Community Research and Development Information Service - CORDIS


IMAGEMEND Report Summary

Project ID: 602450
Funded under: FP7-HEALTH
Country: Germany

Periodic Report Summary 2 - IMAGEMEND (IMAging GEnetics for MENtal Disorders)

Project Context and Objectives:
IMAGEMEND aims to identify multimodal algorithms integrating neuroimaging, genetic, environmental risk and clinical data for optimal diagnosis, course prediction and direct, neuroimaging based treatment of schizophrenia (SZ), bipolar disorder (BD), and attention deficit hyperactivity disorder (ADHD). The project comprises 6 scientific, 1 ethics, 1 dissemination and 1 management WP. IMAGEMEND will develop a database combining information across project partners with data on approximately 13,000 subjects (WP1, objective 1). The central data infrastructure will serve as the backbone for safeguarding data quality and ensuring that IMAGEMEND objectives are achieved according to the highest quality standards (WP1, objective 2). Based on this extensive data resource, IMAGEMEND aims to identify neuroimaging markers linked to classical diagnostic categories for case-control discrimination and differential diagnosis of SZ, BD, ADHD and controls (WP2, objectives 1 and 2). Multimodal data will be used to identify patterns linked to symptom domains across diagnoses and those defining trans-diagnostic patient subgroups (WP2, objective 3). Using data on clinical course, IMAGEMEND aims to identify brain network predictors for stratification of patients (WP3, objective 1). We will refine patient stratification by integrating neuroimaging with genetic multi-loci predictive panels (WP3, objective 3) and explore the relationship between trans-diagnostic patient clusters (see WP2) and treatment outcome (WP3, objective 4). Population based data will be used to identify marker sets indexing high-risk subjects, and to identify predictors of transition from high-risk state to early illness manifestation (WP4, objective 1). These longitudinal data will allow assessment of marker utility when used in early diagnosis patients (WP4, objective 2) and facilitate identification of markers of remission and persistence of ADHD (WP4, objective 3). WP5 will tailor classifiers towards clinically optimal performance criteria (WP5, objective 1) and develop a workflow for their application (WP5, objective 2). Finally, WP5 will develop clinical real-time fMRI software that directly targets the mental disorders of this project through neurofeedback training (WP5, objective 3).
The IMAGEMEND ethics WP addresses ethical and legal concerns arising as part of the project, in particular regarding application of genetic testing in the field of psychiatry. Informed consent procedures will be established (WP6, objective 1), and surveys implemented to understand attitudes towards genetic testing (WP6, objective 2). WP6 will assess the degree to which a given risk prediction and its consequences are understood (WP6, objective 3) and further develop informed consent procedures (WP6, objective 4). Finally, WP6 will consider the ethical, legal, and regulatory issues involved in implementing the developed decision-making rules in clinical practice (WP6, objective 5).
WP7 focusses on making IMAGEMEND known to the scientific community and the public (WP7, objective 1), to disseminate results and to foster interactions with the scientific community and the public (WP7, objective 2). Also, WP7 aims to Identify and valorize intellectual property rights and commercialize software packages based on IMAGEMEND results for use in clinical practice (WP7, objective 3 and 4).
Finally, WP8 will ensure that IMAGEMEND achieves its objectives (WP8, objective 1), help the consortium abide by the regulations and contractual obligations according to the grant agreement (WP8, objective 2), control the project`s finances (WP8, objective 3) and establish a communication infrastructure which enables the partners to communicate efficiently (WP8, objective 4). Finally WP8 will preserve the rights of the partners regarding intellectual property and act as a mediator in case of disputes (WP8, objective 5).

Project Results:
In the 1st period, WP1 set up IMAGEMEND servers and procedures for storage and automated data preprocessing. Extensive cataloguing of information was completed for available baseline data on over 8,500 subjects. In period 2, WP1 achieved for data from all relevant case-control cohorts to be stored on IMAGEMEND servers, substantially simplifying machine learning analyses. WP1 further coordinated the efforts of an “analysis group” that shares analysis strategies across WPs. WP1 is also reaching out to other consortia (e.g. PRONIA, PSYSCAN) and scientific groups to expand the IMAGEMEND database and ensures that all analyses are performed to the highest scientific standards.
Previously, WP2 identified markers of the disorders of interest and several publications resulted from this work. In the 2nd period, WP2 identified multimodal markers within and across diagnoses using novel statistical methodology. WP2 discovered that although volumes of brain structures are significantly defined by genetic factors, there is no genetic overlap between subcortical brain volume and SZ risk. WP2 also showed that brain volumetric changes in ADHD result from a delay in brain maturation and diminish in adults (papers have already been published or are in preparation).
WP3 previously compiled a consensus report on clinical criteria and protocols for statistical analysis of outcome predictors. In the 2nd period, WP3 identified neuroimaging markers of clinical improvement. Also, WP3 leader UNIBA utilized locally available datasets to identify novel genetic variants associated with treatment response, trans-diagnostic imaging markers linked to SZ and BD as well as imaging and genetic markers of BD. This pilot data will be utilized to explore multimodal data integration and to prioritize genetic marker candidates across the IMAGEMEND WPs.
In the first period, WP4 assessed sub-clinical psychotic symptoms in IMAGEN using the ‘CAPE’ self-report questionnaire and explored the prediction of ADHD remission/persistence. Since then, WP4 identified genetic associations with CAPE scores and overlapping neuroimaging associations between the IMAGEN adolescent sample and patient cohorts of the IMAGEMEND database. Finally, WP4 focused on the identification of ADHD predictors in adults with the aim to validate markers across IMAGEMEND ADHD cohorts (ongoing).
In period 1, WP5 developed a software pipeline for machine learning analysis of structural MRI. In the meanwhile, WP5 refined the classification prototype and found structural MRI features to differentiate SZ patients from controls with approximate 65-70% accuracy. Addition of other data modalities will be explored as means to improve accuracy. Previously, WP5 has designed real-time fMRI analysis software, and now performed a neurofeedback study with healthy subjects using connectivity neurofeedback and completed a feedback display study that demonstrated the equivalence of different feedback types.
WP6 previously scrutinized the informed consents of all clinical IMAGEMEND partners, explored various ethical problem areas related to genetic testing and developed case-vignettes for their illustration. In period 2, the WP performed Delphi rounds with experts and consumer groups of diagnostic and predictive tests and obtained important insights into attitude towards information desired prior to genetic testing, the disclosure of genetic testing results and the right to know and not to know.
In the last 18 months, within WP7, IMAGEMEND members participated in various conferences and a symposium (‘Multimodal Markers of disease expression in mental disorders: results from large clinical and general population cohorts’, SOBP 2016) was organized. Also, six Dissemination Board TCs took place, since the last reporting.
WP08 ensured that IMAGEMEND achieved its objectives, supported the consortium regarding legal and financial matters and has organized successful consortium meetings.

Potential Impact:
IMAGEMEND is designed to improve the clinical management of mental illnesses by establishing a new generation of clinically useful imaging tools based on standard clinical MRI equipment. With mental illnesses being the largest contributor to all cause morbidly burden in the EU, IMAGEMEND is expected to have a significant economical and societal impact. As the major group of chronic illnesses affecting the working population, mental disorders are now among the two leading causes of early disability and illness-related work absence, contributing to a massive indirect socioeconomic cost. No indications of improved care and treatment of mental disorders were found since 2005 and less than one third of all cases receive any treatment, suggesting a considerable level of unmet needs. Currently available clinical algorithms offer little guidance for personalized treatment beyond sequential pharmacological treatment attempts following insufficient drug response, a procedure that is time-consuming, expensive, and often frustrating for client and therapist alike.
IMAGEMEND will change this situation by revolutionizing the way neuroimaging is used in clinical practice to diagnose and treat mental disorders. Despite the large-scale human experimental data and information processing that will be performed in this grant to create our final deliverables, the resulting algorithms will be standardized, implemented and distributed to be used rapidly, without specific expertise and on standard clinical scanning equipment, enabling broad distribution throughout Europe.
Specifically, our approach is expected to
• enable a new approach to personalized treatment, by more accurate patient stratification through the systems-level biology underlying mental disorders as currently defined that are the true targets of diversity.
• enable the diagnosis of mental disorders at the pre-symptomatic stage or early during development, and therefore early intervention and prevention, by mapping the biology of established risk factors for mental disorders in algorithms validated in population samples
• enable prediction of treatment response and better measurement of disease progression (with an emphasis on the conversion of the pre-symptomatic stage to early manifest disorders) through markers and decision rules validated in large-scale clinical datasets
While IMAGEMEND will therefore impact psychiatric practice through a new generation of imaging-based markers, the project will also create a novel approach to directly use marker information to modify disease biology using imaging technology. To achieve this goal, the project will develop new imaging technology to enable the direct imaging-based modification of disease relevant neural circuits through rapid real-time fMRI.
Critical for the derivation and validation of these new diagnostic, prognostic and stratification markers is the integration of imaging data with complementary knowledge from genomics, environmental and clinical data, using imaging genetics and a sophisticated bioinformatics approach utilizing advances in multimodal data analysis and multivariate statistics. The impact of this strategy is maximized by (a) the assembly of one of the largest datasets combining imaging with genomic and clinical data in psychiatric disorders, including unique data such as large samples of high-risk rare genetic variant carriers and prodromal subjects followed longitudinally, (b) extensive consortium expertise in imaging genetics, multivariate statistics, early prediction and prevention, and a broad range of clinical psychiatry, (c) taking a trans-diagnostic approach, meaning that the results are not confined to traditional nosology but index the true neurobiology that is the target for personalized therapy, and (d) extensive expertise in the implementation and dissemination of user-friendly software in neuroimaging.

List of Websites:

Reported by



Life Sciences
Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top