An evidence-based algorithm for the utility of FDG-PET for diagnosing Alzheimer's disease according to presence of medial temporal lobe atrophy

Reducing inference cost of Alzheimer's disease identification using an uncertainty-aware ensemble of uni-modal and multi-modal learners

While multi-modal deep learning approaches trained using magnetic resonance imaging (MRI) and fluorodeoxyglucose positron emission tomography (FDG PET) data have shown promise in the accurate identification of Alzheimer's disease, their clinical applicability is hindered by the assumption that both modalities are always available during model inference. In practice, clinicians adjust diagnostic tests based on available information and specific clinical contexts. We propose a novel MRI- and FDG PET-based multi-modal deep learning approach that mimics clinical decision-making by incorporating uncertainty estimates of an MRI-based model (generated using Monte Carlo dropout and evidential deep learning) to determine the necessity of an FDG PET scan, and only inputting the FDG PET to a multi-modal model when required. This approach significantly reduces the reliance on FDG PET scans, which are costly and expose patients to radiation. Our approach reduces the need for FDG PET by up to 92% without compromising model performance, thus optimizing resource use and patient safety. Furthermore, using a global model explanation technique, we provide insights into how anatomical changes in brain regions-such as the entorhinal cortex, amygdala, and ventricles-can positively or negatively influence the need for FDG PET scans in alignment with clinical understanding of Alzheimer's disease.

Brain 18 F-FDG-PET and an optimized cingulate island ratio to differentiate Lewy body dementia and Alzheimer's disease

BACKGROUND AND PURPOSE

The diagnosis of Dementia with Lewy Bodies (DLB) is challenging due to various clinical presentations and clinical and neuropathological features that overlap with Alzheimer's disease (AD). The use of ¹⁸ F-Fluorodeoxyglucose-PET (¹⁸ F-FDG-PET) can be limited due to similar patterns in DLB and AD. However, metabolism in the posterior cingulate cortex is known to be relatively preserved in DLB and visual assessment of the "cingulate island sign" became a helpful tool in the analysis of 18F-FDG-PET. The aim of this study was the evaluation of visual and semiquantitative 18F-FDG-PET analyses in the diagnosis of DLB and the differentiation to AD as well as its relation to other dementia biomarkers.

METHODS

This retrospective study comprises 81 patients with a clinical diagnosis of DLB or AD that underwent ¹⁸ F-FDG-PET/CT. PET scans were analyzed visually and semiquantitatively and results were compared to clinical data, cerebrospinal fluid results, dopamine transporter scintigraphy, and 18F-Florbetaben-PET. Furthermore, different cingulate island ratios were calculated to analyze their diagnostic accuracy.

RESULTS

Visual assessment of 18F-FDG-PET showed an accuracy of 62%-77% in differentiating between DLB and AD. Standard uptake values were significantly lower in the primary visual cortex and the lateral occipital cortex of DLB patients compared to AD patients. The cingulate island ratio was significantly higher in the DLB group compared to the AD group and the ratio posterior cingulate cortex to visual cortex plus lateral occipital cortex showed the highest diagnostic accuracy to discriminate between DLB and AD at 81%.

CONCLUSIONS

Semiquantitative 18F-FDG-PET imaging and especially the use of an optimized cingulate island ratio are valuable tools to differentiate between DLB and AD.

Added value of semiquantitative analysis of brain FDG-PET for the differentiation between MCI-Lewy bodies and MCI due to Alzheimer's disease

PURPOSE

FDG-PET is an established supportive biomarker in dementia with Lewy bodies (DLB), but its diagnostic accuracy is unknown at the mild cognitive impairment (MCI-LB) stage when the typical metabolic pattern may be difficultly recognized at the individual level. Semiquantitative analysis of scans could enhance accuracy especially in less skilled readers, but its added role with respect to visual assessment in MCI-LB is still unknown.

METHODS

We assessed the diagnostic accuracy of visual assessment of FDG-PET by six expert readers, blind to diagnosis, in discriminating two matched groups of patients (40 with prodromal AD (MCI-AD) and 39 with MCI-LB), both confirmed by in vivo biomarkers. Readers were provided in a stepwise fashion with (i) maps obtained by the univariate single-subject voxel-based analysis (VBA) with respect to a control group of 40 age- and sex-matched healthy subjects, and (ii) individual odds ratio (OR) plots obtained by the volumetric regions of interest (VROI) semiquantitative analysis of the two main hypometabolic clusters deriving from the comparison of MCI-AD and MCI-LB groups in the two directions, respectively.

RESULTS

Mean diagnostic accuracy of visual assessment was 76.8 ± 5.0% and did not significantly benefit from adding the univariate VBA map reading (77.4 ± 8.3%) whereas VROI-derived OR plot reading significantly increased both accuracy (89.7 ± 2.3%) and inter-rater reliability (ICC 0.97 [0.96-0.98]), regardless of the readers' expertise.

CONCLUSION

Conventional visual reading of FDG-PET is moderately accurate in distinguishing between MCI-LB and MCI-AD, and is not significantly improved by univariate single-subject VBA but by a VROI analysis built on macro-regions, allowing for high accuracy independent of reader skills.

Diagnostic performance of the medial temporal lobe atrophy scale in patients with Alzheimer's disease: a systematic review and meta-analysis

OBJECTIVE

To evaluate the diagnostic performance and reliability of the medial temporal lobe atrophy (MTA) scale in patients with Alzheimer's disease.

METHODS

A systematic literature search of MEDLINE and EMBASE databases was performed to select studies that evaluated the diagnostic performance or reliability of MTA scale, published up to January 21, 2021. Pooled estimates of sensitivity and specificity were calculated using a bivariate random-effects model. Pooled correlation coefficients for intra- and interobserver agreements were calculated using the random-effects model based on Fisher's Z transformation of correlations. Meta-regression was performed to explain the study heterogeneity. Subgroup analysis was performed to compare the diagnostic performance of the MTA scale and hippocampal volumetry.

RESULTS

Twenty-one original articles were included. The pooled sensitivity and specificity of the MTA scale in differentiating Alzheimer's disease from healthy control were 74% (95% CI, 68-79%) and 88% (95% CI, 83-91%), respectively. The area under the curve of the MTA scale was 0.88 (95% CI, 0.84-0.90). Meta-regression demonstrated that the difference in the method of rating the MTA scale was significantly associated with study heterogeneity (p = 0.04). No significant difference was observed in five studies regarding the diagnostic performance between MTA scale and hippocampal volumetry (p = 0.40). The pooled correlation coefficients for intra- and interobserver agreements were 0.85 (95% CI, 0.69-0.93) and 0.83 (95% CI, 0.66-0.92), respectively.

CONCLUSIONS

Our meta-analysis demonstrated a good diagnostic performance and reliability of the MTA scale in Alzheimer's disease.

KEY POINTS

• The pooled sensitivity and specificity of the MTA scale in differentiating Alzheimer's disease from healthy control were 74% and 88%, respectively. • There was no significant difference in the diagnostic performance between MTA scale and hippocampal volumetry. • The reliability of MTA scale was excellent based on the pooled correlation coefficient for intra- and interobserver agreements.

Differentiating dementia with Lewy bodies from Alzheimer's disease and Parkinson's disease dementia: an update on imaging modalities

Dementia with Lewy bodies is the second most common cause of neurodegenerative dementia after Alzheimer's disease. Dementia with Lewy bodies can provide a diagnostic challenge due to the frequent overlap of clinical signs with other neurodegenerative conditions, namely Parkinson's disease dementia, and Alzheimer's disease. Part of this clinical overlap is due to the neuropathological overlap. Dementia with Lewy bodies is characterized by the accumulation of aggregated α-synuclein protein in Lewy bodies, similar to Parkinson's disease and Parkinson's disease dementia. However, it is also frequently accompanied by aggregation of amyloid-beta and tau, the pathological hallmarks of Alzheimer's disease. Neuroimaging is central to the diagnostic process. This review is an overview of both established and evolving imaging methods that can improve diagnostic accuracy and improve management of this disorder.

Supervised pathway analysis of blood gene expression profiles in Alzheimer's disease

Early identification and treatment of Alzheimer's disease (AD) is hampered by the lack of easily accessible biomarkers. Currently available fluid biomarkers of AD provide indications of the disease stage; however, these are measured in the cerebrospinal fluid, requiring invasive procedures, which are not applicable at the population level. Thus, gene expression profiling of blood provides a viable alternative as a way to screen individuals at risk of AD. Previous studies have shown that despite the limited permeability of the blood-brain barriers, expression profiles of blood genes can be used for the diagnosis and prognosis of several brain disorders. Here, we propose a new approach to pathway analysis of blood gene expression profiles to classify healthy (control [CTL]), mildly cognitively impaired (mild cognitive impairment [MCI]; preclinical stage of AD), and AD subjects. In the pathway analysis, gene expression data are mapped to pathway scores according to a predefined gene set instead of considering each gene separately. The robustness of the analysis enables detection of weak differences between groups owing to the inherent dimension reduction. Our proposed method for pathway analysis takes advantage of linear discriminant analysis for identifying a linear combination of features best separating groups of subjects within each gene set. The gene expression data were retrieved from Gene Expression Omnibus (batch 1: GSE63060; batch 2: GSE63061). Predefined gene sets for pathway analysis were obtained from the Broad Institute Collection of Curated Pathways. The method achieved a 10-fold cross-validated area under receiver operating characteristic curve of 0.84 for classification of AD versus CTL and 0.80 for classification of mild cognitive impairment versus CTL. These results reveal the good potential of blood-based biomarkers for assisting early diagnosis and disease monitoring of AD.

Brain glucose metabolism in Lewy body dementia: implications for diagnostic criteria

BACKGROUND

[18F]FDG-PET hypometabolism patterns are indicative of different neurodegenerative conditions, even from the earliest disease phase. This makes [18F]FDG-PET a valuable tool in the diagnostic workup of neurodegenerative diseases. The utility of [18F]FDG-PET in dementia with Lewy bodies (DLB) needs further validation by considering large samples of patients and disease comparisons and applying state-of-the-art statistical methods. Here, we aimed to provide an extensive validation of the [18F]FDG-PET metabolic signatures in supporting DLB diagnosis near the first clinical assessment, which is characterized by high diagnostic uncertainty, at the single-subject level.

METHODS

In this retrospective study, we included N = 72 patients with heterogeneous clinical classification at entry (mild cognitive impairment, atypical parkinsonisms, possible DLB, probable DLB, and other dementias) and an established diagnosis of DLB at a later follow-up. We generated patterns of [18F]FDG-PET hypometabolism in single cases by using a validated voxel-wise analysis (p < 0.05, FWE-corrected). The hypometabolism patterns were independently classified by expert raters blinded to any clinical information. The final clinical diagnosis at follow-up (2.94 ± 1.39 [0.34-6.04] years) was considered as the diagnostic reference and compared with clinical classification at entry and with [18F]FDG-PET classification alone. In addition, we calculated the diagnostic accuracy of [18F]FDG-PET maps in the differential diagnosis of DLB with Alzheimer's disease dementia (ADD) (N = 60) and Parkinson's disease (PD) (N = 36).

RESULTS

The single-subject [18F]FDG-PET hypometabolism pattern, showing temporo-parietal and occipital involvement, was highly consistent across DLB cases. Clinical classification at entry produced several misclassifications with an agreement of only 61.1% with the diagnostic reference. On the contrary, [18F]FDG-PET hypometabolism maps alone accurately predicted diagnosis of DLB at follow-up (88.9%). The high power of the [18F]FDG-PET hypometabolism signature in predicting the final clinical diagnosis allowed a ≈ 50% increase in accuracy compared to the first clinical assessment alone. Finally, [18F]FDG-PET hypometabolism maps yielded extremely high discriminative power, distinguishing DLB from ADD and PD conditions with an accuracy of > 90%.

CONCLUSION

The present validation of the diagnostic and prognostic accuracy of the disease-specific brain metabolic signature in DLB at the single-subject level argues for the consideration of [18F]FDG-PET in the early phase of the DLB diagnostic flowchart. The assessment of the [18F]FDG-PET hypometabolism pattern at entry may shorten the diagnostic time, resulting in benefits for treatment options and management of patients.

European Association of Nuclear Medicine and European Academy of Neurology recommendations for the use of brain 18 F-fluorodeoxyglucose positron emission tomography in neurodegenerative cognitive impairment and dementia: Delphi consensus

BACKGROUND AND PURPOSE

Recommendations for using fluorodeoxyglucose positron emission tomography (FDG-PET) to support the diagnosis of dementing neurodegenerative disorders are sparse and poorly structured.

METHODS

Twenty-one questions on diagnostic issues and on semi-automated analysis to assist visual reading were defined. Literature was reviewed to assess study design, risk of bias, inconsistency, imprecision, indirectness and effect size. Critical outcomes were sensitivity, specificity, accuracy, positive/negative predictive value, area under the receiver operating characteristic curve, and positive/negative likelihood ratio of FDG-PET in detecting the target conditions. Using the Delphi method, an expert panel voted for/against the use of FDG-PET based on published evidence and expert opinion.

RESULTS

Of the 1435 papers, 58 papers provided proper quantitative assessment of test performance. The panel agreed on recommending FDG-PET for 14 questions: diagnosing mild cognitive impairment due to Alzheimer's disease (AD), frontotemporal lobar degeneration (FTLD) or dementia with Lewy bodies (DLB); diagnosing atypical AD and pseudo-dementia; differentiating between AD and DLB, FTLD or vascular dementia, between DLB and FTLD, and between Parkinson's disease and progressive supranuclear palsy; suggesting underlying pathophysiology in corticobasal degeneration and progressive primary aphasia, and cortical dysfunction in Parkinson's disease; using semi-automated assessment to assist visual reading. Panellists did not support FDG-PET use for pre-clinical stages of neurodegenerative disorders, for amyotrophic lateral sclerosis and Huntington disease diagnoses, and for amyotrophic lateral sclerosis or Huntington-disease-related cognitive decline.

CONCLUSIONS

Despite limited formal evidence, panellists deemed FDG-PET useful in the early and differential diagnosis of the main neurodegenerative disorders, and semi-automated assessment helpful to assist visual reading. These decisions are proposed as interim recommendations.

Clinical utility of FDG-PET for the differential diagnosis among the main forms of dementia

AIM

To assess the clinical utility of FDG-PET as a diagnostic aid for differentiating Alzheimer's disease (AD; both typical and atypical forms), dementia with Lewy bodies (DLB), frontotemporal lobar degeneration (FTLD), vascular dementia (VaD) and non-degenerative pseudodementia.

METHODS

A comprehensive literature search was conducted using the PICO model to extract evidence from relevant studies. An expert panel then voted on six different diagnostic scenarios using the Delphi method.

RESULTS

The level of empirical study evidence for the use of FDG-PET was considered good for the discrimination of DLB and AD; fair for discriminating FTLD from AD; poor for atypical AD; and lacking for discriminating DLB from FTLD, AD from VaD, and for pseudodementia. Delphi voting led to consensus in all scenarios within two iterations. Panellists supported the use of FDG-PET for all PICOs-including those where study evidence was poor or lacking-based on its negative predictive value and on the assistance it provides when typical patterns of hypometabolism for a given diagnosis are observed.

CONCLUSION

Although there is an overall lack of evidence on which to base strong recommendations, it was generally concluded that FDG-PET has a diagnostic role in all scenarios. Prospective studies targeting diagnostically uncertain patients for assessing the added value of FDG-PET would be highly desirable.

Decreased Complexity in Alzheimer's Disease: Resting-State fMRI Evidence of Brain Entropy Mapping

Alzheimer's disease (AD) is a frequently observed, irreversible brain function disorder among elderly individuals. Resting-state functional magnetic resonance imaging (rs-fMRI) has been introduced as an alternative approach to assessing brain functional abnormalities in AD patients. However, alterations in the brain rs-fMRI signal complexities in mild cognitive impairment (MCI) and AD patients remain unclear. Here, we described the novel application of permutation entropy (PE) to investigate the abnormal complexity of rs-fMRI signals in MCI and AD patients. The rs-fMRI signals of 30 normal controls (NCs), 33 early MCI (EMCI), 32 late MCI (LMCI), and 29 AD patients were obtained from the Alzheimer's disease Neuroimaging Initiative (ADNI) database. After preprocessing, whole-brain entropy maps of the four groups were extracted and subjected to Gaussian smoothing. We performed a one-way analysis of variance (ANOVA) on the brain entropy maps of the four groups. The results after adjusting for age and sex differences together revealed that the patients with AD exhibited lower complexity than did the MCI and NC controls. We found five clusters that exhibited significant differences and were distributed primarily in the occipital, frontal, and temporal lobes. The average PE of the five clusters exhibited a decreasing trend from MCI to AD. The AD group exhibited the least complexity. Additionally, the average PE of the five clusters was significantly positively correlated with the Mini-Mental State Examination (MMSE) scores and significantly negatively correlated with Functional Assessment Questionnaire (FAQ) scores and global Clinical Dementia Rating (CDR) scores in the patient groups. Significant correlations were also found between the PE and regional homogeneity (ReHo) in the patient groups. These results indicated that declines in PE might be related to changes in regional functional homogeneity in AD. These findings suggested that complexity analyses using PE in rs-fMRI signals can provide important information about the fMRI characteristics of cognitive impairments in MCI and AD.

Molecular and cellular pathophysiology of preclinical Alzheimer's disease

Although the two pathological hallmarks of Alzheimer's disease (AD), senile plaques composed of amyloid-β (Aβ) peptides and neurofibrillary tangles (NFTs) consisting of hyperphosphorylated tau, have been studied extensively in postmortem AD and relevant animal and cellular models, the pathogenesis of AD remains unknown, particularly in the early stages of the disease where therapies presumably would be most effective. We and others have demonstrated that Aβ plaques and NFTs are present in varying degrees before the onset and throughout the progression of dementia. In this regard, aged people with no cognitive impairment (NCI), mild cognitive impairment (MCI, a presumed prodromal AD transitional state, and AD all present at autopsy with varying levels of pathological hallmarks. Cognitive decline, a requisite for the clinical diagnosis of dementia associated with AD, generally correlates better with NFTs than Aβ plaques. However, correlations are even higher between cognitive decline and synaptic loss. In this review, we illustrate relevant clinical pathological research in preclinical AD and throughout the progression of dementia in several areas including Aβ and tau pathobiology, single population expression profiling of vulnerable hippocampal and basal forebrain neurons, neuroplasticity, neuroimaging, cerebrospinal fluid (CSF) biomarker studies and their correlation with antemortem cognitive endpoints. In each of these areas, we provide evidence for the importance of studying the pathological hallmarks of AD not in isolation, but rather in conjunction with other molecular, cellular, and imaging markers to provide a more systematic and comprehensive assessment of the multiple changes that occur during the transition from NCI to MCI to frank AD.