Dataset Information

Robust Identification of Alzheimer's Disease subtypes based on cortical atrophy patterns.

ABSTRACT: Accumulating evidence suggests that Alzheimer's disease (AD) is heterogenous and can be classified into several subtypes. Here, we propose a robust subtyping method for AD based on cortical atrophy patterns and graph theory. We calculated similarities between subjects in their atrophy patterns throughout the whole brain, and clustered subjects with similar atrophy patterns using the Louvain method for modular organization extraction. We applied our method to AD patients recruited at Samsung Medical Center and externally validated our method by using the AD Neuroimaging Initiative (ADNI) dataset. Our method categorized very mild AD into three clinically distinct subtypes with high reproducibility (>90%); the parietal-predominant (P), medial temporal-predominant (MT), and diffuse (D) atrophy subtype. The P subtype showed the worst clinical presentation throughout the cognitive domains, while the MT and D subtypes exhibited relatively mild presentation. The MT subtype revealed more impaired language and executive function compared to the D subtype.

SUBMITTER: Park JY

PROVIDER: S-EPMC5343676 | biostudies-literature | 2017 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Robust Identification of Alzheimer's Disease subtypes based on cortical atrophy patterns.

Park Jong-Yun JY Na Han Kyu HK Kim Sungsoo S Kim Hyunwook H Kim Hee Jin HJ Seo Sang Won SW Na Duk L DL Han Cheol E CE Seong Joon-Kyung JK

Scientific reports 20170309

Accumulating evidence suggests that Alzheimer's disease (AD) is heterogenous and can be classified into several subtypes. Here, we propose a robust subtyping method for AD based on cortical atrophy patterns and graph theory. We calculated similarities between subjects in their atrophy patterns throughout the whole brain, and clustered subjects with similar atrophy patterns using the Louvain method for modular organization extraction. We applied our method to AD patients recruited at Samsung Medi ...[more]

PMID: 28276464

Similar Datasets

Project description:ObjectivesTo investigate the global cortical and regional quantitative features of cortical neural architecture in the brains of patients with posterior cortical atrophy (PCA) and typical Alzheimer's disease (tAD) compared with elderly healthy controls (HC).MethodsA novel diffusion MRI method, that has been shown to correlate with minicolumnar organization changes in the cerebral cortex, was used as a surrogate of neuropathological changes in dementia. A cohort of 15 PCA patients, 23 tAD and 22 healthy elderly controls (HC) were enrolled to investigate the changes in cortical diffusivity among groups. For each subject, 3 T MRI T1-weighted images and diffusion tensor imaging (DTI) scans were analysed to extract novel cortical DTI derived measures (AngleR, PerpPD and ParlPD). Receiver operating characteristics (ROC) curve analysis and the area under the curve (AUC) were used to assess the group discrimination capability of the method.ResultsThe results showed that the global cortical DTI derived measures were able to detect differences, in both PCA and tAD patients compared to healthy controls. The AngleR was the best measure to discriminate HC from tAD (AUC?=?0.922), while PerpPD was the best measure to discriminate HC from PCA (AUC?=?0.961). Finally, the best global measure to differentiate the two patient groups was ParlPD (AUC?=?0.771). The comparison between PCA and tAD patients revealed a different pattern of damage within the AD spectrum and the regional comparisons identified significant differences in key regions including parietal and temporal lobe cortical areas. The best AUCs were shown by PerpPD right lingual cortex (AUC?=?0.856), PerpPD right superior parietal cortex (AUC?=?0.842) and ParlPD right lateral occipital cortex (AUC?=?0.826).ConclusionsDiagnostic group differences were found, suggesting that the new cortical DTI analysis method may be useful to investigate cortical changes in dementia, providing better characterization of neurodegeneration, and potentially aiding differential diagnosis and prognostic accuracy.

Project description:IntroductionIn vivo clinical, anatomical and metabolic differences between posterior cortical atrophy (PCA) patients presenting with different Alzheimer's disease (AD) cerebrospinal fluid (CSF) biomarkers profiles are still unknown.MethodsTwenty-seven PCA patients underwent CSF examination and were classified as 1) PCA with a typical CSF AD profile (PCA-tAD; abnormal amyloid and T-tau/P-tau biomarkers, n = 13); 2) PCA with an atypical AD CSF profile (PCA-aAD; abnormal amyloid biomarker only, n = 9); and 3) PCA not associated with AD (PCA-nonAD; normal biomarkers, n = 5). All patients underwent clinical and cognitive assessment, structural MRI, and a subset of them underwent brain 18F-FDG PET.ResultsAll patients' groups showed a common pattern of posterior GM atrophy and hypometabolism typical of PCA, as well as equivalent demographics and clinical/cognitive profiles. PCA-tAD patients showed a group-specific pattern of hypometabolism in the left fusiform gyrus and inferior temporal gyrus. PCA-aAD did not present a group-specific atrophy pattern. Finally, group-specific gray matter atrophy in the right dorsolateral prefrontal cortex, left caudate nucleus and right medial temporal regions and hypometabolism in the right supplementary motor area and paracentral lobule were observed in PCA-nonAD patients.ConclusionOur findings suggest that both PCA-tAD and PCA-aAD patients are on the AD continuum, in agreement with the recently suggested A/T/N model. Furthermore, in PCA, the underlying pathology has an impact at least on the anatomo-functional presentation. Brain damage observed in PCA-tAD and PCA-aAD was mostly consistent with the well-described presentation of the disease, although it was more widespread in PCA-tAD group, especially in the left temporal lobe. Additional fronto-temporal (especially dorsolateral prefrontal) damage seems to be a clue to underlying non-AD pathology in PCA, which warrants the need for longitudinal follow-ups to investigate frontal symptoms in these patients.

Project description:Introduction: It has been shown that Alzheimer's disease (AD) is accompanied by marked structural brain changes that can be detected several years before clinical diagnosis via structural magnetic resonance (MR) imaging. In this study, we developed a structural MR-based biomarker for in vivo detection of AD using a supervised machine learning approach. Based on an individual's pattern of brain atrophy a continuous AD score is assigned which measures the similarity with brain atrophy patterns seen in clinical cases of AD. Methods: The underlying statistical model was trained with MR scans of patients and healthy controls from the Alzheimer's Disease Neuroimaging Initiative (ADNI-1 screening). Validation was performed within ADNI-1 and in an independent patient sample from the Open Access Series of Imaging Studies (OASIS-1). In addition, our analyses included data from a large general population sample of the Study of Health in Pomerania (SHIP-Trend). Results: Based on the proposed AD score we were able to differentiate patients from healthy controls in ADNI-1 and OASIS-1 with an accuracy of 89% (AUC = 95%) and 87% (AUC = 93%), respectively. Moreover, we found the AD score to be significantly associated with cognitive functioning as assessed by the Mini-Mental State Examination in the OASIS-1 sample after correcting for diagnosis, age, sex, age·sex, and total intracranial volume (Cohen's f2 = 0.13). Additional analyses showed that the prediction accuracy of AD status based on both the AD score and the MMSE score is significantly higher than when using just one of them. In SHIP-Trend we found the AD score to be weakly but significantly associated with a test of verbal memory consisting of an immediate and a delayed word list recall (again after correcting for age, sex, age·sex, and total intracranial volume, Cohen's f2 = 0.009). This association was mainly driven by the immediate recall performance. Discussion: In summary, our proposed biomarker well differentiated between patients and healthy controls in an independent test sample. It was associated with measures of cognitive functioning both in a patient sample and a general population sample. Our approach might be useful for defining robust MR-based biomarkers for other neurodegenerative diseases, too.

Dataset Information

Robust Identification of Alzheimer's Disease subtypes based on cortical atrophy patterns.

Publications

Robust Identification of Alzheimer's Disease subtypes based on cortical atrophy patterns.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets