Multi-Modal Multi-Task Learning for Joint Prediction of Multiple Regression and Classification Variables in Alzheimer’s Disease

By Daoqiang Zhang, Dinggang Shen. NeuroImage, 2011

647 citations recorded by the source corpus.

Many machine learning and pattern classification methods have been applied to the diagnosis of Alzheimer’s disease (AD) and its prodromal stage, i.e., mild cognitive impairment (MCI). Recently, rather than predicting categorical variables as in classification, several pattern regression methods have also been used to estimate continuous clinical variables from brain images. However, most existing regression methods focus on estimating multiple clinical variables separately and thus cannot utilize the intrinsic useful correlation information among different clinical variables. On the other hand, in those regression methods, only a single modality of data (usually only the structural MRI) is often used, without considering the complementary information that can be provided by different modalities. In this paper, we propose a general methodology, namely Multi-Modal Multi-Task (M3T) learning, to jointly predict multiple variables from multi-modal data. Here, the variables include not only the clinical variables used for regression but also the categorical variable used for classification, with different tasks corresponding to prediction of different variables. Specifically, our method contains two key components, i.e., (1) a multi-task feature selection which selects the common subset of relevant features for multiple variables from each modality, and (2) a multi-modal support vector machine which fuses the above-selected features from all modalities to predict multiple (regression and classification) variables. To validate our method, we perform two sets of experiments on ADNI baseline MRI, FDG-PET, and cerebrospinal fluid (CSF) data from 45 AD patients, 91 MCI patients, and 50 healthy controls (HC). In the first set of experiments, we estimate two clinical variables such as Mini Mental State Examination (MMSE) and Alzheimer’s Disease Assessment Scale - Cognitive Subscale (ADAS-Cog), as well as one categorical variable (with value of ‘AD’, ‘MCI’ or ‘HC’), from the baseline MRI, FDG-PET, and CSF data. In the second set of experiments, we predict the 2-year changes of MMSE and ADAS-Cog scores and also the conversion of MCI to AD from the baseline MRI, FDG-PET, and CSF data. The results on both sets of experiments demonstrate that our proposed M3T learning scheme can achieve better performance on both regression and classification tasks than the conventional learning methods.

Subfields: Neurology, Psychiatry and Mental health

View Paper: https://www.semanticscholar.org/paper/2df4b0f177195b697facf4769a0530dddad4d69d

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

Learning Transferable Knowledge Through Embedding Spaces (2019, background): “• Local data processing can be inevitable in some applications, such as when health care regulations prevent personal medical data from being shared between learning systems [234].”
A Survey on ensemble learning under the era of deep learning (2021, methodology): “Based on the extracted features, sparse regression model (SRM) (Wang et al. 2011; Zhang and Shen 2012) was utilized to train multiple base learners with different values of the regularization control parameter.”
Not‐so‐supervised: A survey of semi‐supervised, multi‐instance, and transfer learning in medical image analysis (2018, background): “Using multiple labels for the same samples can be seen in (Zhang and Shen, 2012).”
On Better Exploring and Exploiting Task Relationships in Multitask Learning: Joint Model and Feature Learning (2018, background): “Consider the merits of multi-task learning, it has been applied to various research areas, for example, web image search [1], video tracking [2], disease prediction [3], and relative attributes learning [4].”
Multi-Agent Distributed Lifelong Learning for Collective Knowledge Acquisition (2017, neutral): “• Local data processing can be inevitable in some applications, such as when health care regulations prevent personal medical data from being shared between learning systems [38].”
High-Order Multi-Task Feature Learning to Identify Longitudinal Phenotypic Markers for Alzheimer's Disease Progression Prediction (2012, background): “Neuroimaging measures have be en widely studied to predict disease status and/or cognitive performance [1, 2, 3, 4, 5, 6, 7].”
Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis (2014, neutral): “…unlike the previous approaches (Hinrichs et al., 2011; Kohannim et al., 2010; Liu et al., 2012, 2013; Walhovd et al., 2010; Westman et al., 2012; Zhang and Shen, 2012; Zhang et al., 2011) that considered simple low-level features, which are often vulnerable to noises, we propose to consider…”
Deep ensemble learning of sparse regression models for brain disease diagnosis (2017, methodology): “To validate the effectiveness of the proposed method, we ompared our method with the two baseline sparse regression odels and their variants of the following methods • MOLR+SVM: This method first finds the optimal weight coef- ficients ˆ W in Eq.”
A review on neuroimaging‐based classification studies and associated feature extraction methods for Alzheimer's disease and its prodromal stages (2017, neutral): “(Zhang and Shen, 2012) 45 91 – – 50 SFS Multi-kernel SVM ADNI 93.”
Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks (2015, background): “MTL has demonstrated good results in many applications, such as disease prediction [39], [40] and ﬁnancial stock selection [41].”
Modeling disease progression via multi-task learning (2013, neutral): “The lack of predictable MRI biomarkers in later stages is a potential factor that contributes to the lower prediction performance of MMSE than that of ADAS-Cog in our study and other related studies (Stonnington et al., 2010; Zhang and Shen, 2011).”