MINDSET principals offer invaluable expertise for CNS clinical trials, especially when there is an interest in neurobiological pre-stratification of patients, identification of biomarkers for tracking disease progression, and/or identification of baseline multivariate profiles that can be used on a subject-by-subject basis to predict responsivity to neuroactive compounds. Using different imaging modalities and their unique state of the art image analysis capabilities MINDSET can detect drug effects and mechanisms that would be missed in traditional clinical trial paradigms.
MINDSET principals have been developing differential diagnostic strategies based of novel processing and analysis methods for brain imaging data for the past decade. Most of this work has focused on diagnosis of psychiatric and neurodegenerative diseases using functional, structural, and diffusion weighted MRI data, but the developed methods are fully translatable to the evaluation of other types of imaging data (e.g. positron emission tomography (PET) data ).
Much of our research strategy is based on independent component analysis (ICA) methods used in combination with Bayesian classification methods and/or machine vector learning strategies. These methods can help to reveal hidden patterns in imaging data that strongly correlate with clinical and/or diagnostic metrics. A special strength of the ICA approach is that it provides a means for integrating data across multiple modalities. PET data, in conjunction with behavioral, genetic, or other imaging data (e.g., MRI or fMRI) can all be integrated in the development of diagnostic discriminants. Another important aspect is the "data driven" nature of the approach. ICA can look for critical hidden patterns in the data, in the absence of a priori expectations on what information is critical to distinguishing diagnostic groups. The actual data drive the analysis process, not hypotheses which have the potential to be incorrect.
For example, an important challenge in clinical psychiatry is differentiation of patients with bipolar disorder with psychotic features from patients with schizophrenia. In many cases, it will take a clinician six months or more to make a definitive diagnosis, a troubling situation since treatment paths for the two conditions are substantively different. Recently MINDSET principals have demonstrated that an ICA-based analysis of fMRI resting-state dataset is sufficient for differential diagnosis of bipolar disorder and schizophrenia with greater than 90% sensitivity and specificity.
Citations to selected publications are listed below:
Arribas JI, Calhoun VD, Adali T. Automatic Bayesian classification of healthy controls, bipolar disorder, and schizophrenia using intrinsic connectivity maps from FMRI data. IEEE Trans Biomed Eng. 2010 Dec;57(12):2850-60. Epub 2010 Sep 27.
Calhoun VD, Maciejewski PK, Pearlson GD, Kiehl KA. Temporal lobe and "default" hemodynamic brain modes discriminate between schizophrenia and bipolar disorder. Hum Brain Mapp. 2008 Nov;29(11):1265-75.
Calhoun VD, Sui J, Kiehl K, Turner J, Allen E, Pearlson G. Exploring the psychosis functional connectome: aberrant intrinsic networks in schizophrenia and bipolar disorder. Front Psychiatry. 2011;2:75. Epub 2012 Jan 10.
Celone KA, Calhoun VD, Dickerson B, Atri A, Chua E, Miller S, DePeau K, Rentz D, Selkoe D, Albert MS, and Sperling RA, Alterations in Memory Networks in Mild Cognitive Impairment and Alzheimer's Disease: An Independent Component Analysis, Journal of Neuroscience, vol. 26, pp. 10222-10231, 2006.
Meda SA, Gill A, Stevens MC, Lorenzoni RP, Glahn DC, Calhoun VD, Sweeney JA, Tamminga CA, Keshavan MS, Thaker G, Pearlson GD. Differences in resting-state functional magnetic resonance imaging functional network connectivity between schizophrenia and psychotic bipolar probands and their unaffected first-degree relatives. Biol Psychiatry. 2012 May 15;71(10):881-9.
Meda S, Narayanan B, Liu J, Perrone-Bizzozero N, Stevens M, Calhoun VD, Glahn G, Shen, L, Risacher L, Sayking A, and Pearlson GD, A large scale multivariate parallel ICA method reveals novel imaging-genetic relationships for Alzheimer's Disease in the ADNI cohort, NeuroImage, vol. 60, pp. 1608-1621, 2012.
Sui J, Pearlson G, Caprihan A, Adali T, Kiehl KA, Liu J, Yamamoto J, Calhoun VD. Discriminating schizophrenia and bipolar disorder by fusing fMRI and DTI in a multimodal CCA+ joint ICA model. Neuroimage. 2011 Aug 1;57(3):839-55. Epub 2011 May 27.
Sorg C, Riedl V, Muhlau M, Calhoun VD, Drzezga L, Forstl H, Kurz A, Zimmer C, and Wohlschlager A. Selective changes of resting-state networks in patients at high risk for Alzheimer’s disease – an example for profiling functional brain disorders, Proc Natl Acad Sci U S A, vol. 104, pp. 18760-18765, 2007.
back to Our Customers