Search Results (25)

Background: Artificial intelligence (AI) is reshaping neuroimaging workflows for Alzheimer’s disease (AD) diagnosis, particularly through PET and MRI analysis advances. Since the FDA approval of Tauvid, a PET tracer targeting tau pathology, there has been a notable increase in studies applying AI to neuroimaging data. This narrative review synthesizes recent, high-impact literature to highlight clinically relevant AI applications in AD imaging. Methods: This review examined peer-reviewed studies published between January 2020 and January 2025, focusing on the use of AI, including machine learning, deep learning, and hybrid models for diagnostic and prognostic tasks in AD using PET and/or MRI. Studies were identified through targeted PubMed, Scopus, and Embase searches, emphasizing methodological diversity and clinical relevance. Results: A total of 111 studies were categorized into five thematic areas: Image preprocessing and segmentation, diagnostic classification, prognosis and disease staging, multimodal data fusion, and emerging innovations. Deep learning models such as convolutional neural networks (CNNs), generative adversarial networks (GANs), and transformer-based architectures were widely employed by the research community in the field of AD. At the same time, several models reported strong diagnostic performance, but methodological challenges such as reproducibility, small sample sizes, and lack of external validation limit clinical translation. Trends in explainable AI, synthetic imaging, and integration of clinical biomarkers are also discussed. Conclusions: AI is rapidly advancing the field of AD imaging, offering tools for enhanced segmentation, staging, and early diagnosis. Multimodal approaches and biomarker-guided models show particular promise. However, future research must focus on reproducibility, interpretability, and standardized validation to bridge the gap between research and clinical practice. Full article

Advancements in neuroimaging, particularly diffusion magnetic resonance imaging (MRI) techniques and molecular imaging with positron emission tomography (PET), have significantly enhanced the early detection of biomarkers in neurodegenerative and neuro-ophthalmic disorders. These include Alzheimer’s disease, Parkinson’s disease, multiple sclerosis, neuromyelitis optica, and myelin oligodendrocyte glycoprotein antibody disease. This review highlights the transformative role of advanced diffusion MRI techniques—Neurite Orientation Dispersion and Density Imaging and Diffusion Kurtosis Imaging—in identifying subtle microstructural changes in the brain and visual pathways that precede clinical symptoms. When integrated with artificial intelligence (AI) algorithms, these techniques achieve unprecedented diagnostic precision, facilitating early detection of neurodegeneration and inflammation. Additionally, next-generation PET tracers targeting misfolded proteins, such as tau and alpha-synuclein, along with inflammatory markers, enhance the visualization and quantification of pathological processes in vivo. Deep learning models, including convolutional neural networks and multimodal transformers, further improve diagnostic accuracy by integrating multimodal imaging data and predicting disease progression. Despite challenges such as technical variability, data privacy concerns, and regulatory barriers, the potential of AI-enhanced neuroimaging to revolutionize early diagnosis and personalized treatment in neurodegenerative and neuro-ophthalmic disorders is immense. This review underscores the importance of ongoing efforts to validate, standardize, and implement these technologies to maximize their clinical impact. Full article

The identification of neuroinflammation as a critical factor in Alzheimer’s disease (AD) has expanded the focus of research beyond amyloid-β and tau pathology. The neuroinflammatory fluid biomarkers GFAP, sTREM2, and YKL-40 have gained attention for their potential in early detection and monitoring of disease progression. Plasma GFAP has demonstrated promise in predicting the conversion from mild cognitive impairment to AD dementia, while sTREM2 highlights microglial activation, although there are conflicting results regarding its dynamics in AD pathogenesis. Advanced imaging techniques, such as PET tracers targeting TSPO and MAO-B, have also been developed to visualize glial activation in vivo, offering spatial and temporal insights into neuroinflammatory processes. However, the clinical implementation of these biomarkers faces challenges due to their lack of specificity, as many of them can be elevated in other conditions. Therapeutic strategies targeting neuroinflammation are emerging, with TREM2-targeting therapies and antidiabetic drugs like GLP-1 receptor agonists showing potential in modulating microglial activity. Nevertheless, the complexity of neuroinflammation, which encompasses both protective and harmful responses, necessitates further research to fully unravel its role and optimize therapeutic approaches for AD. Full article

The α-synucleinopathies are a group of neurodegenerative diseases characterized by the deposition of α-synuclein aggregates (α-syn) in the brain. Currently, there is no suitable tracer to enable a definitive early diagnosis of these diseases. We reported candidates based on 4,4′-disarylbisthiazole (DABTA) scaffold with a high affinity towards α-syn and excellent selectivity over Aβ and tau fibrils. Based on prior in silico studies, a focused library of 23 halogen-containing and O-methylated DABTAs was prepared. The DABTAs were synthesized via a modified two-step Hantzsch thiazole synthesis, characterized, and used in competitive binding assays against [³H]PiB and [³H]DCVJ. The DABTAs were obtained with an overall chemical yield of 15–71%, and showed a calculated lipophilicity of 2.5–5.7. The ligands demonstrated an excellent affinity to α-syn with both [³H]PiB and [³H]DCVJ: K_i 0.1–4.9 nM and up to 20–3900-fold selectivity over Aβ and tau fibrils. It could be concluded that in silico simulation is useful for the rational design of a new generation of DABTAs. Further investigation of the leads in the next step is encouraged: radiolabeling of the ligands with radioisotopes such as fluorine-18 or carbon-11 for in vivo, ex vivo, and translational research and for further in vitro experiments on human-derived protein aggregates. Full article

Aggregation of Tau protein into paired helical filaments causing neurofibrillary tangles (NFT) is a neuropathological feature in Alzheimer’s disease (AD). This study aimed to develop and evaluate the effectiveness of a novel radioiodinated tracer, 4-[¹²⁵I]iodo-3-(1H-pyrrolo[2,3-c]pyridine-1-yl)pyridine ([¹²⁵I]INFT), for binding to Tau protein in postmortem human AD brain. Radiosynthesis of [¹²⁵I]INFT was carried out using electrophilic destannylation by iodine-125 and purified chromatographically. Computational modeling of INFT binding on Tau fibril was compared with IPPI. In vitro, autoradiography studies were conducted with [¹²⁵I]INFT for Tau in AD and cognitively normal (CN) brains. [¹²⁵I]INFT was produced in >95% purity. Molecular modeling of INFT revealed comparable binding energies to IPPI at site-1 of the Tau fibril with an affinity of IC₅₀ = 7.3 × 10⁻⁸ M. Binding of [¹²⁵I]INFT correlated with the presence of Tau in the AD brain, confirmed by anti-Tau immunohistochemistry. The ratio of average grey matter (GM) [¹²⁵I]INFT in AD versus CN was found to be 5.9, and AD GM/white matter (WM) = 2.5. Specifically bound [¹²⁵I]INFT to Tau in AD brains was displaced by IPPI (>90%). Monoamine oxidase inhibitor deprenyl had no effect and clorgyline had little effect on [¹²⁵I]INFT binding. [¹²⁵I]INFT is a less lipophilic imaging agent for Tau in AD. Full article

The accumulation of tau is a hallmark of several neurodegenerative diseases and is associated with neuronal hypoactivity and presynaptic dysfunction. Oral administration of the adenosine A₁ receptor antagonist rolofylline (KW-3902) has previously been shown to reverse spatial memory deficits and to normalize the basic synaptic transmission in a mouse line expressing full-length pro-aggregant tau (Tau^ΔK) at low levels, with late onset of disease. However, the efficacy of treatment remained to be explored for cases of more aggressive tauopathy. Using a combination of behavioral assays, imaging with several PET-tracers, and analysis of brain tissue, we compared the curative reversal of tau pathology by blocking adenosine A1 receptors in three mouse models expressing different types and levels of tau and tau mutants. We show through positron emission tomography using the tracer [¹⁸F]CPFPX (a selective A1 receptor ligand) that intravenous injection of rolofylline effectively blocks A₁ receptors in the brain. Moreover, when administered to Tau^ΔK mice, rolofylline can reverse tau pathology and synaptic decay. The beneficial effects are also observed in a line with more aggressive tau pathology, expressing the amyloidogenic repeat domain of tau (TauRD^ΔK) with higher aggregation propensity. Both models develop a progressive tau pathology with missorting, phosphorylation, accumulation of tau, loss of synapses, and cognitive decline. TauRD^ΔK causes pronounced neurofibrillary tangle assembly concomitant with neuronal death, whereas Tau^ΔK accumulates only to tau pretangles without overt neuronal loss. A third model tested, the rTg4510 line, has a high expression of mutant Tau^P301L and hence a very aggressive phenotype starting at ~3 months of age. This line failed to reverse pathology upon rolofylline treatment, consistent with a higher accumulation of tau-specific PET tracers and inflammation. In conclusion, blocking adenosine A1 receptors by rolofylline can reverse pathology if the pathological potential of tau remains below a threshold value that depends on concentration and aggregation propensity. Full article

Reactive astrogliosis is an early event in the continuum of Alzheimer’s disease (AD). Current advances in positron emission tomography (PET) imaging provide ways of assessing reactive astrogliosis in the living brain. In this review, we revisit clinical PET imaging and in vitro findings using the multi-tracer approach, and point out that reactive astrogliosis precedes the deposition of Aβ plaques, tau pathology, and neurodegeneration in AD. Furthermore, considering the current view of reactive astrogliosis heterogeneity—more than one subtype of astrocyte involved—in AD, we discuss how astrocytic body fluid biomarkers might fit into trajectories different from that of astrocytic PET imaging. Future research focusing on the development of innovative astrocytic PET radiotracers and fluid biomarkers may provide further insights into the heterogeneity of reactive astrogliosis and improve the detection of AD in its early stages. Full article

(1) Background: Tauopathies are a group of diseases characterized by the deposition of abnormal tau protein. They are distinguished into 3R, 4R, and 3R/4R tauopathies and also include Alzheimer’s disease (AD) and chronic traumatic encephalopathy (CTE). Positron emission tomography (PET) imaging represents a pivotal instrument to guide clinicians. This systematic review aims to summarize the current and novel PET tracers. (2) Methods: Literature research was conducted on Pubmed, Scopus, Medline, Central, and the Web of Science using the query “pet ligands” and “tauopathies”. Articles published from January 2018 to 9 February, 2023, were searched. Only studies on the development of novel PET radiotracers for imaging in tauopathies or comparative studies between existing PET tracers were included. (3) Results: A total of 126 articles were found, as follows: 96 were identified from PubMed, 27 from Scopus, one on Central, two on Medline, and zero on the Web of Science. Twenty-four duplicated works were excluded, and 63 articles did not satisfy the inclusion criteria. The remaining 40 articles were included for quality assessment. (4) Conclusions: PET imaging represents a valid instrument capable of helping clinicians in diagnosis, but it is not always perfect in differential diagnosis, even if further investigations on humans for novel promising ligands are needed. Full article

The accumulation of pathologically misfolded tau is a feature shared by a group of neurodegenerative disorders collectively referred to as tauopathies. Alzheimer’s disease (AD) is the most prevalent of these tauopathies. Immunohistochemical evaluation allows neuropathologists to visualize paired-helical filaments (PHFs)—tau pathological lesions, but this is possible only after death and only shows tau in the portion of brain sampled. Positron emission tomography (PET) imaging allows both the quantitative and qualitative analysis of pathology over the whole brain of a living subject. The ability to detect and quantify tau pathology in vivo using PET can aid in the early diagnosis of AD, provide a way to monitor disease progression, and determine the effectiveness of therapeutic interventions aimed at reducing tau pathology. Several tau-specific PET radiotracers are now available for research purposes, and one is approved for clinical use. This study aims to analyze, compare, and rank currently available tau PET radiotracers using the fuzzy preference ranking organization method for enrichment of evaluations (PROMETHEE), which is a multi-criteria decision-making (MCDM) tool. The evaluation is based on relatively weighted criteria, such as specificity, target binding affinity, brain uptake, brain penetration, and rates of adverse reactions. Based on the selected criteria and assigned weights, this study shows that a second-generation tau tracer, [¹⁸F]RO-948, may be the most favorable. This flexible method can be extended and updated to include new tracers, additional criteria, and modified weights to help researchers and clinicians select the optimal tau PET tracer for specific purposes. Additional work is needed to confirm these results, including a systematic approach to defining and weighting criteria and clinical validation of tracers in different diseases and patient populations. Full article

Hyperphosphorylated tau aggregates, also known as neurofibrillary tangles, are a hallmark neuropathological feature of Alzheimer’s disease (AD). Molecular imaging of tau by positron emission tomography (PET) began with the development of [¹⁸F]FDDNP, an amyloid β tracer with off-target binding to tau, which obtained regional specificity through the differing distributions of amyloid β and tau in AD brains. A concerted search for more selective and affine tau PET tracers yielded compounds belonging to at least eight structural categories; ¹⁸F-flortaucipir, known variously as [¹⁸F]-T807, AV-1451, and Tauvid^®, emerged as the first tau tracer approved by the American Food and Drug Administration. The various tau tracers differ concerning their selectivity over amyloid β, off-target binding at sites such as monoamine oxidase and neuromelanin, and degree of uptake in white matter. While there have been many reviews of molecular imaging of tau in AD and other conditions, there has been no systematic comparison of the fitness of the various tracers for discriminating between AD patient and healthy control (HC) groups. In this narrative review, we endeavored to compare the binding properties of the various tau tracers in vitro and the effect size (Cohen’s d) for the contrast by PET between AD patients and age-matched HC groups. The available tracers all gave good discrimination, with Cohen’s d generally in the range of two–three in culprit brain regions. Overall, Cohen’s d was higher for AD patient groups with more severe illness. Second-generation tracers, while superior concerning off-target binding, do not have conspicuously higher sensitivity for the discrimination of AD and HC groups. We suppose that available pharmacophores may have converged on a maximal affinity for tau fibrils, which may limit the specific signal imparted in PET studies. Full article

The dementia spectrum is a broad range of disorders with complex diagnosis, pathophysiology, and a limited set of treatment options, where the most common variety is Alzheimer’s disease (AD). Positron emission tomography (PET) has become a valuable tool for the detection of AD; however, following the results of post-mortem studies, AD diagnosis has modest sensitivity and specificity at best. It remains common practice that readings of these images are performed by a physician’s subjective impressions of the spatial pattern of tracer uptake, and so quantitative methods based on established biomarkers have had little penetration into clinical practice. The present study is a review of the data-driven methods available for molecular neuroimaging studies (fluorodeoxyglucose-/amyloid-/tau-PET), with emphasis on the use of machine/deep learning as quantitative tools complementing the specialist in detecting AD. This work is divided into two broad parts. The first covers the epidemiology and pathology of AD, followed by a review of the role of PET imaging and tracers for AD detection. The second presents quantitative methods used in the literature for detecting AD, including the general linear model and statistical parametric mapping, 3D stereotactic surface projection, principal component analysis, scaled subprofile modeling, support vector machines, and neural networks. Full article

Background: Hybrid positron emission tomography (PET)/magnetic resonance (MR) is an emerging imaging modality with great potential to provide complementary data acquired at the same time, under the same physiological conditions. The aim of this study was to evaluate the prognostic value of hybrid ¹⁸F-fluorodeoxyglucose (FDG) PET/MR in patients with differentiated thyroid cancer (DTC) who underwent total thyroidectomy and radioactive iodine therapy for suspicion of disease relapse. Methods: Between November 2015 and February 2017, 55 patients underwent hybrid ¹⁸F-FDG PET/MR. Assessment of positive MR was made considering all sequences in terms of malignancy based on the morphological T2-weighted features and the presence of restricted diffusivity on diffusion-weighted imaging images and both needed to be positive on the same lesion. Both foci with abnormal ¹⁸F-FDG uptake, which corresponded to tissue abnormalities on the MR, and tracer accumulation, which did not correspond to normal morphological structures, were considered positive. Results: During follow-up (mean 42 ± 27 months), 29 patients (53%) had disease recurrence. In the Cox univariate regression analysis age, serum Tg level ≥ 2 ng/mL, positive short tau inversion recovery (STIR), and positive PET were significant predictors of DTC recurrence. Kaplan–Meier survival analyses showed that patients with Tg ≥ 2 ng/mL had poorer outcomes compared to those with serum Tg level < 2 ng/mL (p < 0.05). Similarly, patients with positive STIR and positive PET had a worst outcome compared to those with negative STIR (p < 0.05) and negative PET (p < 0.005). Survival analysis performed in the subgroup of 36 subjects with Tg level ≥ 2 ng/mL revealed that patients with positive PET had a worst outcome compared to those with negative PET (p < 0.05). Conclusions: Age, serum Tg level ≥ 2 ng/mL, positive STIR, and positive ¹⁸F-FDG PET were significant predictors of DTC recurrence. However, the serum Tg level was the only independent predictor of DTC. Hybrid PET/MR imaging may have the potential to improve the information content of one modality with the other and would offer new opportunities in patients with DTC. Thus, further studies in a larger patient population are needed to understand the additional value of ¹⁸F-FDG PET/MR in patients with DTC. Full article

Tau aggregates accumulate in the Alzheimer’s disease (AD) brain according to the established Braak staging scheme and spread from transentorhinal over limbic regions to the neocortex. To impact the management of AD patients, an in vivo tool for tau Braak staging is needed. First-generation tau tracers have limited performance in detecting early stages of tau. Therefore, we tested the corresponding capability of the next-generation tau tracer, ¹⁸F-PI-2620. We analyzed ¹⁸F-PI-2620 multicenter PET data from 37 beta-amyloid-positive AD dementia patients and those from 26 healthy controls. We applied kinetic modeling of the 0–60 min p.i. PET data using MRTM2 with the lower cerebellum as the reference region to extract Braak stage-dependent distribution volume ratios, whereas controls were used to define Braak stage PET positivity thresholds. Stage-dependent PET positivity widely followed the Braak scheme (except Braak stage III) presenting descending frequency of PET positivity from Braak I (43%), II (38%), III (49%), IV (35%), V (30%) to VI (14%). A strictly hierarchical model was met by 64% of AD dementia cases. Nineteen percent showed a hippocampal sparing tauopathy pattern. Thus, we could assign 87% to the six-stage hierarchical Braak model including tauopathy variants. ¹⁸F-PI-2620 PET appears to be able to perform Braak tau staging of AD in vivo. Full article

Corticobasal syndrome (CBS) is a rare neurodegenerative condition characterized by four-repeat tau aggregation in the cortical and subcortical brain regions and accompanied by severe atrophy. The aim of this study was to evaluate partial volume effect correction (PVEC) in patients with CBS compared to a control cohort imaged with the 18-kDa translocator protein (TSPO) positron emission tomography (PET) tracer [¹⁸F]GE-180. Eighteen patients with CBS and 12 age- and sex-matched healthy controls underwent [¹⁸F]GE-180 PET. The cortical and subcortical regions were delineated by deep nuclei parcellation (DNP) of a 3D-T1 MRI. Region-specific subcortical volumes and standardized uptake values and ratios (SUV and SUVr) were extracted before and after region-based voxel-wise PVEC. Regional volumes were compared between patients with CBS and controls. The % group differences and effect sizes (CBS vs. controls) of uncorrected and PVE-corrected SUVr data were compared. Single-region positivity in patients with CBS was assessed by a >2 SD threshold vs. controls and compared between uncorrected and PVE-corrected data. Smaller regional volumes were detected in patients with CBS compared to controls in the right ventral striatum (p = 0.041), the left putamen (p = 0.005), the right putamen (p = 0.038) and the left pallidum (p = 0.015). After applying PVEC, the % group differences were distinctly higher, but the effect sizes of TSPO uptake were only slightly stronger due to the higher variance after PVEC. The single-region positivity of TSPO PET increased in patients with CBS after PVEC (100 vs. 83 regions). PVEC in the cortical and subcortical regions is valuable for TSPO imaging of patients with CBS, leading to the improved detection of elevated [¹⁸F]GE-180 uptake, although the effect sizes in the comparison against the controls did not improve strongly. Full article

Abnormal accumulation of Tau protein is closely associated with neurodegeneration and cognitive impairment and it is a biomarker of neurodegeneration in the dementia field, especially in Alzheimer’s disease (AD); therefore, it is crucial to be able to assess the Tau deposits in vivo. Beyond the fluid biomarkers of tauopathy described in this review in relationship with the brain glucose metabolic patterns, this review aims to focus on tauopathy assessment by using Tau PET imaging. In recent years, several first-generation Tau PET tracers have been developed and applied in the dementia field. Common limitations of first-generation tracers include off-target binding and subcortical white-matter uptake; therefore, several institutions are working on developing second-generation Tau tracers. The increasing knowledge about the distribution of first- and second-generation Tau PET tracers in the brain may support physicians with Tau PET data interpretation, both in the research and in the clinical field, but an updated description of differences in distribution patterns among different Tau tracers, and in different clinical conditions, has not been reported yet. We provide an overview of first- and second-generation tracers used in ongoing clinical trials, also describing the differences and the properties of novel tracers, with a special focus on the distribution patterns of different Tau tracers. We also describe the distribution patterns of Tau tracers in AD, in atypical AD, and further neurodegenerative diseases in the dementia field. Full article