scholarly journals Radiomics Analysis of Magnetic Resonance Imaging Facilitates the Identification of Preclinical Alzheimer’s Disease: An Exploratory Study

2020 ◽  
Vol 8 ◽  
Author(s):  
Tao-Ran Li ◽  
Yue Wu ◽  
Juan-Juan Jiang ◽  
Hua Lin ◽  
Chun-Lei Han ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Decline ◽  
High Frequency ◽  
Resonance Imaging ◽  
Posterior Cingulate Gyrus ◽  
Preclinical Ad ◽  
Mri Scans ◽  
Conversion Time ◽  
Frequency Features

Diagnosing Alzheimer’s disease (AD) in the preclinical stage offers opportunities for early intervention; however, there is currently a lack of convenient biomarkers to facilitate the diagnosis. Using radiomics analysis, we aimed to determine whether the features extracted from multiparametric magnetic resonance imaging (MRI) can be used as potential biomarkers. This study was part of the Sino Longitudinal Study on Cognitive Decline project (NCT03370744), a prospective cohort study. All participants were cognitively healthy at baseline. Cohort 1 (n = 183) was divided into individuals with preclinical AD (n = 78) and controls (n = 105) using amyloid-positron emission tomography, and this cohort was used as the training dataset (80%) and validation dataset (the remaining 20%); cohort 2 (n = 51) was selected retrospectively and divided into “converters” and “nonconverters” according to individuals’ future cognitive status, and this cohort was used as a separate test dataset; cohort three included 37 converters (13 from the Alzheimer’s Disease Neuroimaging Initiative) and was used as another test set for independent longitudinal research. We extracted radiomics features from multiparametric MRI scans from each participant, using t-tests, autocorrelation tests, and three independent selection algorithms. We then established two classification models (support vector machine [SVM] and random forest [RF]) to verify the efficiency of the retained features. Five-fold cross-validation and 100 repetitions were carried out for the above process. Furthermore, the acquired stable high-frequency features were tested in cohort three by paired two-sample t-tests and survival analyses to identify whether their levels changed with cognitive decline and impact conversion time. The SVM and RF models both showed excellent classification efficiency, with an average accuracy of 89.7–95.9% and 87.1–90.8% in the validation set and 81.9–89.1% and 83.2–83.7% in the test set, respectively. Three stable high-frequency features were identified, all based on the structural MRI modality: the large zone high-gray-level emphasis feature of the right posterior cingulate gyrus, the variance feature of the left superior parietal gyrus, and the coarseness feature of the left posterior cingulate gyrus; their levels were correlated with amyloid-β deposition and predicted future cognitive decline (areas under the curve 0.649–0.761). In addition, levels of the variance feature at baseline decreased with cognitive decline and could affect the conversion time (p < 0.05). In conclusion, this exploratory study shows that the radiomics features of multiparametric MRI scans could represent potential biomarkers of preclinical AD.

scholarly journals Radiomics analysis of magnetic resonance imaging helps to identify preclinical Alzheimer’s disease: an exploratory study

2020 ◽  
Author(s):  
Tao-Ran Li ◽  
Yue Wu ◽  
Juan-Juan Jiang ◽  
Jie-Hui Jiang ◽  
Ying Han
Keyword(s):  
Cognitive Decline ◽  
High Frequency ◽  
Exploratory Study ◽  
Cingulate Gyrus ◽  
Resonance Imaging ◽  
Test Set ◽  
Posterior Cingulate Gyrus ◽  
Preclinical Ad ◽  
Conversion Time ◽  
Frequency Features

Abstract Background: Diagnosing Alzheimer’s disease (AD) in the preclinical stage offers opportunities to early intervention, however, there is a lack of convenient biomarkers currently. By using the methods of radiomics analysis, we aimed to determine whether the features extracted from multi-parameter magnetic resonance imaging (MRI) can be used as potential biomarkers. Methods: This study is part of the SILCODE project (NCT03370744). All participants were cognitively healthy at baseline. The cohort 1 (n=183) was divided into individuals with preclinical AD (n=78) and controls (n=105) by amyloid-positron emission tomography, used as the training dataset (80%) and validation dataset (the rest 20%); cohort 2 (n=51) was divided into “converters” and “non-converters” by individuals’ future cognitive status, used as a separate test dataset; cohort 3 included 37 “converters” (13 from ADNI), was used as another test set for independent longitudinal researches. We extracted radiomics features from multi-parameter MRI of each participant, used t-tests, autocorrelation tests, and three independent selection algorithms, respectively, to select features. Then we established two classification models (support vector machine (SVM) and random forest (RF)) to verify the efficiency of retained features. Five-fold cross-validation and 100 repetitions were carried out for the above process. Furthermore, the acquired stable high-frequency features were tested in cohort 3 by paired two-sample t-tests and survival analyses, in order to identify whether their levels change with cognitive decline and impact conversion time. Results: The SVM and RF models both showed excellent classification efficiency, with the average accuracy of 89.65%-95.90% and 87.07%-90.81% respectively in the validation set, 81.86%-89.10% and 83.19%-83.68% respectively in the test set. Three stable high-frequency features were identified, namely Large zone high-gray-level emphasis feature of right posterior cingulate gyrus, Variance feature of left superior parietal gyrus and Coarseness feature of left posterior cingulate gyrus, all based on structural MRI modality; their levels were correlated with amyloid-β deposition, played good roles in predicting future cognitive decline (AUCs 64.9%-76.1%). In addition, levels of the Variance feature at baseline timepoint decreased with cognitive decline, and can affect the conversion time (p<0.05). Conclusion: In this exploratory study, we show radiomics features of multi-parameter MRI can be potential biomarkers of preclinical AD.

scholarly journals O4-09-04: Association of magnetic resonance imaging white matter lesions and cognitive decline in Alzheimer's disease

2013 ◽  
Vol 9 ◽  
pp. P701-P701
Author(s):  
Margit Mikula ◽  
Petroula Proitsi ◽  
Martina Sattlecker ◽  
Mike O'Sullivan ◽  
Andy Simmons ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
White Matter ◽  
Magnetic Resonance ◽  
Cognitive Decline ◽  
White Matter Lesions ◽  
Resonance Imaging

scholarly journals Genetic Effects on Longitudinal Cognitive Decline During the Early Stages of Alzheimer's Disease

2021 ◽  
Author(s):  
Atul Kumar ◽  
Maryam Shoai ◽  
Sebastian Palmqvist ◽  
Erik Stomrud ◽  
John Hardy ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Decline ◽  
Genome Wide Association Study ◽  
Early Stage ◽  
Cognitive Change ◽  
Preclinical Ad ◽  
Genome Wide ◽  
A Genome ◽  
Polygenic Scores

Abstract Background Cognitive decline in early-stage Alzheimer’s disease (AD) may depend on genetic variability. Methods In the Swedish BioFINDER study, we used polygenic scores (PGS) (for AD, intelligence and educational attainment), and genetic variants (in a genome-wide association study [GWAS]) to predict longitudinal cognitive change (measured by MMSE) over a mean of 4.2 years. We included 555 β-amyloid (Aβ) negative cognitively unimpaired (CU) individuals, 206 Aβ-positive CU (preclinical AD), 110 Aβ-negative mild cognitive impairment (MCI) patients, and 146 Aβ-positive MCI patients (prodromal AD). Results Polygenic scores for AD (in Aβ-positive individuals) and intelligence (independent of Aβ-status) were associated with cognitive decline. Eight genes were associated with cognitive decline in GWAS (3 independent of Aβ-status). Conclusions AD risk genes may influence cognitive decline in early AD, while genes related to intelligence may modulate cognitive decline irrespective of disease. Therapies targeting the implicated biological pathways may modulate the clinical course of AD.

scholarly journals Monthly At-Home Computerized Cognitive Testing to Detect Diminished Practice Effects in Preclinical Alzheimer's Disease

2022 ◽  
Vol 13 ◽  
Author(s):  
Roos J. Jutten ◽  
Dorene M. Rentz ◽  
Jessie F. Fu ◽  
Danielle V. Mayblyum ◽  
Rebecca E. Amariglio ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Decline ◽  
Pet Imaging ◽  
Cognitive Testing ◽  
Practice Effects ◽  
Aging Brain ◽  
Amyloid Burden ◽  
Preclinical Ad ◽  
At Home

Introduction: We investigated whether monthly assessments of a computerized cognitive composite (C3) could aid in the detection of differences in practice effects (PE) in clinically unimpaired (CU) older adults, and whether diminished PE were associated with Alzheimer's disease (AD) biomarkers and annual cognitive decline.Materials and Methods:N = 114 CU participants (age 77.6 ± 5.0, 61% female, MMSE 29 ± 1.2) from the Harvard Aging Brain Study completed the self-administered C3 monthly, at-home, on an iPad for one year. At baseline, participants underwent in-clinic Preclinical Alzheimer's Cognitive Composite-5 (PACC5) testing, and a subsample (n = 72, age = 77.8 ± 4.9, 59% female, MMSE 29 ± 1.3) had 1-year follow-up in-clinic PACC5 testing available. Participants had undergone PIB-PET imaging (0.99 ± 1.6 years before at-home baseline) and Flortaucipir PET imaging (n = 105, 0.62 ± 1.1 years before at-home baseline). Linear mixed models were used to investigate change over months on the C3 adjusting for age, sex, and years of education, and to extract individual covariate-adjusted slopes over the first 3 months. We investigated the association of 3-month C3 slopes with global amyloid burden and tau deposition in eight predefined regions of interest, and conducted Receiver Operating Characteristic analyses to examine how accurately 3-month C3 slopes could identify individuals that showed &gt;0.10 SD annual decline on the PACC-5.Results: Overall, individuals improved on all C3 measures over 12 months (β = 0.23, 95% CI [0.21–0.25], p &lt; 0.001), but improvement over the first 3 months was greatest (β = 0.68, 95% CI [0.59–0.77], p &lt; 0.001), suggesting stronger PE over initial repeated exposures. However, lower PE over 3 months were associated with more global amyloid burden (r = −0.20, 95% CI [−0.38 – −0.01], p = 0.049) and tau deposition in the entorhinal cortex (r = −0.38, 95% CI [−0.54 – −0.19], p &lt; 0.001) and inferior-temporal lobe (r = −0.23, 95% CI [−0.41 – −0.02], p = 0.03). 3-month C3 slopes exhibited good discriminative ability to identify PACC-5 decliners (AUC 0.91, 95% CI [0.84–0.98]), which was better than baseline C3 (p &lt; 0.001) and baseline PACC-5 scores (p = 0.02).Conclusion: While PE are commonly observed among CU adults, diminished PE over monthly cognitive testing are associated with greater AD biomarker burden and cognitive decline. Our findings imply that unsupervised computerized testing using monthly retest paradigms can provide rapid detection of diminished PE indicative of future cognitive decline in preclinical AD.

scholarly journals Evidence for Reduced Autobiographical Memory Episodic Specificity in Cognitively Normal Middle-Aged and Older Individuals at Increased Risk for Alzheimer’s Disease Dementia

2018 ◽  
Vol 24 (10) ◽  
pp. 1073-1083 ◽  
Author(s):  
Matthew D. Grilli ◽  
Aubrey A. Wank ◽  
John J. Bercel ◽  
Lee Ryan
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Decline ◽  
Older Individuals ◽  
Autobiographical Memories ◽  
Middle Aged ◽  
Cognitively Normal ◽  
Preclinical Ad ◽  
Increased Risk ◽  
And Gender

AbstractObjectives: Alzheimer’s disease (AD) typically eludes clinical detection for years, if not decades. The identification of subtle cognitive decline associated with preclinical AD would not only advance understanding of the disease, but also provide clinical targets to assess preventative and early intervention treatments. Disrupted retrieval of detailed episodic autobiographical memories may be a sensitive indicator of subtle cognitive decline, because this type of memory taxes a core neural network affected by preclinical AD neuropathology. Methods: To begin to address this idea, we assessed the episodic specificity of autobiographical memories retrieved by cognitively normal middle-aged and older individuals who are carriers of the apolipoprotein E ε4 allele – a population at increased risk for subtle cognitive decline related to neuropathological risk factors for AD. We compared the ε4 carriers to non-carriers of ε4 similar in age, education, and gender. Results: The ε4 carriers did not perform worse than the non-carriers on a comprehensive battery of neuropsychological tests. In contrast, as a group, the ε4 carriers generated autobiographical memories that were reduced in “internal” or episodic details relative to non-carriers. Conclusions: These findings support the notion that reduced autobiographical episodic detail generation may be a marker of subtle cognitive decline associated with AD. (JINS, 2018, 24, 1073–1183)

A Magnetic Resonance Imaging Study of White Matter Lesions in Depression and Alzheimer's Disease

1996 ◽  
Vol 168 (4) ◽  
pp. 477-485 ◽  
Author(s):  
John O'brien ◽  
Patricia Desmond ◽  
David Ames ◽  
Isaac Schweitzer ◽  
Susan Harrigan ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
White Matter ◽  
Magnetic Resonance ◽  
Imaging Study ◽  
White Matter Lesions ◽  
Elderly Subjects ◽  
Resonance Imaging ◽  
Mri Scans

BackgroundWhite matter changes, as revealed by magnetic resonance imaging (MRI), may occur in depression and Alzheimer's disease.MethodT2-weighted MRI scans were performed in 39 control subjects, 61 subjects with NINCDS/ADRDA Alzheimer's disease and 60 subjects with DSM–III–R major depression. Deep white matter lesions (DWML) and periventricular lesions (PVL) were rated on a standard 0–3 scale by two radiologists blind to clinical diagnosis.ResultsAfter controlling for differences in vascular risk factors and current blood pressure, DWML were significantly more common in depressed subjects and PVL in Alzheimer's disease subjects compared to controls. DWML were most common in those presenting in late life with their first ever depression and 50% of such subjects had severe (grade 3) DWML.ConclusionAn association between DWML and depression and PVL and Alzheimer's disease is supported. The increase with DWML that occurs with ageing may predispose some elderly subjects to depression.

scholarly journals Genetic Effects on Longitudinal Cognitive Decline During the Early Stages of Alzheimer's Disease

2021 ◽  
Author(s):  
Atul Kumar ◽  
Maryam Shoai ◽  
Sebastian Palmqvist ◽  
Erik Stomrud ◽  
John Hardy ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Decline ◽  
Genome Wide Association Study ◽  
Early Stage ◽  
Cognitive Change ◽  
Preclinical Ad ◽  
Genome Wide ◽  
A Genome ◽  
Polygenic Scores

Abstract Background Cognitive decline in early-stage Alzheimer’s disease (AD) may depend on genetic variability. Methods In the Swedish BioFINDER study, we used polygenic scores (PGS) (for AD, intelligence and educational attainment), and genetic variants (in a genome-wide association study [GWAS]) to predict longitudinal cognitive change (measured by MMSE) over a mean of 4.2 years. We included 555 β-amyloid (Aβ) negative cognitively unimpaired (CU) individuals, 206 Aβ-positive CU (preclinical AD), 110 Aβ-negative mild cognitive impairment (MCI) patients, and 146 Aβ-positive MCI patients (prodromal AD). Results Polygenic scores for AD (in Aβ-positive individuals) and intelligence (independent of Aβ-status) were associated with cognitive decline. Eight genes were associated with cognitive decline in GWAS (3 independent of Aβ-status). Conclusions AD risk genes may influence cognitive decline in early AD, while genes related to intelligence may modulate cognitive decline irrespective of disease. Therapies targeting the implicated biological pathways may modulate the clinical course of AD.

scholarly journals Associations of AT(N) biomarkers with neuropsychiatric symptoms in preclinical Alzheimer’s disease and cognitively unimpaired individuals

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Kok Pin Ng ◽  
Hui Chiew ◽  
Pedro Rosa-Neto ◽  
Nagaendran Kandiah ◽  
Zahinoor Ismail ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Decline ◽  
Longitudinal Studies ◽  
Neuropsychiatric Symptoms ◽  
Amyloid Β ◽  
Cross Sectional ◽  
Preclinical Ad ◽  
Cross Sectional Studies

AbstractThe development of in vivo biomarkers of Alzheimer’s disease (AD) has advanced the diagnosis of AD from a clinical syndrome to a biological construct. The preclinical stage of AD continuum is defined by the identification of AD biomarkers crossing the pathological threshold in cognitively unimpaired individuals. While neuropsychiatric symptoms (NPS) are non-cognitive symptoms that are increasingly recognized as early manifestations of AD, the associations of NPS with AD pathophysiology in preclinical AD remain unclear. Here, we review the associations between NPS and AD biomarkers amyloid-β (Aβ), tau and neurodegeneration in preclinical AD and cognitively-unimpaired individuals in 19 eligible English-language publications (8 cross-sectional studies, 10 longitudinal, 1 both cross-sectional and longitudinal). The cross-sectional studies have consistently shown that NPS, particularly depressive and anxiety symptoms, are associated with higher Aβ. The longitudinal studies have suggested that greater NPS are associated with higher Aβ and cognitive decline in cognitively unimpaired subjects over time. However, most of the studies have either cross-sectionally or longitudinally shown no association between NPS and tau pathology. For the association of NPS and neurodegeneration, two studies have shown that the cerebrospinal fluid total-tau is linked to longitudinal increase in NPS and that the NPS may predict longitudinal metabolic decline in preclinical AD, respectively. However, evidence for the association between atrophy and NPS in preclinical AD is less consistent. Therefore, future longitudinal studies with well-designed methodologies and NPS measurements are required not only to determine the relationship among AT(N) biomarkers, NPS and cognitive decline, but also to elucidate the contribution of comorbid pathology to preclinical AD.

scholarly journals Enhancing magnetic resonance imaging-driven Alzheimer’s disease classification performance using generative adversarial learning

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Xiao Zhou ◽  
Shangran Qiu ◽  
Prajakta S. Joshi ◽  
Chonghua Xue ◽  
Ronald J. Killiany ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Magnetic Resonance ◽  
Image Quality ◽  
Classification Performance ◽  
Resonance Imaging ◽  
Mri Scans ◽  
The Mean

Abstract Background Generative adversarial networks (GAN) can produce images of improved quality but their ability to augment image-based classification is not fully explored. We evaluated if a modified GAN can learn from magnetic resonance imaging (MRI) scans of multiple magnetic field strengths to enhance Alzheimer’s disease (AD) classification performance. Methods T1-weighted brain MRI scans from 151 participants of the Alzheimer’s Disease Neuroimaging Initiative (ADNI), who underwent both 1.5-Tesla (1.5-T) and 3-Tesla imaging at the same time were selected to construct a GAN model. This model was trained along with a three-dimensional fully convolutional network (FCN) using the generated images (3T*) as inputs to predict AD status. Quality of the generated images was evaluated using signal to noise ratio (SNR), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) and Natural Image Quality Evaluator (NIQE). Cases from the Australian Imaging, Biomarker & Lifestyle Flagship Study of Ageing (AIBL, n = 107) and the National Alzheimer’s Coordinating Center (NACC, n = 565) were used for model validation. Results The 3T*-based FCN classifier performed better than the FCN model trained using the 1.5-T scans. Specifically, the mean area under curve increased from 0.907 to 0.932, from 0.934 to 0.940, and from 0.870 to 0.907 on the ADNI test, AIBL, and NACC datasets, respectively. Additionally, we found that the mean quality of the generated (3T*) images was consistently higher than the 1.5-T images, as measured using SNR, BRISQUE, and NIQE on the validation datasets. Conclusion This study demonstrates a proof of principle that GAN frameworks can be constructed to augment AD classification performance and improve image quality.

Sign in / Sign up

Export Citation Format

Share Document