Semi-Supervised Multimodal Relevance Vector Regression Improves Cognitive Performance Estimation from Imaging and Biological Biomarkers

• Published in: Neuroinformatics (Totowa, N.J.) N.J.), 2013-07, Vol.11 (3), p.339-353
• Main Authors: Cheng, Bo, Zhang, Daoqiang, Chen, Songcan, Kaufer, Daniel I., Shen, Dinggang
• Format: Article
• Language: English
• Subjects: Aged; Aged, 80 and over; Alzheimer Disease - cerebrospinal fluid; Alzheimer Disease - diagnosis; Applied sciences; Artificial Intelligence; Bioinformatics; Biological and medical sciences; Biomarkers - cerebrospinal fluid; Biomedical and Life Sciences; Biomedicine; Brain Mapping; Cognition Disorders - cerebrospinal fluid; Cognition Disorders - diagnosis; Computational Biology/Bioinformatics; Computer Appl. in Life Sciences; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Databases, Factual - statistics & numerical data; Exact sciences and technology; Female; Fluorodeoxyglucose F18; Humans; Investigative techniques, diagnostic techniques (general aspects); Magnetic Resonance Imaging; Male; Medical sciences; Mental Status Schedule; Middle Aged; National Institutes of Health (U.S.); Nervous system; Neurology; Neuropsychological Tests; Neurosciences; Original Article; Pattern recognition. Digital image processing. Computational geometry; Positron-Emission Tomography; Radiodiagnosis. Nmr imagery. Nmr spectrometry; Regression Analysis; Reproducibility of Results; Software; United States
• ISSN: 1539-2791; 1559-0089
• DOI: 10.1007/s12021-013-9180-7

Accurate estimation of cognitive scores for patients can help track the progress of neurological diseases. In this paper, we present a novel semi-supervised multimodal relevance vector regression (SM-RVR) method for predicting clinical scores of neurological diseases from multimodal imaging and biological biomarker, to help evaluate pathological stage and predict progression of diseases, e.g., Alzheimer’s diseases (AD). Unlike most existing methods, we predict clinical scores from multimodal (imaging and biological) biomarkers, including MRI, FDG-PET, and CSF. Considering that the clinical scores of mild cognitive impairment (MCI) subjects are often less stable compared to those of AD and normal control (NC) subjects due to the heterogeneity of MCI, we use only the multimodal data of MCI subjects, but no corresponding clinical scores, to train a semi-supervised model for enhancing the estimation of clinical scores for AD and NC subjects. We also develop a new strategy for selecting the most informative MCI subjects. We evaluate the performance of our approach on 202 subjects with all three modalities of data (MRI, FDG-PET and CSF) from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. The experimental results show that our SM-RVR method achieves a root-mean-square error (RMSE) of 1.91 and a correlation coefficient (CORR) of 0.80 for estimating the MMSE scores, and also a RMSE of 4.45 and a CORR of 0.78 for estimating the ADAS-Cog scores, demonstrating very promising performances in AD studies.