A Clinical Decision Support system based on Quantitative multimodal brain MRI for personalized treatment in neurological and psychiatric disorders

Project Information

CDS-QUAMRI

Grant agreement ID: 634541

DOI

10.3030/634541

Project closed

EC signature date 12 March 2015

Start date 1 September 2015

End date 28 February 2021

Funded under

• SOCIETAL CHALLENGES - Health, demographic change and well-being

Total cost

€ 2 168 125,00

EU contribution

€ 2 168 125,00

Coordinated by

MAX-PLANCK-GESELLSCHAFT ZUR FORDERUNG DER WISSENSCHAFTEN EV
Germany

Periodic Reporting for period 4 - CDS-QUAMRI (A Clinical Decision Support system based on Quantitative multimodal brain MRI for personalized treatment in neurological and psychiatric disorders)

Reporting period: 2020-03-01 to 2021-02-28

Summary of the context and overall objectives of the project

A large number of neurological and psychiatric disorders lack objective criteria for primary diagnosis, early differential diagnosis with regard to subtypes in treatment response and disease progression or effective therapy monitoring. Correct diagnoses at early stages and correct patient stratification are hence often severely delayed and patients are left without any appropriate treatment for years resulting in a tremendous negative socio-economic impact. In contrast to many clinical disciplines, neither predictive physiological biomarkers nor imaging-based surrogate markers have been established yet. However, scientific studies based on advanced magnetic resonance imaging (MRI) methods indicate that patients with neurological and psychiatric disorders show specific subtle changes in multiple MRI readouts that are only detectable by quantitative approaches.

Hence a clinical decision support system (CDS) enabling personalized diagnostics and treatment for neurological and psychiatric disorders is envisioned that is based on multimodal quantitative (QUA) magnetic resonance imaging (MRI) and multi-parametric
classification and shall be demonstrated for major depressive disorder (treatment response prediction) and multiple sclerosis (disease progression type prediction).

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

One objective of the CDS QUAMRI project was to fully integrate advanced analysis algorithms of multi-modal structural, functional and metabolic MRI data into a single software framework to make them accessible for non-expert clinical users in order to allow for large scale clinical trials and more widespread use in neuroscience as a basis for the future use in clinical decision making. At the end of the entire project the development of a respective data base system that serves as software framework for MRI data and analysis workflow management and visualization has been fully established. The development, adaptation and integration of MRI data analysis modules for quantitative anatomical and microstructural imaging, functional imaging, perfusion imaging and metabolic imaging has been completed as well as the development and integration of a machine learning and classification module. An impressive number of novel MRI data analysis methods that give access to so far inaccessible tissue parameters and enhance the precision and accuracy of quantitative data analysis for relaxometry, myelin imaging, axon density imaging, functional imaging, metabolic imaging and perfusion imaging have been developed and are integrated into the respective software modules.

The second objective of the CDS QUAMRI project was to develop a prototype Clinical Decision support system using classifiers that discriminate different patient subgroups (treatment response, disease progression) using machine-learning based classification methods and multi-modal MRI data from patients with major depressive disorder as well as multiple sclerosis. At the end of the entire period duration it was demonstrated that anatomical, functional and metabolic MRI allow prediction of therapy response to electroconvulsive, ketamine and psycho therapy in patients with major depressive disorder. Furthermore, the correct assignment of patients to different disease progression types of multiple scleroses was possible based on a combination of anatomical, microstructural and metabolic MRI. Furthermore microstructural MRI shows strong predictive power for disability scores in multiple sclerosis patients. The data analysis and classification trials for both multiple sclerosis and major depressive disorder are going to be continued after the project end.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

We obtained a data base software solution that offers full integration of reconstruction, processing and quantification pipelines for anatomical, functional, perfusion and metabolic MRI into a common data handling, visualization, feature extraction and classification framework and supports automatic data transfer from the MRI scanners and is distributed as a commercial product. In addition, major advances with respect to novel quantification and feature extraction algorithms for these MRI modalities have been implemented and will be available to the public via distribution of open source analysis modules and open access scientific publications. In addition standardized data acquisition protocols have been implemented. This overall effort enables a more widespread use of state-of-the-art multi-modal quantitative MRI in neuroscience and large clinical trials. This in turn is the basis for future application of advanced MRI in combination with machine learning in clinical decision making with regard to a large number of neurological and psychiatric disorders.

The envisioned Clinical Decision Support System has been successfully demonstrated for specific clinical decision making problems in patients with major depression and multiple sclerosis. It makes use of disease specific anatomical, microstructural, functional and metabolic MRI based surrogate markers to enable (1) the prediction of treatment response to electroconvulsive therapy, ketamine therapy and psychotherapy in major depressive disorder and (2) the distinction of different disease progression types in multiple sclerosis. In both patient groups it was also found that anatomical imaging data that are routinely acquired yield predictive power if a quantitative analysis is performed instead of the qualitative evaluation that is the current clinical standard. The demonstrated principles can be extended to a larger number of neurological and psychiatric disorders and disease specific clinical decision making problems in order to facilitate personalized treatment. A key outcome of this project is the need for clinical trials that provide large consistent multimodal MRI data sets acquired with standardized scan protocols on one hand and the move from qualitative to quantitative analysis of clinical MRI data on the other hand.

quamri-figure.png