Prediction of MCI to AD conversion, via MRI, CSF biomarkers, pattern classification

By Christos Davatzikos, Priyanka Bhatt, Leslie M. Shaw, Kayhan Batmanghelich, John Q. Trojanowski. 2010

614 citations recorded by the source corpus.

MRI patterns were examined together with cerebrospinal fluid (CSF) biomarkers in serial scans of ADNI participants with mild cognitive impairment (MCI). The SPARE-AD score, summarizing brain atrophy patterns, was tested as predictor of short-term conversion to AD. MCI individuals that converted to AD (MCI-C) had mostly positive baseline SPARE-AD and atrophy in temporal lobe grey (GM) and white (WM) matter, posterior cingulate/precuneous, insula. MCI-C had mostly AD-like baseline CSF biomarkers. MCI non-converters (MCI-NC) had mixed baseline SPARE-AD and CSF values, suggesting that some MCI-NC subjects may later convert. Those MCI-NC with most negative baseline SPARE-AD scores (normal brain structure) had significantly higher baseline MMSE scores (28.67) than others, and relatively low annual rate of MMSE decrease (−0.25). MCI-NC with mid-level baseline SPARE-AD displayed faster annual rates of SPARE-AD increase (indicating progressing atrophy). SPARE-AD and CSF combination improved prediction over individual values. In summary, both SPARE-AD and CSF biomarkers showed high baseline sensitivity, however, many MCI-NC had abnormal baseline SPARE-AD and CSF biomarkers. Longer follow-up will elucidate the specificity of baseline measurements.

Subfields: Cognitive Neuroscience, Psychiatry and Mental health, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Psychiatry and Mental health

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Interpreting support vector machine models for multivariate group wise analysis in neuroimaging (2015, positive): “SVM Wang et al. (2007) Cuingnet et al. (2011) Craddock et al. (2009) Fan et al. (2007) Batmanghelich et al. (2012) Vemuri et al. (2008) Davatzikos et al. (2011) Mouro-Miranda et al. (2005) based tools for imaging based diagnoses came a little later and addressed a paradigm completely different from…”
Machine learning framework for early MRI-based Alzheimer’s conversion prediction in MCI subjects (2014, neutral): “…positron emission tomography (PET) (Zhang and Shen, 2011, 2012; Cheng et al., 2012; Shaffer et al., 2013), cerebrospinal ﬂ uid (CSF) biomarkers (Zhang and Shen, 2011; Cheng et al., 2012; Davatzikos et al., 2011; Shaffer et al., 2013), and demographic and cognitive information (see Tables 1 and 7).”
A review on neuroimaging‐based classification studies and associated feature extraction methods for Alzheimer's disease and its prodromal stages (2017, positive): “(Davatzikos et al., 2011) – – 69 170 – SFC SVM ADNI – – – 61.”
Multimodal Classification of Alzheimer’s Disease and Mild Cognitive Impairment (2011, methodology): “Specifically, ADNI baseline MRI, FDG-PET, and CSF data from 51 AD patients, 99 MCI patients (including 43 MCI converters who had converted to AD within 18 months and 56 MCI non-converters who had not converted to AD within 18 months), and 52 healthy controls are used for development and validation…”
Deep Learning-Based Feature Representation for AD/MCI Classification (2013, methodology): “Researchers in many scientific fields have devoted their efforts to understand the underlying mechanism that causes these diseases and to identify pathological biomarkers for diagnosis or prognosis of AD/MCI by analyzing different types of imaging modalities, such as Magnetic Resonance Imaging (MRI)”
Multi-Modal Neuroimaging Feature Learning for Multi-Class Diagnosis of Alzheimer’s Disease (2014, methodology): “[7] R. Cuingnet et al., “Automatic classification of patients with Alzheimer’s disease from structural MRI: A comparison of ten methods using the ADNI database,” Neuroimage, vol. 56, no. 2, pp. 766–781, 2011.”
Ensemble Sparse Classification of Alzheimer’s Disease (2012, methodology): “…positron emission tomography (FDG-PET) are powerful imaging tools in helping understand the neural changes related to the neurodegenerative disorder of AD (Chan et al., 2003; Davatzikos et al., 2010; Fan et al., 2008a; Hinrichs et al., 2009; Magnin et al., 2009; Mueller et al., 2005).”
Deep ensemble learning of sparse regression models for brain disease diagnosis (2017, methodology): “…whose list is provided in Table B1 , by warping the atlas of Kabani et al. (1998) , which has been widely used for AD/MCI diagnosis studies ( Davatzikos et al., 2011; Negash et al., 2013; Suk et al., 2015a ) to each subject’s space via HAMMER ( Shen and Davatzikos, 2002 ), although many…”
Latent feature representation with stacked auto-encoder for AD/MCI diagnosis (2013, methodology): “…(Schroeter et al. 2009; Nobili et al. 2013; Yao et al. 2012), superior parietal lobule, precuneus, cuneus (Bokde et al. 2006; Singh et al. 2006; Davatzikos et al. 2011), cingulate region (Mosconi 2005), anterior limb of internal capsule (Zhang et al. 2009), caudate nucleus (Dai et al. 2009),…”
Identification of MCI Individuals Using Structural and Functional Connectivity Networks (2011, result): “The regions selected in the course of classification by our method are in agreement with previous studies and include the prefrontal cortex and or-bitofrontal cortex [14], temporal pole [13], anterior and posterior cingulate gyrus, precuneus and insula [8], amygdala [7], thalamus [30], parahippocamp”
Analytic estimation of statistical significance maps for support vector machine based multi-variate image analysis and classification (2013, positive): “The authors of Davatzikos et al. (2011) preprocessed raw T1-structural MR images using a pipeline that involved skull stripping using BET (Smith, 2002), followed by bias correction using N3 (Sled et al., 1998) and segmentation into the gray matter (GM), white matter(WM) and ventricular(VN) CSF…”
Multi-Modal Multi-Task Learning for Joint Prediction of Multiple Regression and Classification Variables in Alzheimer’s Disease (2011, methodology): “In (Davatzikos et al., 2010), the maximum accuracy of 0.617 and AUC of 0.734 were reported on 69 MCI-C and 170 MCI-NC using both MRI and CSF data.”
Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis (2014, neutral): “ROI-based approach considers the structurally or functionally predefined brain regions and extracts representative features from each region (Cuingnet et al., 2011; Davatzikos et al., 2011; Kohannim et al., 2010; Nordberg et al., 2010; Suk and Shen, 2013; Walhovd et al., 2010; Zhang and Shen, 2012).”