Positron Emission Tomography Modalities Research Articles

Abstract PO2-01-01: Biophysical simulation using DCE-MRI to forecast response to NAT in HER2+ patients, with glucose characterization and orthogonal validation using FDG-PET

Abstract Background: Metabolic reprogramming and tumor angiogenesis are two tightly linked hallmarks of cancer. Regions of high metabolic activity within a tumor can become hypoxic or nutrient starved, eliciting a cascade of pro-angiogenic signals that can lead to increased tumor perfusion and in turn greater metabolic activity. Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) and 18Fluorodeoxyglucose (FDG) positron emission tomography (PET) are two imaging methods commonly used in the diagnosis of cancer; the former can be also used to identify the perfusion of the tumor microenvironment (TME) and the latter provides a coarse readout of glucose metabolic activity. Here, we are presented with a unique cohort of patients who underwent DCE-MRI, 18FDG-PET and 64Cu-DOTA-Traztuzumab offering potential to perform a pilot analysis. First, we characterize the performance of our perfusion model SimBioSys- Microvasculature (SBS-MV) through a stability analysis, as well as comparison with two PET modalities. Finally, we use this model in 3D simulations of individual HER2+ breast cancer patients to forecast responses to neoadjuvant chemotherapy (NAT). Methods: SBS-MV is a modified Tofts model for pharmacokinetic modeling of DCE-MRI data, utilizing a tissue segmentation model developed in-house to inform parameter fits and ensure that the derived parameters fall within acceptable values on a tissue-by-tissue level, in addition its function for standard fitting of DCE time-course data. We first evaluated the stability of the SBS-MV model by analyzing a separate cohort of 10 patients who underwent ultrafast DCE-MRI. Temporal undersampling was performed on the original high temporal resolution data to mimic low temporal resolution from standard-of-care (SoC) DCE studies. Both datasets were processed with SBS-MV model. Next, we analyzed data from a cohort of 18 patients, each of whom underwent a pre-NAT SoC DCE-MRI study, a mid-treatment FDG PET/CT study, and a mid-treatment 64Cu-DOTA-Trastuzumab/CT study during treatment. Tissue segmentation and SBS-MV fits were performed on the pre-NAT DCE MRI. Tightly cropped boxes encompassing the tumor in the 3D SBS-MV volumes as well as the PET volumes were created. Using these identified regions, all summary statistics were calculated and cross-correlated between imaging modalities. Results: SBS-MV was stable to SoC-mimicking temporally undersampled ultrafast DCE MRI series, demonstrating relatively little variability in the output parameters (a voxel wise median deviation of approximately 0.005 min-1 ). Further, we demonstrate that SBS-MV parameters (Ktrans, ve) are correlated with FDG SUVSA and 64Cu SUVSA. In addition, the glucose concentrations used in the biophysical simulations were correlated with FDG SUVSA, indicating that downstream applications of the SBS-MV models still carry this information about perfusion. Finally, using SBS-MV, our biophysical simulations of HER2-targeted therapy accurately predict patient response. In this small cohort, our biophysical simulation platform performed well, yielding predictive accuracy of 0.83, with sensitivity and specificity of 0.83 and 0.83, respectively. These performance metrics are in line with previously published reports. Conclusion: Our MV model is capable of extracting biologically meaningful perfusion parameters from standard clinical DCE MRI time series, providing the same benefits of a comprehensive kinetic analysis, without impacting current clinical workflow. This approach could be used in both the research and clinical settings, offering actionable information on what drives individual patient therapeutic response for a more personalized care. Citation Format: John Whitman, Vikram Adhikarla, Russell Rockne, Lusine Tumyan, Joanne Mortimer, Wei Huang, Joseph Peterson, Dorys Lopez-Ramos, John Cole. Biophysical simulation using DCE-MRI to forecast response to NAT in HER2+ patients, with glucose characterization and orthogonal validation using FDG-PET [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO2-01-01.

A Transformer-Guided Cross-Modality Adaptive Feature Fusion Framework for Esophageal Gross Tumor Volume Segmentation

Background and ObjectiveAccurate segmentation of esophageal gross tumor volume (GTV) indirectly enhances the efficacy of radiotherapy for patients with esophagus cancer. In this domain, learning-based methods have been employed to fuse cross-modality positron emission tomography (PET) and computed tomography (CT) images, aiming to improve segmentation accuracy. This fusion is essential as it combines functional metabolic information from PET with anatomical information from CT, providing complementary information. While the existing three-dimensional (3D) segmentation method has achieved state-of-the-art (SOTA) performance, it typically relies on pure-convolution architectures, limiting its ability to capture long-range spatial dependencies due to convolution's confinement to a local receptive field. To address this limitation and further enhance esophageal GTV segmentation performance, this work proposes a transformer-guided cross-modality adaptive feature fusion network, referred to as TransAttPSNN, which is based on cross-modality PET/CT scans. MethodsSpecifically, we establish an attention progressive semantically-nested network (AttPSNN) by incorporating the convolutional attention mechanism into the progressive semantically-nested network (PSNN). Subsequently, we devise a plug-and-play transformer-guided cross-modality adaptive feature fusion model, which is inserted between the multi-scale feature counterparts of a two-stream AttPSNN backbone (one for the PET modality flow and another for the CT modality flow), resulting in the proposed TransAttPSNN architecture. ResultsThrough extensive four-fold cross-validation experiments on the clinical PET/CT cohort. The proposed approach acquires a Dice similarity coefficient (DSC) of 0.76 ± 0.13, a Hausdorff distance (HD) of 9.38 ± 8.76 mm, and a Mean surface distance (MSD) of 1.13 ± 0.94 mm, outperforming the SOTA competing methods. The qualitative results show a satisfying consistency with the lesion areas. ConclusionsThe devised transformer-guided cross-modality adaptive feature fusion module integrates the strengths of PET and CT, effectively enhancing the segmentation performance of esophageal GTV. The proposed TransAttPSNN has further advanced the research of esophageal GTV segmentation.

NANOPARTICLES FOR DUAL IMAGING: PET AND FLUORESCENCE IMAGING

Objective: Molecular imaging methods are gaining popularity in clinical and preclinical fields. There are many different imaging methods such as computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), single photon emission computed tomography (SPECT) and Near-infrared fluorescence (NIRF), and each has different advantages and disadvantages. Multimodal imaging methods, a combination of two or more molecular imaging modalities, have been developed to overcome the disadvantages of these molecular imaging methods. However, these imaging methods are conjugated with different vectors to improve the multimodal imaging methods used. In this field, drug delivery systems, peptides, proteins, antibodies and aptamers have been widely used for conjugation of multimodal imaging modalities to overcome some of the disadvantages that come from imaging modalities. In this review, PET and NIRF combination imaging modalities were explained and more specifically PET and NIRF nanoparticle dual imaging modalities with their pros and cons were investigated. Result and Discussion: Dual imaging modalities overcome to limitations of single imaging modalities and provide a better understanding of biological, anatomical, and physiological processes. Multimodal imaging modalities offer higher sensitivity, resolution, and specificity with lower cost and toxicity although have several disadvantages.

Strategies for deep learning-based attenuation and scatter correction of brain 18 F-FDG PET images in the image domain.

Attenuation and scatter correction is crucial for quantitative positron emission tomography (PET) imaging. Direct attenuation correction (AC) in the image domain using deep learning approaches has been recently proposed for combined PET/MR and standalone PET modalities lacking transmission scanning devices or anatomical imaging. In this study, different input settings were considered in the model training to investigate deep learning-based AC in the image space. Three different deep learning methods were developed for direct AC in the image space: (i) use of non-attenuation-corrected PET images as input (NonAC-PET), (ii) use of attenuation-corrected PET images with a simple two-class AC map (composed of soft-tissue and background air) obtained from NonAC-PET images (PET segmentation-based AC [SegAC-PET]), and (iii) use of both NonAC-PET and SegAC-PET images in a Double-Channel fashion to predict ground truth attenuation corrected PET images with Computed Tomography images (CTAC-PET). Since a simple two-class AC map (generated from NonAC-PET images) can easily be generated, this work assessed the added value of incorporating SegAC-PET images into direct AC in the image space. A 4-fold cross-validation scheme was adopted to train and evaluate the different models based using 80 brain 18 F-Fluorodeoxyglucose PET/CT images. The voxel-wise and region-wise accuracy of the models were examined via measuring the standardized uptake value (SUV) quantification bias in different regions of the brain. The overall root mean square error (RMSE) for the Double-Channel setting was 0.157±0.08 SUV in the whole brain region, while RMSEs of 0.214±0.07 and 0.189±0.14 SUV were observed in NonAC-PET and SegAC-PET models, respectively. A mean SUV bias of 0.01±0.26% was achieved by the Double-Channel model regarding the activity concentration in cerebellum region, as opposed to 0.08±0.28% and 0.05±0.28% SUV biases for the network that uniquely used NonAC-PET or SegAC-PET as input, respectively. SegAC-PET images with an SUV bias of -1.15±0.54%, served as a benchmark for clinically accepted errors. In general, the Double-Channel network, relying on both SegAC-PET and NonAC-PET images, outperformed the other AC models. Since the generation of two-class AC maps from non-AC PET images is straightforward, the current study investigated the potential added value of incorporating SegAC-PET images into a deep learning-based direct AC approach. Altogether, compared with models that use only NonAC-PET and SegAC-PET images, the Double-Channel deep learning network exhibited superior attenuation correction accuracy.

Potential role of 68Ga-PSMA PET/CT in metastatic renal cell cancer: A prospective study

PurposeProstate-specific membrane antigen (PSMA), in addition to its utility in prostate cancer, is also an angiogenic imaging marker for hypervascular tumors like renal cell carcinoma (RCC). Our study aims to assess the potential role of 68Ga-PSMA-11 positron emission tomography (PET)/CT in metastatic RCC and compare it with contrast-enhanced computed tomography (CECT). MethodsBiopsy-proven RCC patients with known or suspected distant metastases who underwent 68Ga-PSMA-11 PET/CT for staging/restaging were prospectively recruited. Those patients who had undergone 18F-FDG PET/CT within six weeks of 68Ga-PSMA PET/CT were also included retrospectively for comparative analysis. A patient-based and lesion-based analysis was done to compare the lesion detection rates of CECT, 68Ga-PSMA-11 PET and 18F-FDG PET. PET-based quantitative parameters were also compared between both the PET modalities. Impact of baseline parameters on survival was assessed using Cox regression analysis. A p-value of < 0.05 was considered significant. ResultsThirty-seven patients with median age 60 years ± 13 years (range = 26–76 years) were included in the study. Twenty-seven patients had clear cell (cc) RCC, six had papillary RCC (pRCC), and one each had an eosinophilic variant of ccRCC, collecting duct RCC, translocation RCC and poorly differentiated RCC. 68Ga-PSMA-11 PET performed better in detecting marrow and equivocal bone lesions and worse in detecting liver lesions compared to CECT. 68Ga-PSMA-11 PET-based angiogenic tumor burden estimation using Total Lesion-PSMA (TL-PSMA) and PSMA-Total volume (PSMA-TV) had a prognostic impact on the survival of patients. 68Ga-PSMA-11 PET also detected more lesions and showed significantly higher SUVmax than 18F-FDG PET. Conclusion68Ga-PSMA-11 PET/CT performs better than CECT and 18F-FDG PET/CT in metastatic evaluation and has prognostic value in the management of clear cell RCC.

A hybrid few-shot multiple-instance learning model predicting the aggressiveness of lymphoma in PET/CT images

Background and objectivePatients with aggressive non-Hodgkin lymphoma (NHL) undergo distinct therapy strategies compared with indolent NHL patients. However, it is challenging to estimate NHL aggressiveness based on visual inspection of positron emission tomography (PET) or computed tomography (CT) images. Since diffuse large B-cell lymphoma (DLBCL) and Follicular lymphoma (FL) are the most typical and dominant aggressive and indolent NHL, respectively, this study aims to develop an artificial-intelligence-enabled model to distinguish DLBCL from FL in PET/CT images as the first step to tackle this challenge. MethodsWe propose a hybrid few-shot multiple-instance learning model to predict the aggressiveness of the NHL. First, rotation-based self-supervision learning (SSL) has been employed to train the encoder on a large-scale, publicly available CT image dataset. Second, hybrid instance-level features are obtained for each NHL lesion by combining deep features with the radiomics features from both PET and CT modalities. Third, instance-level features are transformed into bag-level (or patient-level) representations. Finally, bag-level representations are fed into a distance-based classifier through few-shot learning to predict NHL aggressiveness. ResultsOur model achieves an accuracy of 0.751 ± 0.008, a sensitivity of 0.787 ± 0.012, a specificity of 0.715 ± 0.013, an F1-score of 0.753 ± 0.009, and an area under the curve (AUC) of 0.795 ± 0.009 at the bag level. It outperforms the typical counterparts that use the radiomic features, random forest for feature selection, and support vector machines (SVMs) as classifiers. The three counterparts yield accuracies of 0.714 ± 0.023, 0.705 ± 0.008, and 0.698 ± 0.008, respectively. Moreover, settings of the SSL training dataset (Deep lesion) and task (rotation), hybrid CT and radiomic PET features, the pool-layer strategy of maximum, and distance-based classifier generate the best model. ConclusionsA hybrid few-shot multiple-instance learning model can predict lymphoma aggressiveness in PET/CT images and could be a potential tool for determining therapy strategies. Hybrid features and the combination of SSL, few-shot learning, and weakly supervised learning are the two powerful pillars of the model, and these can be expanded to other medical applications with limited samples and incomplete annotations.

Pareto Optimized Adaptive Learning with Transposed Convolution for Image Fusion Alzheimer's Disease Classification.

Alzheimer's disease (AD) is a neurological condition that gradually weakens the brain and impairs cognition and memory. Multimodal imaging techniques have become increasingly important in the diagnosis of AD because they can help monitor disease progression over time by providing a more complete picture of the changes in the brain that occur over time in AD. Medical image fusion is crucial in that it combines data from various image modalities into a single, better-understood output. The present study explores the feasibility of employing Pareto optimized deep learning methodologies to integrate Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) images through the utilization of pre-existing models, namely the Visual Geometry Group (VGG) 11, VGG16, and VGG19 architectures. Morphological operations are carried out on MRI and PET images using Analyze 14.0 software and after which PET images are manipulated for the desired angle of alignment with MRI image using GNU Image Manipulation Program (GIMP). To enhance the network's performance, transposed convolution layer is incorporated into the previously extracted feature maps before image fusion. This process generates feature maps and fusion weights that facilitate the fusion process. This investigation concerns the assessment of the efficacy of three VGG models in capturing significant features from the MRI and PET data. The hyperparameters of the models are tuned using Pareto optimization. The models' performance is evaluated on the ADNI dataset utilizing the Structure Similarity Index Method (SSIM), Peak Signal-to-Noise Ratio (PSNR), Mean-Square Error (MSE), and Entropy (E). Experimental results show that VGG19 outperforms VGG16 and VGG11 with an average of 0.668, 0.802, and 0.664 SSIM for CN, AD, and MCI stages from ADNI (MRI modality) respectively. Likewise, an average of 0.669, 0.815, and 0.660 SSIM for CN, AD, and MCI stages from ADNI (PET modality) respectively.

Monte Carlo Simulation to Test the Effectiveness of Crystal Detector Length for PHITS-Based PET Modality

PET (Positron-emission tomography) is used to determine physiological and metabolic functions in the body. Monte Carlo simulation is an important part of PET imaging, and the Particle Heavy Ion Transport code System (PHITS) is a simulation platform that can be used to perform Monte Carlo simulations. This study uses a Monte Carlo simulation based on PHITS to determine the range of gamma absorption with an energy of 511 keV in a scintillation detector crystal material. The gamma absorption range determines the effective crystal length in the PET modality. The simulation process is carried out by shooting Gamma at various types of materials, which are the materials used in PET scintillation crystals. The materials used in this simulation are NaI (Sodium Iodide), BaF2 (Barium Florida), BGO (Bismuth Germanate), and GSO (Gadolinium Oxyorthosilicate), considering their atomic number and crystal density. The crystal material is capable of absorbing gamma radiation with an energy of 511 keV with detailed crystal lengths for each NaI crystal of 0.26 cm; 0.25 cm BaF2 crystals; 0.1cm BGO crystals; and 0.18 cm GSO crystals. The crystal length from this simulation is smaller than the commercially available crystal length (range 1-3 cm). Based on the crystal length data, the most effective crystal for absorbing gamma radiation is the BGO crystal.

The first PET glimpse of a proton FLASH beam

We demonstrate the first ever recorded positron-emission tomography (PET) imaging and dosimetry of a FLASH proton beam at the Proton Center of the MD Anderson Cancer Center. Two scintillating LYSO crystal arrays, read out by silicon photomultipliers, were configured with a partial field of view of a cylindrical poly-methyl methacrylate (PMMA) phantom irradiated by a FLASH proton beam. The proton beam had a kinetic energy of 75.8 MeV and an intensity of about 3.5 × 1010 protons that were extracted over 101.5 ms-long spills. The radiation environment was characterized by cadmium–zinc–telluride and plastic scintillator counters. Preliminary results indicate that the PET technology used in our tests can efficiently record FLASH beam events. The instrument yielded informative and quantitative imaging and dosimetry of beam-activated isotopes in a PMMA phantom, as supported by Monte Carlo simulations. These studies open a new PET modality that can lead to improved imaging and monitoring of FLASH proton therapy.

Positron Emission Tomography in Heart Failure: From Pathophysiology to Clinical Application.

Imaging modalities are increasingly being used to evaluate the underlying pathophysiology of heart failure. Positron emission tomography (PET) is a non-invasive imaging technique that uses radioactive tracers to visualize and measure biological processes in vivo. PET imaging of the heart uses different radiopharmaceuticals to provide information on myocardial metabolism, perfusion, inflammation, fibrosis, and sympathetic nervous system activity, which are all important contributors to the development and progression of heart failure. This narrative review provides an overview of the use of PET imaging in heart failure, highlighting the different PET tracers and modalities, and discussing fields of present and future clinical application.

PET-CT image Co-segmentation of lung tumor using joint level set model

Accurate lung tumor segmentation plays an important role in radiotherapy and targeted therapy. Positron emission tomography (PET) and computed tomography (CT) scanner imaging provide complementary evidence for lung tumor segmentation. In specific, PET can recognize the tumor tissues, while the tissue boundaries are blurred in such a modality. By contrast, CT has a better resolution but a lower contrast between tumor and normal tissues. It is well known that jointly exploiting the evidence from PET and CT images significantly benefits lung tumor delineation. A novel joint level set model is proposed in this paper to integrate PET and CT evidence in a unified energy form, providing co-segmentation results. The convergence result of our co-segmentation model can find the optimal tradeoff between PET and CT modalities. Different characteristics of these two modalities are comprehensively considered in the adaptive convergence process which starts mostly with the PET evidence to locate tumor tissues and stops mostly with the CT evidence to delineate tissue boundaries. The novelty of our joint level set model lies in its adaptability which stepwise moderates joint weights during the model convergence process. The performance of our proposed model is validated on 20 PET-CT images of the nonsmall cell lung tumor. The excellent performance of our proposed model for PET-CT image co-segmentation of the lung tumor is demonstrated by comparing it to the state-of-art models.

High-quality PET image synthesis from ultra-low-dose PET/MRI using bi-task deep learning.

Lowering the dose for positron emission tomography (PET) imaging reduces patients' radiation burden but decreases the image quality by increasing noise and reducing imaging detail and quantifications. This paper introduces a method for acquiring high-quality PET images from an ultra-low-dose state to achieve both high-quality images and a low radiation burden. We developed a two-task-based end-to-end generative adversarial network, named bi-c-GAN, that incorporated the advantages of PET and magnetic resonance imaging (MRI) modalities to synthesize high-quality PET images from an ultra-low-dose input. Moreover, a combined loss, including the mean absolute error, structural loss, and bias loss, was created to improve the trained model's performance. Real integrated PET/MRI data from 67 patients' axial heads (each with 161 slices) were used for training and validation purposes. Synthesized images were quantified by the peak signal-to-noise ratio (PSNR), normalized mean square error (NMSE), structural similarity (SSIM), and contrast noise ratio (CNR). The improvement ratios of these four selected quantitative metrics were used to compare the images produced by bi-c-GAN with other methods. In the four-fold cross-validation, the proposed bi-c-GAN outperformed the other three selected methods (U-net, c-GAN, and multiple input c-GAN). With the bi-c-GAN, in a 5% low-dose PET, the image quality was higher than that of the other three methods by at least 6.7% in the PSNR, 0.6% in the SSIM, 1.3% in the NMSE, and 8% in the CNR. In the hold-out validation, bi-c-GAN improved the image quality compared to U-net and c-GAN in both 2.5% and 10% low-dose PET. For example, the PSNR using bi-C-GAN was at least 4.46% in the 2.5% low-dose PET and at most 14.88% in the 10% low-dose PET. Visual examples also showed a higher quality of images generated from the proposed method, demonstrating the denoising and improving ability of bi-c-GAN. By taking advantage of integrated PET/MR images and multitask deep learning (MDL), the proposed bi-c-GAN can efficiently improve the image quality of ultra-low-dose PET and reduce radiation exposure.

On Disharmony in Batch Normalization and Dropout Methods for Early Categorization of Alzheimer’s Disease

Alzheimer’s disease (AD) is a global health issue that predominantly affects older people. It affects one’s daily activities by modifying neural networks in the brain. AD is categorized by the death of neurons, the creation of amyloid plaques, and the development of neurofibrillary tangles. In clinical settings, an early diagnosis of AD is critical to limit the problems associated with it and can be accomplished using neuroimaging modalities, such as magnetic resonance imaging (MRI) and positron emission tomography (PET). Deep learning (DL) techniques are widely used in computer vision and related disciplines for various tasks such as classification, segmentation, detection, etc. CNN is a sort of DL architecture, which is normally useful to categorize and extract data in the spatial and frequency domains for image-based applications. Batch normalization and dropout are commonly deployed elements of modern CNN architectures. Due to the internal covariance shift between batch normalization and dropout, the models perform sub-optimally under diverse scenarios. This study looks at the influence of disharmony between batch normalization and dropout techniques on the early diagnosis of AD. We looked at three different scenarios: (1) no dropout but batch normalization, (2) a single dropout layer in the network right before the softmax layer, and (3) a convolutional layer between a dropout layer and a batch normalization layer. We investigated three binaries: mild cognitive impairment (MCI) vs. normal control (NC), AD vs. NC, AD vs. MCI, one multiclass AD vs. NC vs. MCI classification problem using PET modality, as well as one binary AD vs. NC classification problem using MRI modality. In comparison to using a large value of dropout, our findings suggest that using little or none at all leads to better-performing designs.

Deep learning-based classification of healthy aging controls, mild cognitive impairment and Alzheimer’s disease using fusion of MRI-PET imaging

Automated detection of dementia stage using multimodal imaging modalities will be helpful for improving the clinical diagnosis. In this study, we develop the Inception-ResNet wrapper model in differentiating the healthy controls (HC), mild cognitive impairment (MCI), and Alzheimer’s disease (AD) using conjoint magnetic resonance imaging (MRI) and positron emission tomography (PET) scans. We use T1-weighted MR and PET images of individuals aged between 42 and 95 years, including HC, MCI and AD patients. We first perform 3D tissue segmentation of MR images after skull striping. The atlas-based segmented MR image tissue is fused with PET image. Then we transform PET images from RGB to HSI color space and apply fusion of MRI with PET images using two-dimensional Fourier and discrete wavelet transform (DWT) and then reconstruct the MR-PET fused image using inverse Fourier and DWT methods. After the fusion of MRI and PET imaging modalities, we used 60 % training, 20 % for validation and the remaining 20 % as a test set using various convolutional neural networks. We found the proposed model as the best classifier with an accuracy of 95.5 %, 94.1 % and 95.9 % in classifying HC vs MCI, MCI vs AD and AD vs HC respectively when compared to the existing methods. We conclude that the proposed deep learning model has potential in automated classification of healthy and dementia stages using combined MRI and PET modalities with good performance.

Alzheimer’s Disease-Related Genes Identified by Linking Spatial Patterns of Pathology and Gene Expression

BackgroundAlzheimer’s Disease (AD) is an age-related neurodegenerative disease with a poorly understood etiology, shown to be partly genetic. Glucose hypometabolism, extracellular Amyloid-beta (Aβ) deposition, and intracellular Tau deposition are cardinal features of AD and display characteristic spatial patterns in the brain. We hypothesize that regional differences in underlying gene expression confer either resistance or susceptibility to AD pathogenic processes and are associated with these spatial patterns. Data-driven methods for the identification of genes involved in AD pathogenesis complement hypothesis-driven approaches that reflect current theories about the disease. Here we present a data driven method for the identification of genes involved in AD pathogenesis based on comparing spatial patterns of normal gene expression to Positron Emission Tomography (PET) images of glucose hypometabolism, Aβ deposition, and Tau deposition.MethodsWe performed correlations between the cerebral cortex microarray samples from the six cognitively normal (CN) post-mortem Allen Human Brain Atlas (AHBA) specimens and PET FDG-18, AV-45, and AV-1451 tracer images from AD and CN participants in the Alzheimer’s Disease and Neuroimaging Initiative (ADNI) database. Correlation coefficients for each gene by each ADNI subject were then entered into a partial least squares discriminant analysis (PLS-DA) to determine sets that best classified the AD and CN groups. Pathway analysis via BioPlanet 2019 was then used to infer the function of implicated genes.ResultsWe identified distinct sets of genes strongly associated with each PET modality. Pathway analyses implicated novel genes involved in mitochondrial function, and Notch signaling, as well as genes previously associated with AD.ConclusionUsing an unbiased approach, we derived sets of genes with expression patterns spatially associated with FDG hypometabolism, Aβ deposition, and Tau deposition in AD. This methodology may complement population-based approaches for identifying the genetic underpinnings of AD.

When is a biomarker an AD biomarker? Face versus construct validity and practical implications for differential application

AbstractBackgroundTremendous recent developments have expanded the portfolio of biomarkers that have been described as directly specific for Alzheimer’s disease (AD) pathophysiology or assessing its consequences. This presentation will aim to provide a snapshot of the current validation and readiness status of imaging‐ and bodily fluid‐based AD biomarkers for different potential application scenarios.MethodAn overview of AD biomarker characteristics will be provided, focusing on established and emerging positron emission tomography (PET) and blood‐based biomarkers for amyloid‐β (Aβ) and tau pathology as well as glial activation and synaptic and neurodegeneration. Summarizing and discussing the foregoing talks in this session as well as reviewing relevant literature, emphasis will be placed on unique validation and application aspects of the respective biomarkers and on practical considerations.ResultAD‐related pathophysiology and its consequences can be assessed in vivo directly in the brain or in bodily fluids, most recently also in blood. The underlying modalities differ greatly in how their proposed face validity is confirmed, i.e. how specific the respective biomarker is to disease‐specific processes and how sensitive to longitudinal changes and different disease stages. Specifically, PET enables the direct mapping, quantification, and staging of regional pathology and related processes in the brain, while blood‐based measures generally provide information about peripheral, yet highly associated processes. Both yield continuous measures; however, this information is often discarded in favor of dichotomous, and global, biomarker classification. Novel blood‐based biomarkers have thus been claimed to have diagnostic and prognostic properties comparable with PET modalities. PET is limited to specialized centers, is resource‐hungry and involves radiation, while blood‐based biomarkers promise a scalable and accessible alternative or complement. However, the construct validity of blood biomarkers has hitherto mainly been established against relevant PET biomarkers. Finally, the various levels of harmonization and standardization of biomarker acquisition and analysis have major implications for their potential application.ConclusionThe field of AD biomarkers is more dynamic than ever. Snapshot evaluations of their current state of validity, their potential use and their practical limitations are needed to establish their potential differential, joint, and complementary roles in AD diagnostics, population screening, clinical trial enrichment, and use as trial outcome measure.

Classification of Initial Stages of Alzheimer’s Disease through Pet Neuroimaging Modality and Deep Learning: Quantifying the Impact of Image Filtering Approaches

Alzheimer’s disease (AD) is a leading health concern affecting the elderly population worldwide. It is defined by amyloid plaques, neurofibrillary tangles, and neuronal loss. Neuroimaging modalities such as positron emission tomography (PET) and magnetic resonance imaging are routinely used in clinical settings to monitor the alterations in the brain during the course of progression of AD. Deep learning techniques such as convolutional neural networks (CNNs) have found numerous applications in healthcare and other technologies. Together with neuroimaging modalities, they can be deployed in clinical settings to learn effective representations of data for different tasks such as classification, segmentation, detection, etc. Image filtering methods are instrumental in making images viable for image processing operations and have found numerous applications in image-processing-related tasks. In this work, we deployed 3D-CNNs to learn effective representations of PET modality data to quantify the impact of different image filtering approaches. We used box filtering, median filtering, Gaussian filtering, and modified Gaussian filtering approaches to preprocess the images and use them for classification using 3D-CNN architecture. Our findings suggest that these approaches are nearly equivalent and have no distinct advantage over one another. For the multiclass classification task between normal control (NC), mild cognitive impairment (MCI), and AD classes, the 3D-CNN architecture trained using Gaussian-filtered data performed the best. For binary classification between NC and MCI classes, the 3D-CNN architecture trained using median-filtered data performed the best, while, for binary classification between AD and MCI classes, the 3D-CNN architecture trained using modified Gaussian-filtered data performed the best. Finally, for binary classification between AD and NC classes, the 3D-CNN architecture trained using box-filtered data performed the best.

3D convolutional neural networks-based multiclass classification of Alzheimer\u2019s and Parkinson\u2019s diseases using PET and SPECT neuroimaging modalities

BackgroundAlzheimer’s disease (AD) is a neurodegenerative brain pathology formed due to piling up of amyloid proteins, development of plaques and disappearance of neurons. Another common subtype of dementia like AD, Parkinson’s disease (PD) is determined by the disappearance of dopaminergic neurons in the region known as substantia nigra pars compacta located in the midbrain. Both AD and PD target aged population worldwide forming a major chunk of healthcare costs. Hence, there is a need for methods that help in the early diagnosis of these diseases. PD subjects especially those who have confirmed postmortem plaque are a strong candidate for a second AD diagnosis. Modalities such as positron emission tomography (PET) and single photon emission computed tomography (SPECT) can be combined with deep learning methods to diagnose these two diseases for the benefit of clinicians.ResultIn this work, we deployed a 3D Convolutional Neural Network (CNN) to extract features for multiclass classification of both AD and PD in the frequency and spatial domains using PET and SPECT neuroimaging modalities to differentiate between AD, PD and Normal Control (NC) classes. Discrete Cosine Transform has been deployed as a frequency domain learning method along with random weak Gaussian blurring and random zooming in/out augmentation methods in both frequency and spatial domains. To select the hyperparameters of the 3D-CNN model, we deployed both 5- and 10-fold cross-validation (CV) approaches. The best performing model was found to be AD/NC(SPECT)/PD classification with random weak Gaussian blurred augmentation in the spatial domain using fivefold CV approach while the worst performing model happens to be AD/NC(PET)/PD classification without augmentation in the frequency domain using tenfold CV approach. We also found that spatial domain methods tend to perform better than their frequency domain counterparts.ConclusionThe proposed model provides a good performance in discriminating AD and PD subjects due to minimal correlation between these two dementia types on the clinicopathological continuum between AD and PD subjects from a neuroimaging perspective.

PET with Different Radiopharmaceuticals in Neuroendocrine Neoplasms: An Umbrella Review of Published Meta-Analyses.

Simple SummaryFunctional imaging methods and, in particular, positron emission tomography (PET) using several radiopharmaceuticals may play a pivotal role in patients with neuroendocrine neoplasms including neuroendocrine tumors (NETs) located in different sites, paraganglioma (PGL) and neuroblastoma (NB), recurrent medullary thyroid carcinoma (rMTC) and aggressive neuroendocrine neoplasms. Several radiopharmaceuticals can be used in this setting such as Gallium-68 somatostatin analogues (68Ga-SSA), Fluorine-18 fluorodihydroxyphenylalanine (18F-FDOPA), Gallium-68 exendin-4 (68Ga-exendin-4), Fluorine-18 fluorodeoxyglucose (18F-FDG). This umbrella review provides an evidence-based summary about meta-analyses on diagnostic performance, prognostic value, clinical impact and safety of PET with different radiopharmaceuticals in patients with neuroendocrine neoplasms. Overall, evidence-based data support the use of PET with different radiopharmaceuticals in patients with neuroendocrine neoplasms but with specific indications for each radiopharmaceutical.Background: Several meta-analyses have reported quantitative data about the diagnostic performance, the prognostic value, the impact on management and the safety of positron emission tomography (PET) including related hybrid modalities (PET/CT or PET/MRI) using different radiopharmaceuticals in patients with neuroendocrine neoplasms. We performed an umbrella review of published meta-analyses to provide an evidence-based summary. Methods: A comprehensive literature search of meta-analyses listed in PubMed/MEDLINE and Cochrane Library databases was carried out (last search date: 30 June 2021). Results: Thirty-four published meta-analyses were selected and summarized. About the diagnostic performance: 68Ga-SSA PET yields high diagnostic performance in patients with NETs and PGL; 18F-FDOPA PET yields good diagnostic performance in patients with intestinal NETs, PGL, NB, being the best available PET method in detecting rMTC; 68Ga-exendin-4 PET has good diagnostic accuracy in detecting insulinomas; 18F-FDG PET has good diagnostic performance in detecting aggressive neuroendocrine neoplasms. About the prognostic value: 68Ga-SSA PET has a recognized prognostic value in well-differentiated NETs, whereas 18F-FDG PET has a recognized prognostic value in aggressive neuroendocrine neoplasms. A significant clinical impact of 68Ga-SSA PET and related hybrid modalities in patients with NETs was demonstrated. There are no major toxicities or safety issues related to the use of PET radiopharmaceuticals in patients with neuroendocrine neoplasms. Conclusions: Evidence-based data support the use of PET with different radiopharmaceuticals in patients with neuroendocrine neoplasms with specific indications for each radiopharmaceutical.

Association of the tissue microstructural diffusivity and translocator protein PET in Gulf War Illness

About a third of all United States veterans who served in the 1991 Gulf War (GW) report a range of chronic health symptoms including fatigue, neurocognitive symptoms, and musculoskeletal pain. There is growing evidence supporting the detrimental effects of maladaptive neuroimmune reactions in this multi-symptom illness. Indeed, recent studies using positron emission tomography (PET) using the radioligand [11C]PBR28, which binds the neuroinflammation marker 18 ​kDa translocator protein (TSPO), and diffusion magnetic resonance imaging (dMRI) have independently identified the anterior cingulate (ACC) and midcingulate cortices (MCC) as key regions for differentiating GWI veterans from healthy controls (HC). Here, we used integrated (i.e., simultaneous) PET/MRI imaging techniques, paired with dMRI processing methods (neurite density imaging, NDI, and free-water diffusion tensor model to single-shell high-order dMRI), to directly evaluate the relationship between ACC and MCC microstructural tissue parameters, TSPO signal and clinical parameters in the same cohorts of 10 GWI veterans and 19 ​HCs.Within the regions evaluated, TSPO signal elevations were associated with restricted diffusivity in the extracellular compartment, while clinical measures were best explained by neurite density and cellular structure complexity measures. Our study is the first to provide evidence of a relationship between PET and dMRI modalities in GWI and suggests that microstructural changes in the ACC and MCC are correlated to mood symptoms and cognitive performances in GWI veterans.