Predictive Markers for AD in a Multi-Modality Framework: An Analysis of MCI Progression in the ADNI Population

By Chris Hinrichs, Vikas Singh, Guofan Xu, Sterling C. Johnson. NeuroImage, 2010

435 citations recorded by the source corpus.

Alzheimer’s Disease (AD) and other neurodegenerative diseases affect over 20 million people worldwide, and this number is projected to significantly increase in the coming decades. Proposed imaging-based markers have shown steadily improving levels of sensitivity/specificity in classifying individual subjects as AD or normal. Several of these efforts have utilized statistical machine learning techniques, using brain images as input, as means of deriving such AD-related markers. A common characteristic of this line of research is a focus on either (1) using a single imaging modality for classification, or (2) incorporating several modalities, but reporting separate results for each. One strategy to improve on the success of these methods is to leverage all available imaging modalities together in a single automated learning framework. The rationale is that some subjects may show signs of pathology in one modality but not in another – by combining all available images a clearer view of the progression of disease pathology will emerge. Our method is based on the Multi-Kernel Learning (MKL) framework, which allows the inclusion of an arbitrary number of views of the data in a maximum margin, kernel learning framework. The principal innovation behind MKL is that it learns an optimal combination of kernel (similarity) matrices while simultaneously training a classifier. In classification experiments MKL outperformed an SVM trained on all available features by 3% – 4%. We are especially interested in whether such markers are capable of identifying early signs of the disease. To address this question, we have examined whether our multi-modal disease marker (MMDM) can predict conversion from Mild Cognitive Impairment (MCI) to AD. Our experiments reveal that this measure shows significant group differences between MCI subjects who progressed to AD, and those who remained stable for 3 years. These differences were most significant in MMDMs based on imaging data. We also discuss the relationship between our MMDM and an individual’s conversion from MCI to AD.

Subfields: Neurology, Psychiatry and Mental health

View Paper: https://www.semanticscholar.org/paper/bbcf8bbe9247b326465d1d42483bbadf1c0e9b59

How researchers see this paper

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

In Neurology

In Psychiatry and Mental health

Citations in the corpus

Deep ensemble learning of sparse regression models for brain disease diagnosis (2017, methodology): “is widely used in the field for AD/MCI diagnosis (Davatzikos et al., 2011; Hinrichs et al., 2011; Zhang and Shen, 2012; Suk et al., 2015a), as features, i.”
Single Subject Prediction of Brain Disorders in Neuroimaging: Promises and Pitfalls (2016, background): “…= 163, Total = 319 76.5–90.1% Yun et al. (2015) t2:99 sMRI, FDG-PET AD/MCI GM and WM maps from sMRI and FDG-PET images Variable Multi-kernel learning HC = 66, AD = 48, MCI = 119, Total = 233 87.6% Hinrichs et al. (2011) t2:100 sMRI, FDG-PET t2:101 and Florbetapir PET AD/MCI Mean volume of GM,…”
Identifying Neuroimaging and Proteomic Biomarkers for MCI and AD via the Elastic Net (2011, background): “, [7,16]) and see if better predictive models can be achieved and relevant biomarkers can be identified.”
Machine learning framework for early MRI-based Alzheimer’s conversion prediction in MCI subjects (2014, neutral): “…patients in different disease stages (Fan et al., 2008; Duchesne et al., 2008; Chupin et al., 2009; Querbes et al., 2009; Wolz et al., 2011; Hinrichs et al., 2011; Westman et al., 2011a,b; Westman et al., 2012; Cho et al., 2012; Coupé et al., 2012; Gray et al., 2013; Eskildsen et al., 2013;…”
Multimodal Neuroimaging Feature Learning With Multimodal Stacked Deep Polynomial Networks for Diagnosis of Alzheimer's Disease (2018, methodology): “In this work, we adopt MRI and PET as two neuroimaging modalities, which are commonly used in multimodal neuroimaging based AD classification [13]–[18], [38].”
Multi-Modal Multi-Task Learning for Joint Prediction of Multiple Regression and Classification Variables in Alzheimer’s Disease (2011, methodology): “More recently, multiple-kernel method is used for multi-modal data fusion and classification, and achieves better performance than the baseline feature concatenation method (Hinrichs et al., 2011; Zhang et al., 2011).”
Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis (2014, positive): “We argue that this joint feature representation discriminates our method from the previous multimodal methods (Hinrichs et al., 2011; Suk and Shen, 2013; Zhang et al., 2011), which first extracted features from each modality independently, and then combined them through kernel machines.”
Latent feature representation with stacked auto-encoder for AD/MCI diagnosis (2013, methodology): “…data for discriminating AD/MCI patients from healthy normal controls (HC) (Fan et al. 2007; Perrin et al. 2009; Kohannim et al. 2010; Walhovd et al. 2010; Cui et al. 2011; Hinrichs et al. 2011; Zhang et al. 2011; Wee et al. 2012; Westman et al. 2012; Yuan et al. 2012; Zhang and Shen 2012).”
Imaging based enrichment criteria using deep learning algorithms for efficient clinical trials in MCI (2015, methodology): “Furthermore, CSF cannot be used in practice as a screening instrument because assays typically need to be performed in a single batch and are highly laboratory speciﬁc [12].”
Multimodal Classification of Alzheimer’s Disease and Mild Cognitive Impairment (2011, methodology): “It’s worth noting that, in (Hinrichs et al., 2010), both baseline and longitudinal data are used for MRI and PET modalities, while the proposed method uses only the baseline data.”
Random forest-based similarity measures for multi-modal classification of Alzheimer's disease (2013, positive): “This finding is in agreement with other recent studies (Hinrichs et al., 2011; Zhang et al., 2011), and supports previous suggestions that there is some complementary information between modalities which can be exploited to produce more powerful combined classifiers (Landau et al.”
Deep Learning-Based Feature Representation for AD/MCI Classification (2013, methodology): “For each ROI, we used the gray matter tissue volume from MRI and the mean intensity from PET as features, which are most widely used in the field for AD/MCI diagnosis [3,6,13].”
A review on neuroimaging‐based classification studies and associated feature extraction methods for Alzheimer's disease and its prodromal stages (2017, neutral): “In earlier studies, Hinrichs et al. (2011) used structural MRI-based density maps, FDG-PET intensities, CSF biomarkers, APOE genotype, and neuropsychological status exam scores as features for multi-kernel SVM-based AD classification, and AD conversion prediction.”