performance of the SUVRs in evaluating the visual positivity of amyloid deposits (p = 0.948). In conclusion, Heuron and PMOD have comparable performance in quantifying the degree of amyloid deposits in PET images.

Dynomics: A Novel and Promising Approach for Improved Breast Cancer Prognosis Prediction.

Traditional imaging techniques for breast cancer (BC) diagnosis and prediction, such as X-rays and magnetic resonance imaging (MRI), demonstrate varying sensitivity and specificity due to clinical and technological factors. Consequently, positron emission tomography (PET), capable of detecting abnormal metabolic activity, has emerged as a more effective tool, providing critical quantitative and qualitative tumor-related metabolic information. This study leverages a public clinical dataset of dynamic 18F-Fluorothymidine (FLT) PET scans from BC patients, extending conventional static radiomics methods to the time domain-termed as 'Dynomics'. Radiomic features were extracted from both static and dynamic PET images on lesion and reference tissue masks. The extracted features were used to train an XGBoost model for classifying tumor versus reference tissue and complete versus partial responders to neoadjuvant chemotherapy. The results underscored the superiority of dynamic and static radiomics over standard PET imaging, achieving accuracy of 94% in tumor tissue classification. Notably, in predicting BC prognosis, dynomics delivered the highest performance, achieving accuracy of 86%, thereby outperforming both static radiomics and standard PET data. This study illustrates the enhanced clinical utility of dynomics in yielding more precise and reliable information for BC diagnosis and prognosis, paving the way for improved treatment strategies.

Dopaminergic Dysfunction Is More Symmetric in Dementia with Lewy Bodies Compared to Parkinson's Disease.

The α-syn Origin site and Connectome model (SOC) proposes that α-synucleinopathies can be divided into two categories: the asymmetrical brain-first, and more symmetrical body-first Lewy body disease. We have hypothesized that most patients with dementia with Lewy bodies (DLB) belong to the body-first subtype, whereas patients with Parkinson's disease (PD) more often belong to the brain-first subtype. To compare asymmetry of striatal dopaminergic dysfunction in DLB and PD patients using [18F]-FE-PE2I positron emission tomography (PET). We analyzed [18F]-FE-PE2I PET data from 29 DLB patients and 76 PD patients who were identified retrospectively during a 5-year period at Dept. of Neurology, Aarhus University Hospital. Additionally, imaging data from 34 healthy controls was used for age-correction and visual comparison. PD patients showed significantly more asymmetry in specific binding ratios between the most and least affected putamen (p < 0.0001) and caudate (p = 0.003) compared to DLB patients. PD patients also had more severe degeneration in the putamen compared to the caudate in comparison to DLB patients (p < 0.0001) who had a more universal pattern of striatal degeneration. Patients with DLB show significantly more symmetric striatal degeneration on average compared to PD patients. These results support the hypothesis that DLB patients may be more likely to conform to the body-first subtype characterized by a symmetrical spread of pathology, whereas PD patients may be more likely to conform to the brain-first subtype with more lateralized initial propagation of pathology.

Explainable Deep-Learning-Based Diagnosis of Alzheimer’s Disease Using Multimodal Input Fusion of PET and MRI Images

PurposeAlzheimer’s disease (AD) is a progressive, incurable human brain illness that impairs reasoning and retention as well as recall. Detecting AD in its preliminary stages before clinical manifestations is crucial for timely treatment. Magnetic Resonance Imaging (MRI) provides valuable insights into brain abnormalities by measuring the decrease in brain volume expressly in the mesial temporal cortex and other regions of the brain, while Positron Emission Tomography (PET) measures the decrease of glucose concentration in the temporoparietal association cortex. When these data are combined, the performance of AD diagnostic methods could be improved. However, these data are heterogeneous and there is a need for an effective model that will harness the information from both data for the accurate prediction of AD.MethodsTo this end, we present a novel heuristic early feature fusion framework that performs the concatenation of PET and MRI images, while a modified Resnet18 deep learning architecture is trained simultaneously on the two datasets. The innovative 3-in-channel approach is used to learn the most descriptive features of fused PET and MRI images for effective binary classification of AD.ResultsThe experimental results show that the proposed model achieved a classification accuracy of 73.90% on the ADNI database. Then, we provide an Explainable Artificial Intelligence (XAI) model, allowing us to explain the results.ConclusionOur proposed model could learn latent representations of multimodal data even in the presence of heterogeneity data; hence, the proposed model partially solved the issue with the heterogeneity of the MRI and PET data.

PET‐validated EEG‐machine learning algorithm predicts brain amyloid pathology in pre‐dementia Alzheimer’s disease

AbstractBackgroundCurrently positron emission tomography (PET) is used as the initial or sole biomarker of β‐amyloid (Aβ) brain pathology, which may inhibit Alzheimer’s disease (AD) drug development and clinical use due to cost, access, and tolerability. Machine learning (ML)‐based EEG biomarkers may address these challenges. Previous studies have confirmed their ability to accurately discriminate between normal, mild cognitive impairment (MCI) and Alzheimer’s dementia. However, few quantitative EEG (QEEG) biomarkers have been validated with Aβ PET. We developed a QEEG‐ML algorithm to predict brain Aβ pathology among subjective cognitive decline (SCD) and MCI patients, and validated it using Aβ PET.MethodEEG (19‐channel, eye‐closed, resting‐state) and Aβ PET data were collected from 311 subjects with SCD (Aβ+: N = 36, Aβ‐: N = 160) or MCI (Aβ+: N = 54, Aβ‐: N = 61). We randomly excluded data for 76 subjects (SCD, Aβ+: N = 7, Aβ‐: N = 28; MCI, Aβ+: N = 6, Aβ‐: N = 7) for use in subsequent verification. QEEG absolute power, relative power, power ratio, and connectivity between channels (iCoherence) comprised the input features, from which the most relevant predictive features were identified using several methods (Random Forest Importance (GBM, XGB), ElasticNet, Whitney‐Mann). We then trained four ML algorithms (SVM, Logistic, KNN, Naive Bayes, Random Forest(GBM/XGB)) using each relevant feature set, yielding 24 models (4 sets * 6 algorithms). The 76 validation data sets were input into each model to compare their performance.ResultThe best‐performing model (random forest importance * SVM) showed 82.9% accuracy, 90.9% sensitivity, 76.7% specificity, and 75% positive predictive value in discriminating Aβ+ from Aβ‐, regardless of MCI/SCD. In MCI alone, the model showed 82.1% accuracy, 90.0% sensitivity, 78.9% specificity, and 81.8% positive predictive value. In SCD alone, it showed, 81.1% accuracy, 92.3% sensitivity, 75% specificity, and 66.7% positive predictive value.ConclusionThese findings suggest that our novel ML‐based QEEG biomarker can accurately predict the presence of brain Aβ plaque. Additional benefits of such a biomarker include reduced expense, wide availability, and high‐throughput screening and response monitoring. Future studies will assess utility as primary AD screens, adjunctive use with PET, and as a support in clinical rationales for Aβ PET and treatment choice in AD.

Peripheral immune cell imbalance is associated with cortical beta-amyloid deposition and longitudinal cognitive decline

Neuroinflammation is believed to be a key process in Alzheimer’s disease (AD) pathogenesis. Recently, the neutrophil-to-lymphocyte (NLR) and lymphocyte-to-monocyte ratios (LMR) have been proposed to be useful peripheral markers of inflammation. However, it is unclear how these inflammatory ratios relate to AD pathology, such as β-amyloid (Aβ) plaques and tau tangles. Using 18F-florbetapir and 18F-flortaucipir positron emission tomography (PET), we sought to determine how the NLR and LMR are associated with AD pathology both cross-sectionally and longitudinally. We further evaluated associations between the NLR and LMR and longitudinal cognitive decline. Using data from the Alzheimer’s Disease Neuroimaging Initiative, we analyzed blood, PET, and cognitive data from 1544 subjects—405 cognitively normal, 838 with mild cognitive impairment (MCI), and 301 with AD. Associations between the NLR and LMR and Aβ and tau on PET were assessed using ordinary least-squares and mixed-effects regression models, while adjusting for age, sex, years of education, and apolipoprotein E ε2 or ε4 carrier status. Associations between the NLR and LMR and cognitive function, as measured by the AD Assessment Scale-Cognitive Subscale, 13-item version, were also assessed. MCI and AD subjects had higher NLR (p = 0.017, p < 0.001, respectively) and lower LMR (p = 0.013, p = 0.023). The NLR, but not the LMR, was significantly associated with Aβ (p = 0.028), suggesting that higher NLR was associated with greater Aβ deposition in the brain. Neither the NLR nor the LMR was associated with tau deposition (p > 0.05). A higher NLR was associated with greater longitudinal cognitive decline (p < 0.001). A higher ratio of peripheral neutrophils to lymphocytes, possibly reflecting an imbalance in innate versus adaptive immunity, is related to greater Aβ deposition and longitudinal cognitive decline. As the field moves toward blood-based biomarkers of AD, the altered balance of innate versus adaptive immunity could be a useful biomarker of underlying pathology and may also serve as a potential therapeutic target.

In vivo18F-DOPA PET imaging identifies a dopaminergic deficit in a rat model with a G51D α-synuclein mutation.

Parkinson's disease (PD) is a neurodegenerative condition with several major hallmarks, including loss of substantia nigra neurons, reduction in striatal dopaminergic function, and formation of α-synuclein-rich Lewy bodies. Mutations in SNCA, encoding for α-synuclein, are a known cause of familial PD, and the G51D mutation causes a particularly aggressive form of the condition. CRISPR/Cas9 technology was used to introduce the G51D mutation into the endogenous rat SNCA gene. SNCAG51D/+ and SNCAG51D/G51D rats were born in Mendelian ratios and did not exhibit any severe behavourial defects. L-3,4-dihydroxy-6-18F-fluorophenylalanine (18F-DOPA) positron emission tomography (PET) imaging was used to investigate this novel rat model. Wild-type (WT), SNCAG51D/+ and SNCAG51D/G51D rats were characterized over the course of ageing (5, 11, and 16 months old) using 18F-DOPA PET imaging and kinetic modelling. We measured the influx rate constant (Ki) and effective distribution volume ratio (EDVR) of 18F-DOPA in the striatum relative to the cerebellum in WT, SNCAG51D/+ and SNCAG51D/G51D rats. A significant reduction in EDVR was observed in SNCAG51D/G51D rats at 16 months of age indicative of increased dopamine turnover. Furthermore, we observed a significant asymmetry in EDVR between the left and right striatum in aged SNCAG51D/G51D rats. The increased and asymmetric dopamine turnover observed in the striatum of aged SNCAG51D/G51D rats reflects one aspect of prodromal PD, and suggests the presence of compensatory mechanisms. SNCAG51D rats represent a novel genetic model of PD, and kinetic modelling of 18F-DOPA PET data has identified a highly relevant early disease phenotype.

Time course of neuroinflammation after human stroke – a pilot study using co-registered PET and MRI

BackgroundMicroglial activation contributes to both inflammatory damage and repair in experimental ischemic stroke. However, because of the logistical challenges, there have been few clinical imaging studies directly describing inflammatory activation and its resolution after stroke. The purpose of our pilot study was to describe the spatio-temporal profile of brain inflammation after stroke using 18kD translocator protein (TSPO) positron emission tomography (PET) with magnetic resonance (MR) co-registration in the subacute and chronic stage after stroke.MethodsThree patients underwent magnetic resonance imaging (MRI) and PET scans with TSPO ligand [11C]PBR28 15 ± 3 and 90 ± 7 days after an ischaemic stroke. Regions of interest (ROI) were defined on MRI images and applied to the dynamic PET data to derive regional time-activity curves. Regional uptake was quantified as standardised uptake values (SUV) over 60 to 90 min post-injection. ROI analysis was applied to identify binding in the infarct, and in frontal, temporal, parietal, and occipital lobes and cerebellum excluding the infarcted area.ResultsThe mean age of participants was 56 ± 20.4 years and mean infarct volume was 17.9 ± 18.1 ml. [11C]PBR28 showed increased tracer signal in the infarcted area compared to non-infarcted areas of the brain in the subacute phase of stroke (Patient 1 SUV 1.81; Patient 2 SUV 1.15; Patient 3 SUV 1.64). [11C]PBR28 uptake returned to the level of non-infarcted areas at 90 days Patient 1 SUV 0.99; Patient 3 SUV 0.80). No additional upregulation was detected elsewhere at either time point.ConclusionsThe neuroinflammatory reaction after ischaemic stroke is limited in time and circumscribed in space suggesting that post-ischaemic inflammation is tightly controlled but regulatory mechanisms.

Results of R-CHOP and R-CHOP + interleukin-2 regimens in first-line therapy in patients with diffuse B-cell lymphoma

The study was made to evaluate the effect of interleukin-2 (IL-2) as part of the R-CHOP regimen on the rate of a complete metabolic response (CMR) using the data of interim positron emission tomography (PET/CT) and progression-free survival compared to the standard regimen in patients with diffuse B-cell lymphoma (DCLC). The data of 152 patients with biopsy-proven DCLC who were treated in the period 2015–2020 were included. Among them, 59 patients were included in the prospective group (R-CHOP + IL-2 in a total course dose of 5,000,000 IU). The control group consisting of 93 patients received standard R-CHOP therapy. PET/CT was performed after 4 courses of therapy, metabolic response was assessed using the Deauville scale, and Deauville 1-2 was classified as CMR. The rate of CMR in the R-CHOP+IL-2 group was 67.8 %, while in the control group it was 50.5 % (pχ² = 0.044). The 5-year progression-free survival (PFS) in the R-CHOP+IL-2 and R-CHOP groups was 80.7 and 64.5 %, respectively (p = 0.04). In the favorable and intermediate prognosis groups (IPI 0–3), PFS was not statistically significantly different depending on treatment. At high risk (IPI 4–5), the 5-year PFS in the R-CHOP + IL-2 and R-CHOP groups was 71.4 and 25.0 %, respectively (p = 0.02). Including IL-2 in the R-CHOP regimen in the first-line treatment of patients with DCLC increases the incidence of CMR according to 18-FDG PET/CT after 4 courses of chemoimmunotherapy and PFS in the high-risk group.

Triple modality image reconstruction of PET data using SPECT, PET, CT information increases lesion uptake in images of patients treated with radioembolization with ^{90}Y micro-spheres

PurposeNuclear medicine imaging modalities like computed tomography (CT), single photon emission CT (SPECT) and positron emission tomography (PET) are employed in the field of theranostics to estimate and plan the dose delivered to tumors and the surrounding tissues and to monitor the effect of the therapy. However, therapeutic radionuclides often provide poor images, which translate to inaccurate treatment planning and inadequate monitoring images. Multimodality information can be exploited in the reconstruction to enhance image quality. Triple modality PET/SPECT/CT scanners are particularly useful in this context due to the easier registration process between images. In this study, we propose to include PET, SPECT and CT information in the reconstruction of PET data. The method is applied to Yttrium-90 (^{90}Y) data.MethodsData from a NEMA phantom filled with ^{90}Y were used for validation. PET, SPECT and CT data from 10 patients treated with Selective Internal Radiation Therapy (SIRT) were used. Different combinations of prior images using the Hybrid kernelized expectation maximization were investigated in terms of VOI activity and noise suppression.ResultsOur results show that triple modality PET reconstruction provides significantly higher uptake when compared to the method used as standard in the hospital and OSEM. In particular, using CT-guided SPECT images, as guiding information in the PET reconstruction significantly increases uptake quantification on tumoral lesions.ConclusionThis work proposes the first triple modality reconstruction method and demonstrates up to 69% lesion uptake increase over standard methods with SIRT ^{90}Y patient data. Promising results are expected for other radionuclide combination used in theranostic applications using PET and SPECT.

Carimas: An Extensive Medical Imaging Data Processing Tool for Research.

Carimas is a multi-purpose medical imaging data processing tool, which can be used to visualize, analyze, and model different medical images in research. Originally, it was developed only for positron emission tomography data in 2009, but the use of this software has extended to many other tomography imaging modalities, such as computed tomography and magnetic resonance imaging. Carimas is especially well-suited for analysis of three- and four-dimensional image data and creating polar maps in modeling of cardiac perfusion. This article explores various parts of Carimas, including its key features, program structure, and application possibilities.

Diagnostic significance of MRI versus CT using identical PET data in patients with recurrent differentiated thyroid cancer: A PET/MRI study.

In this retrospective study we compared magnet resonance imaging (MRI) and computed tomography (CT) each combined with identical 2-deoxy-2-[18F] fluoro-D-glucose or 2-[18F] F-18 fluorodeoxyglucose (FDG) positron emission tomography (PET) data in patients with recurrent differentiated thyroid cancer (DTC). In total 42 patients with DTC were examined. All patients underwent FDG PET/MRI and CT, the latter originating from one of the following examinations: I-131 single photon emission computed tomography/CT (32/42), low dose FDG PET/CT (5/42) or diagnostic FDG PET/CT (5/42). Two readers assessed FDG PET/MRI as well as FDG PET/CT, with the latter CT coming from one of the above examinations performed at a maximum temporal interval of 5 days from PET/MRI. Local recurrence, cervical lymph node - and pulmonary metastases were assessed in a consensus read. Lesions rated with a high malignancy score (score 4 or 5) were further analyzed. Every malignant lesion was verified if it was identified by one of both or by both modalities. In 20 of 42 patients altogether 100 malignant lesions were present. In 11/20 patients in total 15 local recurrences (15 in MRI/ 9 in CT: 9 CT/MRI, 6 MRI only, 0 CT only; P = .04) were found with a statistically significant better performance of MRI. Regarding lymph node metastases, in total 13 lesions (12 in MRI/ 8 in CT: 7 CT/MRI, 5 MRI only, 1 CT only; P = .22) in 8/20 patients were found with no significant difference between both modalities. Furthermore, in 9/20 patients in total 72 lung lesions (40 in MRI/ 63 in CT: 31 CT/MRI, 9 MRI only, 32 CT only; P = .001) were found with a statistically significant better performance of CT. In 33/42 patients follow up was available and supported the observations. In patients with recurrent DTC, PET/MRI showed superiority compared to PET/CT in evaluation of the neck region. PET/MRI was inferior to PET/CT in evaluation of the lung. PET/MRI in combination with a low dose CT of the lung may thus represent the ideal staging tool in patients with recurrent DTC.

Operationalizing the centiloid scale for [18F]florbetapir PET studies on PET/MRI.

The Centiloid scale aims to harmonize amyloid beta (Aβ) positron emission tomography (PET) measures across different analysis methods. As Centiloids were created using PET/computerized tomography (CT) data and are influenced by scanner differences, we investigated the Centiloid transformation with data from Insight 46 acquired with PET/magnetic resonanceimaging (MRI). We transformed standardized uptake value ratios (SUVRs) from 432 florbetapir PET/MRI scans processed using whole cerebellum (WC) and white matter (WM) references, with and without partial volume correction. Gaussian-mixture-modelling-derived cutpoints for Aβ PET positivity were converted. The Centiloid cutpoint was 14.2 for WC SUVRs. The relationship between WM and WC uptake differed between the calibration and testing datasets, producing implausibly low WM-based Centiloids. Linear adjustment produced a WM-based cutpoint of 18.1. Transformation of PET/MRI florbetapir data to Centiloids is valid. However, further understanding of the effects of acquisition or biological factors on the transformation using a WM reference is needed. Centiloid conversion of amyloid beta positron emission tomography (PET) data aims to standardize results.Centiloid values can be influenced by differences in acquisition.We converted florbetapir PET/magnetic resonance imaging data from a large birth cohort.Whole cerebellum referenced values could be reliably transformed to Centiloids.White matter referenced values may be less generalizable between datasets.

Deep learning based registration for head motion correction in positron emission tomography as a strategy for improved image quantification

Objectives: Positron emission tomography (PET) is affected by various kinds of patient movement during a scan. Frame-by-frame image registration is one of the most practiced motion correction techniques. In recent years, deep learning has shown a remarkable ability to quickly and accurately register images once trained. This paper studies the feasibility of using a deep learning framework to correct 3D positron emission tomography image volumes for head motion in routine positron emission tomography imaging to improve quantification in motion impacted data.Materials and Methods: A neural network was trained with 3D positron emission tomography image volumes in an unsupervised manner to predict transformation parameters required to perform image registration. A multi-step convolutional neural network (CNN) was combined with a spatial transform layer. Pairs of target and source images were used as input to the network. To prepare the training dataset, a previously published TOF-PEPT algorithm was applied to automatically detect static frames where the patient remained in a relatively steady position and transitional frames where they underwent abrupt motion. A single image volume was reconstructed for each static frame. The image reconstructed from the first static frame served as the target image with images from subsequent static frames being used as source images. The trained neural network predicted transformation parameters that could be used to perform frame-by-frame image-based motion correction but also enabled raw listmode positron emission tomography data correction where individual line-of-responses were repositioned. Line profiles and ROIs were drawn across the reconstructed image volumes to compare performance and quantitative results between standard registration tools and the deep learning technique. Corrected volumes were further compared to motion free images quantitatively using Dice indices.Results: In total, one hundred 3D positron emission tomography image volumes were used to train the network. Cross-validation was carried out using a 4:1 ratio for the training and test data. A conventional algorithm for affine registration from the Advanced Normalization Tools (ANTs) software package served as a baseline. To evaluate the correction performance, the mean Dice index and standardized uptake value (SUV) were used. Application of the algorithm to clinical data showed good performance with respect to registration accuracy as well as processing time. The neural network yielded a mean Dice index of ∼0.87 which was similar to the advanced Normalization Tools algorithm and did so ∼3x faster using a multi-core CPU and ∼20x faster with a GPU. Standardized uptake value analysis showed that quantitative results were 30%–60% higher in the motion-corrected images, and the neural network performed better than or close to the advanced Normalization Tools.Conclusion: The aim of this work was to study the quantitative impact of using a data-driven deep learning motion correction technique for positron emission tomography data and assess its performance. The results showed the technique is capable of producing high quality registrations that compensate for patient motion that occurs during a scan and improve quantitative accuracy.

Optimization of the Algorithm for the Implementation of Point Spread Function in the 3D-OSEM Reconstruction Algorithm Based on the List-Mode Micro PET Data

Positron emission tomography (PET) is a popular research topic. People are becoming more interested in PET images as they become more widely available. However, the partial volume effect (PVE) in PET images remains one of the most influential factors causing the resolution of PET images to degrade. It is possible to reduce this PVE and achieve better image quality by measuring and modeling the point spread function (PSF) and then accounting for it inside the reconstruction algorithm. In this work, we examined the response characteristics of the MetisTM PET/CT system by acquiring 22Na point source at different locations in the field of view (FOV) of the scanner and reconstructing with small pixel size for images to obtain their radial, tangential, and axial full-width half maximum (FWHM). An image-based model of the PSF model was then obtained by fitting asymmetric two-dimensional Gaussians on the 22Na images. This PSF model determined by FWHM in three directions was integrated into a three-dimensional ordered subsets expectation maximization (3D-OSEM) algorithm based on a list-mode format to form a new PSF-OSEM algorithm. We used both algorithms to reconstruct point source, Derenzo phantom, and mouse PET images and performed qualitative and quantitative analyses. In the point source study, the PSF-OSEM algorithm reduced the FWHM of the point source PET image in three directions to about 0.67 mm, and in the phantom study, the PET image reconstructed by the PSF-OSEM algorithm had better visual effects. At the same time, the quantitative analysis results of the Derenzo phantom were better than the original 3D-OSEM algorithm. In the mouse experiment, the results of qualitative and quantitative analyses showed that the imaging quality of PSF-OSEM algorithm was better than that of 3D-OSEM algorithm. Our results show that adding the PSF model to the 3D-OSEM algorithm in the MetisTM PET/CT system helps to improve the resolution of the image and satisfy the qualitative and quantitative analysis criteria.

Establishment of a sequential dual tracer 18F‐NaF/18F‐FDG PET protocol for imaging the equine foot

The combination of 18 F-Sodium Fluoride (18 F-NaF) and 18 F-FluoroDeoxyGlucose (18 F-FDG) for positron emission tomography (PET) imaging of the equine foot is appealing for detection of both osseous and soft tissue lesions in a single scan. As the combination of tracers could lead to a loss of information, a sequential approach, consisting in imaging with one tracer prior to injecting the second tracer, might be valuable. The goals of this prospective, methods comparison, exploratory study were to establish the order of tracer injectionandtimingforimaging. Six research horses were imaged under general anesthesia with 18 F-NaF PET, 18 F-FDG PET, dual 18 F-NaF/18 F-FDG PET, and CT. Proper uptake could be identified in tendon lesions as early as 10 min after 18F-FDG injection. Bone uptake was limited when 18F-NaF was injected under general anesthesia, even at 1h after injection, when compared with 18 F-NaF injection prior to anesthesia. The sensitivity and specificity of the dual tracer scans were 0.77 (0.63 to 0.86) and 0.98 (0.96 to 0.99) respectively, to assess 18 F-NaF uptake and 0.5 (0.28 to 0.72) and 0.98 (0.95 to 0.99), respectively, for 18F-FDG uptake. These results suggest that the sequential dual tracer approach is a pertinent technique to optimize the PET data gained from a single anesthetic episode. Based on dynamics of tracer uptake, the optimal protocol consists in injecting 18F-NaF prior to anesthesia, acquire 18F-NaF data then inject 18F-FDG and start acquisition of dual tracer PET data 10 min later. This protocol should be further validated in a larger clinical study.

Pixel-Level Fusion Approach with Vision Transformer for Early Detection of Alzheimer’s Disease

Alzheimer’s disease (AD) has become a serious hazard to human health in recent years, and proper screening and diagnosis of AD remain a challenge. Multimodal neuroimaging input can help identify AD in the early mild cognitive impairment (EMCI) and late mild cognitive impairment (LMCI) stages from normal cognitive development using magnetic resonance imaging (MRI) and positron emission tomography (PET). MRI provides useful information on brain structural abnormalities, while PET data provide the difference between physiological and pathological changes in brain anatomy. The precision of diagnosing AD can increase when these data are combined. However, they are heterogeneous and appropriate, and an adequate number of features are required for AD classification. This paper proposed a multimodal fusion-based approach that uses a mathematical technique called discrete wavelet transform (DWT) to analyse the data, and the optimisation of this technique is achieved through transfer learning using a pre-trained neural network called VGG16. The final fused image is reconstructed using inverse discrete wavelet transform (IDWT). The fused images are classified using a pre-trained vision transformer. The evaluation of the benchmark Alzheimer’s disease neuroimaging initiative (ADNI) dataset shows an accuracy of 81.25% for AD/EMCI and AD/LMCI in MRI test data, as well as 93.75% for AD/EMCI and AD/LMCI in PET test data. The proposed model performed better than existing studies when tested on PET data with an accuracy of 93.75%.

Neural KEM: A Kernel Method With Deep Coefficient Prior for PET Image Reconstruction.

Image reconstruction of low-count positron emission tomography (PET) data is challenging. Kernel methods address the challenge by incorporating image prior information in the forward model of iterative PET image reconstruction. The kernelized expectation-maximization (KEM) algorithm has been developed and demonstrated to be effective and easy to implement. A common approach for a further improvement of the kernel method would be adding an explicit regularization, which however leads to a complex optimization problem. In this paper, we propose an implicit regularization for the kernel method by using a deep coefficient prior, which represents the kernel coefficient image in the PET forward model using a convolutional neural-network. To solve the maximum-likelihood neural network-based reconstruction problem, we apply the principle of optimization transfer to derive a neural KEM algorithm. Each iteration of the algorithm consists of two separate steps: a KEM step for image update from the projection data and a deep-learning step in the image domain for updating the kernel coefficient image using the neural network. This optimization algorithm is guaranteed to monotonically increase the data likelihood. The results from computer simulations and real patient data have demonstrated that the neural KEM can outperform existing KEM and deep image prior methods.

Federated Transfer Learning for Low-dose PET Denoising: A Pilot Study with Simulated Heterogeneous Data.

Positron emission tomography (PET) with a reduced injection dose, i.e., low-dose PET, is an efficient way to reduce radiation dose. However, low-dose PET reconstruction suffers from a low signal-to-noise ratio (SNR), affecting diagnosis and other PET-related applications. Recently, deep learning-based PET denoising methods have demonstrated superior performance in generating high-quality reconstruction. However, these methods require a large amount of representative data for training, which can be difficult to collect and share due to medical data privacy regulations. Moreover, low-dose PET data at different institutions may use different low-dose protocols, leading to non-identical data distribution. While previous federated learning (FL) algorithms enable multi-institution collaborative training without the need of aggregating local data, it is challenging for previous methods to address the large domain shift caused by different low-dose PET settings, and the application of FL to PET is still under-explored. In this work, we propose a federated transfer learning (FTL) framework for low-dose PET denoising using heterogeneous low-dose data. Our experimental results on simulated multi-institutional data demonstrate that our method can efficiently utilize heterogeneous low-dose data without compromising data privacy for achieving superior low-dose PET denoising performance for different institutions with different low-dose settings, as compared to previous FL methods.