Deriving novel micro biomechanical indices based on clinical imaging and computational simulation data and analysis using machine learning for assessment of cerebrovascular and cognitive health

Project Information

NeuroVascularHealth

Grant agreement ID: 101038096

DOI

10.3030/101038096

Project closed

EC signature date 23 November 2021

Start date 17 October 2022

End date 16 October 2024

Funded under

• SPREADING EXCELLENCE AND WIDENING PARTICIPATION

Total cost

€ 145 355,52

EU contribution

€ 145 355,52

Coordinated by

ISTINYE UNIVERSITY
Türkiye

Periodic Reporting for period 1 - NeuroVascularHealth (Deriving novel micro biomechanical indices based on clinical imaging and computational simulation data and analysis using machine learning for assessment of cerebrovascular and cognitive health)

Reporting period: 2022-10-17 to 2024-10-16

Summary of the context and overall objectives of the project

Cerebrovascular diseases are a significant global health challenge, causing millions of deaths and leading to severe cognitive decline or stroke-related disabilities. The ability to accurately diagnose, predict, and prevent these diseases remains a critical issue, as current medical techniques lack the accuracy and efficiency needed for reliable early detection. Conditions such as aneurysms, strokes, and other vascular abnormalities often progress silently until critical damage occurs.

Addressing cerebrovascular diseases has profound implications for public health, societal productivity, and healthcare costs. Early detection and intervention can prevent severe outcomes, reducing the burden on healthcare systems and improving the quality of life for millions worldwide. Additionally, this research paves the way for personalized medicine, offering tailored interventions based on patient-specific data. This will save lives and contribute to economic stability by reducing long-term care costs.

This project aims to revolutionize the diagnosis, prognosis, and treatment planning of cerebrovascular diseases through innovative approaches integrating advanced computational techniques and machine learning. Specifically, the objectives are:

By successfully merging imaging modalities, computational models, and artificial intelligence, this project increases the potential to improve diagnostic accuracy and treatment planning for cerebrovascular diseases significantly. The developed methodologies and tools have laid the groundwork for early diagnosis and tailored patient care, ensuring better health outcomes and reduced societal costs. These advancements hold promise for widespread clinical adoption and future innovations in translational health sciences.

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

The project addressed critical challenges in the early detection, diagnosis, and treatment planning of vascular and cognitive diseases. This was achieved by integrating advanced computational models, imaging techniques, and machine learning algorithms. Key activities included:

Development of Automated Image Processing Protocols: Leveraging open-source libraries, protocols for the segmentation and geometric characterization of vascular structures and brain tissue sections were developed and automated.
Computational Simulation: Using patient-specific 3D reconstructions, simulations were conducted to derive biomechanical indices such as wall shear stress, blood flow velocity, and pressure distributions.
Novel Metrics for Diagnosis: New indices were generated by combining geometric and physiological data, potentially driving more accurate assessments of vascular and cognitive health.
Machine Learning Integration: Computational and geometric features were processed using machine learning to identify correlations with disease states, enhancing predictive accuracy.

Main Results Achieved
More Physiological Data: Imaging, simulations, and machine learning results were integrated to get more insightful informatics compared to traditional methods.
Development of Predictive Tools: The first steps of predictive tools capable of assessing cerebrovascular health and the risk of cognitive decline for the use of clinicians.
Scientific Contributions: The project yielded novel computational indices and validations of their use in clinical contexts are in progress. This work has been documented in publications and presented at conferences​.

The results have been shared through publications in high-impact journals and presentations at international conferences.
A web-based platform has been proposed to allow general audience access to our results.
Outreach activities targeted at healthcare professionals and the general public were conducted to raise awareness of cerebrovascular and cognitive diseases and the benefits of early diagnosis.
By combining advanced computational science with clinical expertise, the project has made significant strides in improving the early detection and management of cerebrovascular and cognitive diseases, with the potential for widespread clinical impact.

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)

This project made significant advancements in addressing the limitations of current diagnostic and prognostic techniques for vascular and cognitive diseases. Key areas of include:

Integration of Multimodal Approaches: Unlike traditional methods that rely solely on imaging or computational modeling, this project combines advanced imaging modalities, computational simulation, geometric analysis, and machine learning. This novel, integrated approach will hopefully enhance diagnostic accuracy and predictive capabilities.
Development of Novel Metrics: The project introduced innovative computational and geometric indices to assess cerebrovascular and cognitive health. These metrics will be validated against clinical data and hopefully will surpass the capabilities of traditional measures, offering more precise and early-stage detection​.
Automation of Clinical Image Processing: Protocols for automated segmentation and analysis of vascular structures were developed, significantly reducing the time and effort us required for manual processing​.
Personalized Predictive Models: Machine learning was applied to patient-specific data, enabling personalized predictions of disease progression and rupture risks, which were previously difficult to achieve using conventional techniques​.

Expected Results After In-progress Studies, and by the inspiration caused by the project, the following outcomes are anticipated:
Refined Diagnostic Tools: Clinician-ready predictive tools will be developed, enabling real-time assessments of cerebrovascular health and cognitive disease risk during routine scans.
Clinical Validation and Standardization: The newly developed indices and protocols will be validated across diverse patient cohorts, ensuring their reliability and reproducibility in clinical settings.
Online Tool for Clinicians: An accessible web-based platform will be launched to enable clinicians to input patient data and receive diagnostic and prognostic insights.
Broader Data Application: A growing database of patient-specific cases will enable ongoing refinements of the algorithms, paving the way for in-depth population studies.

Potential Socio-Economic Impacts
Reduced Healthcare Costs: Early detection and accurate prognosis can prevent severe complications, reducing long-term healthcare expenditures on critical interventions and chronic care.
Improved Treatment Planning: Tailored, patient-specific interventions will reduce unnecessary procedures, optimizing resource allocation in healthcare systems.
Wider Societal Implications
Enhanced Quality of Life: Early and accurate detection of cerebrovascular and cognitive diseases will lead to timely interventions, improving patient outcomes and minimizing disability.
Public Health Awareness: Dissemination of findings through outreach activities and media campaigns will educate the public on the importance of early diagnosis and preventive care.
Scientific Advancement: The project contributes to the field of computational biomedicine by demonstrating the feasibility and impact of integrating artificial intelligence and computational modeling into routine clinical practice​.

Overall, this project bridges the gap between state-of-the-art computational methodologies and their application in healthcare, offering transformative solutions to long-standing challenges in cerebrovascular and cognitive disease management.

picture2.jpg

picture1.jpg