Skip to main content

Table 1 Brief review of multi-modal data fusion methods from the literature and methodologies that have been used

From: Dimensionality reduction-based fusion approaches for imaging and non-imaging biomedical data: concepts, workflow, and use-cases

Reference Data Method
Moutselos et al. [65] Skin images Combining features into a confusion matrix
  Gene expression  
Golugula et al. [6] Histopathology Correlating features via CCA, combining CCA-based confusion matrices
Dai et al. [20] sMRI Construct classifiers from features, weighted combination of classifier decisions
Gode et al. [66] mRNA Compute LDR/classifier decisions, unweighted combination of LDR- or classifier-based confusion matrices
Raza et al. [22] Gene-expression Compute classifier decisions, unweighted combination of classifier decisions
Sui et al. [67] DTI Correlate features via CCA, unweighted combination of CCA-based confusion matrices
Wolz et al. [7] T1-w MRI Compute LDR, weighted combination of LDR-based confusion matrices
  ApoE genotype, A β 1−42  
Wang et al. [62] T1-w MRI, FDG-PET Feature selection, weighted concatenation of selected features
Lanckriet et al. [9] Protein expression Compute kernel representations, weighted combination of kernels
Yu et al. [68] Text ontologies Compute kernel representations, fuse kernel-based confusion matrices
Higgs et al. [54] CT Compute LDR, fuse LDR maintaining manifold structure
Lee et al. [4] Gene-expression Compute LDR, unweighted concatenation of LDR
Viswanath et al. [5] T2-w Compute LDR, combine LDR-based confusion matrices using label information
  ADC, DCE  
Tiwari et al [8] T2-w MRI Compute kernel representations, weighted LDR-based combination of kernels using label information
  1. CCA Canonical Correlation Analysis, LDR Low-Dimensional Representation. See Description of methods utilized for multi-modal data fusion section for more details