The four-year MEDIRAD project aims to enhance the scientific bases and clinical practice of radiation protection in the medical field and thereby addresses the need to better understand and evaluate the health effects of low-dose ionising radiation exposure from diagnostic and therapeutic imaging and from off-target effects in radiotherapy.

The MEDIRAD project is close to completing its third year and was recently granted a 9-month cost-neutral extension by the European Commission, with a new conclusion date of February 2022. Several major milestones have recently been achieved, including the setup and testing of a central DICOM repository for dosimetry, imaging meta-data, and biobanking. Data collection efforts for the first-ever establishment of European DRLs for specific applications of CT in nuclear medicine have also just been finalised. Moreover, the assessment of low dose radiation exposure from I-131 radioiodine ablation therapy of thyroid cancer is in full swing, laying the foundation for the first epidemiological investigations within nuclear medicine.

MEDIRAD has also significantly progressed towards improving the understanding of low-dose ionising radiation risks associated with major medical radiation procedures, by combining for the first time, clinical and preclinical studies to get further insight into the biological mechanisms and biomarkers that may play a role in the development and prediction of cardiac complications, and to use these insights for the development of predictive models. The clinical studies EARLY-HEART and BRACE are thus close to completion. Furthermore, the pre-clinical studies to identify mechanisms of radiation-induced cardiovascular toxicity are ongoing.

The first-ever nested case control study in a cohort of CT-scan exposed individuals, commenced its study into the long-term effects of the associated low doses on cancer risks in children. In this study, the interaction between genetic and epigenetic factors along with radiation dosage on cancer risk will be assessed, with the results having the potential to significantly impact the medical radiation protection field at large.

In addition, the stakeholder forum and a consensus building infrastructure for the development of the recommendations – based on the scientific evidence emerging from MEDIRAD’s research results – have been established, and work on the recommendations has started with the aim to enhance medical radiation protection in Europe. The MEDIRAD project is thus well on track in its stated goals to significantly enhance the scientific bases and clinical practice of radiation protection in the medical field.

More information on MEDIRAD is available here and on www.medirad-project.eu.

MEDIRAD project has received €9,995,145.75 in funding from the Euratom research and training programme 2014- 2018 under grant agreement No. 755523 and is active until November 30, 2020.

The CHAIMELEON project aims to set up a structured repository of health images and related clinical and molecular data on the most prevalent cancers in Europe: lung, breast, prostate and colorectal. The repository will serve as a resource for developing, testing, and training of AI tools for a more precise and personalised management of cancer.

In 2023, the CHAIMELEON project achieved milestones in infrastructure, data, harmonisation, security, validation, clinical studies, sustainability, and dissemination. The CHAIMELEON repository, a robust distributed infrastructure, was established with 4,500 full cases and 2,000 image-only cases for lung, breast, colon, rectal, and prostate cancers. Harmonisation efforts improved Quantitative Imaging Biomarkers’ reproducibility, utilizing innovative online processing, including QTI sequences and CNN-based strategies.

The project moreover entered the internal and external validation phases. The internal validation phase was successfully completed, and the results fed back into the repository development. The consortium launched the CHAIMELEON Open Challenges to validate the usability and performance of the CHAIMELEON repository as a tool fostering AI experimentation for cancer management. In parallel, the partners started the preparations for the external validation and focused on the design of the early clinical validation studies for each cancer type.

In addition, a stable sustainability plan was designed to secure the project’s and the repository’s long-term viability, while an ambitious dissemination strategy showcased the project’s impact.

“Transforming brain surgery by advancing functional-guided neuronavigational imaging” will develop a novel cost-effective, transportable, compact optical imaging system (“HyperProbe”) to measure brain function during surgery to achieve better guidance during brain tumour removal by 2027. It will thus critically improve surgical outcomes for patients.

The HyperProbe project will develop and validate a cost-effective, transportable, and easy-to-use device to be integrated with existing clinical instrumentation that is fully suitable for the operating room.

The project will significantly impact clinical practice as the consortium proposes, for the first time, a functional-imaging and machine-based decision-making approach in neurosurgery. The HyperProbe device will be the first multi-biomarker, quantitative optical imaging device and functional imaging device used in image-guided surgery to preserve brain functions and minimise the risk of postoperative neurological impairment and considerably improve the life expectancy of patients.

In the past year, the HyperProbe consortium has made remarkable advances in the design and development of the HyperProbe1 system. This high-performance, versatile, laboratory HSI setup for investigating novel biomarkers for glioma detection and optimisation of hyperspectral parameters has shown promising preliminary results for the clinical translation of its future prototypes. The preliminary testing has allowed the Consortium to study the areas in need for further optimisation for the final HyperProbe device. Another achievement in the first year of the project was the development of a computation tool able to simulate light diffusion through a digital brain incorporating realistic instrument specifications.

Furthermore, in 2023, the project successfully established a unified visual identity for the HyperProbe initiative. Additionally, the team implemented effective communication and dissemination strategies to convey project insights to the wider scientific community.

These significant advancements in the project’s first year will help the consortium advance further and the consortium will build on this accumulated knowledge to construct together the final device, HyperProbe2, ready for clinical study.

The i-Violin project addresses the need to optimise and harmonise oncological imaging procedures in Europe, building upon tools developed in other EC-funded projects to ensure their broad adoption.

Since the project began in September 2022, several significant achievements have been made, including adjustments to software tools for image quality assessment in other body regions and for broader applicability, as well as the development of a new quality performance test for systems based on phantom studies, designed for the optimisation procedure in CT imaging.

Concerning the Education & Training developed by WP7, three practical hands-on events at clinical partners’ sites (Leuven, Zagreb, and Ljubljana) are currently being organised and are scheduled to take place in Spring 2024. An i-Violin Webinar Series has been prepared and is set to occur between March and April 2024, and a stakeholder workshop has been organised for February 2024.

In terms of dissemination, a unified visual identity for the i-Violin initiative has been successfully established. The team has implemented effective communication and dissemination strategies to share project insights with the scientific community. i-Violin was presented at several conferences and events such as ECR 2023, ERPW 2023, etc. Additionally, regular updates have been submitted to the SAMIRA SGQS. The project’s outreach has extended to the IAEA, national authorities, regional authorities, and end-user communities.

An outreach connection to the EUCAIM Project, a flagship project implementing the European Cancer Imaging Initiative, has been established to explore collaboration opportunities.

The RadioVal project aims to develop and implement a very comprehensive validation of artificial intelligence solutions in breast cancer treatment. Such AI solutions enhance precision medicine and will help clinicians perform a more individualised treatment adjusted to the patients’ need.

RadioVal is the first multi-centre, multi-continental and multi-faceted clinical validation of radiomics driven estimation of NAC response in breast cancer. The project builds on the repositories, tools and results of five EU-funded projects from the AI for Health Imaging (AI4HI) Network, including a large multi-centre cancer imaging dataset on NAC treatment in breast cancer.

To test applicability as well as transferability, the validation will take place in eight clinical centres from three high-income EU countries (Sweden, Austria, Spain), two emerging EU countries (Poland, Croatia), and three countries from South America (Argentina), North Africa (Egypt) and Eurasia (Türkiye). RadioVal will develop a comprehensive and standardised methodological framework for multi-faceted radiomics evaluation. Furthermore, the project will introduce new tools to enable transparent and continuous evaluation and monitoring of the radiomics tools over time. The RadioVal study will be implemented through a multi-stakeholder approach, taking into account clinical and healthcare needs, as well as socio-ethical and regulatory requirements from day one.

In 2023, the RadioVal project made substantial progress in designing an AI passport, a traceability tool to monitor radiomic tools transparently over their lifespan. Furthermore, RadioVal partners have identified criteria and metrics for comprehensive radiomics AI evaluation in breast cancer. This includes integration with the AI passport and human-in-the-loop mechanisms.

In RadioVal, social innovation is used to identify new approaches for multi-stakeholder, inclusive and trusted validation, and implementation of radiomics solutions in tomorrow’s clinical oncology. In 2023, RadioVal designed a social innovation framework, including stakeholder mapping, a toolkit and methodology. However, this is only the beginning as the social innovation activities will last the entire project, in a highly iterative and interactive approach and until now already included 86 participants in different online and face-to-face co-creation sessions and interviews.

Investigating the implementation of the Euratom and the EU legal bases with respect to the therapeutic uses of radiopharmaceuticals, the SIMPLERAD project made great progress in 2023, concluding its survey on the current practices and implementation of relevant European legal requirements in this field across the EU-27, Norway and Switzerland and formulating guidelines and recommendations for coherent implementation of these legal requirements and promotion of best practices and safer use.

The survey results were analysed for best practices and challenges faced by practitioners. Combined with the previous year’s comparative legal analysis and literature review, the consortium identified and prioritised 10 issues to be addressed by guidelines and recommendations. Stakeholders such as the project’s Advisory Board, European and national professional societies and HERCA were consulted, and the resulting work was presented at a workshop in Brussels in December. Boasting a diverse attendance of more than 110 participants, the workshop brought together a range of stakeholder groups for presentation and discussion of the guidelines and recommendations. Presentations can be found on the project website.

SIMPLERAD concludes in April 2024 with a final consensus publication of the guidelines and recommendations.

In 2023, the ODELIA project, a European project focused on developing and implementing a pan-European swarm learning network that enables privacy-preserving and democratic training of medical AI algorithms was successfully launched. By focusing on breast cancer detection in MRI screenings, the project aims to demonstrate the power of swarm learning and its potential applications in various clinical settings.

During its first project year, the ODELIA project achieved significant milestones across various domains. First steps were taken to establish a robust Swarm Learning environment, providing a decentralised and collaborative platform for training machine learning models across multiple institutions without the need for centralised data sharing. A comprehensive manual for setting up Swarm Learning onsite was compiled, and the partners demonstrated the application of Swarm Learning in a tangible case, specifically in breast cancer detection using MRI data. The instructions cover hardware and software prerequisites, preprocessing workflows, and the integration of Swarm Learning into existing workflows. A minimal viable product was release and successfully used to train an AI model on publicly available data, showcasing decentralised model training.

A technical documentation website for ODELIA’s open-source Swarm Leaning implementation was set up to enable the reuse the Odelia technical platform for other use cases. This technical documentation can be reached at odelia-ai.github.io.

Moreover, significant progress has been made in building a front end to facilitate both gathering of data for new AI model development and to bridge the gap to clinical usability.

In addition, the project’s achievements in 2023 encompassed the development of a cohesive visual identity for the ODELIA project and effective communication and dissemination strategies to share project insights with the broader scientific community. To learn more about the ODELIA project, visit the project website at www.odelila.ai.

Med-IPUT is a ground-breaking project revolutionizing medical ultrasound imaging. Today, medical ultrasound faces several limitations, such as low resolution, limited penetration depth, and high acoustic peak pressures. Therefore, the MED-IPUT project will develop a high-resolution, high-quality, recyclable medical imaging system based on a disruptive integrated photonic ultrasound transducer concept. Med-IPUT transducers are expected to be up to 100 times more sensitive than current ultrasound sensors. This will be a major leap in ultrasound component performance. The project is aiming to create a new generation of ultrasound imaging sensors that are more accurate, cost-effective, and safer for patients.

During the first year of the project, Med-IPUT has achieved:

• Set up of the project operational plan
• Assessed a risk and contingency plan
• Developed a data management plan
• Set up of the requirements for IPUT demonstrator
• Set up of the system architecture of IPUT demonstrators
• On the dissemination side, a communication kit has been created, as well as a plan for the exploitation and dissemination of results. By the end of the first year, a project introduction video has been released.

The project is coordinated by Netherlands Organisation for Applied Scientific Research (TNO), and EIBIR is in charge of the project management and dissemination tasks.

You will find more project information here: https://med-iput.eu/

The SOLACE project aims at developing, testing and disseminating tools to help overcome identified bottlenecks and specifically address the health inequalities in different European countries. It will provide a toolbox for individualised approaches for lung cancer screening on a national or regional level.

Since its launch in April 2023, the SOLACE project has achieved significant milestones across multiple domains. In terms of dissemination, a unified visual identity for the SOLACE initiative has been successfully established. The team has implemented effective communication and dissemination strategies to share project insights with the broader scientific community.

Additionally, SOLACE has formed various support, evaluation, and advisory groups, such as the National Expert Teams, which now cover all 27 EU countries and all EEA countries. Conducting surveys and interviews with contacts in these countries has enabled SOLACE to compile a comprehensive report on the state of lung cancer screening and related needs in member states and EEA countries. Simultaneously, progress has been made in drafting and finalising the Data Management Plan and the Report on the concept for LCSP management and quality assurance.

SOLACE is carrying out three pilots focusing on enhancing knowledge and participation among female individuals, recruiting hard-to-reach individuals, and targeting higher-risk populations. Marked progress has been achieved in the initial phase, including the establishment of working groups, creation of active invitation measures to enhance female participation rates, and preparation of implementation measures.

The 4-year SINFONIA project will develop novel methodologies and tools that will provide a comprehensive a risk appraisal for detrimental effects of radiation exposure on patients, workers, carers and comforters, the public and the environment during the management of patients suspected or diagnosed with lymphoma and brain tumours. The project started in September 2020. The multidisciplinary project consortium combines the expertise of 14 partners from 8 countries. It includes major universities, research institutes, hospitals and industry partners. A data repository will be developed for storing data as well as for the deployment of AI algorithms on an online platform. SINFONIA research outcomes for the two clinical examples, lymphoma and brain tumours, will be also applicable to other diseases. AI-powered personalised dosimetry tools will provide advanced knowledge on parameters affecting radiation detriment. This will help balancing risks and benefits of ionising radiation procedures and developing dose optimisation strategies. SINFONIA also will organise high level multidisciplinary training in the field of radiation dosimetry, risk appraisal and radiation protection and develop decommendations on radiological protection. The project is coordinated by EIBIR with Prof. John Damilakis (University of Crete) acting as Scientific Coordinator.

For more information, visit the project’s website at sinfonia-appraisal.eu.

This project has received €5,999,997.50 in funding from the Euratom research and training programme 2019-2020 under grant agreement No 945196 and is active until August 31, 2024.

Another Euratom tender project, MARLIN, kicked off in 2023 with a consortium of EIBIR, ESTRO and EFOMP members investigating the implementation of Council Directive 2013/59/Euratom and seeking to improve reporting and learning from patient-related incidents and near misses in radiotherapy, interventional cardiology, nuclear medicine and interventional and diagnostic radiology. The consortium conducted a survey of European competent authorities, national professional societies and hospital staff to determine the status of implementation of the Directive and current practices of reporting and analysing incidents and dissemination of lessons learned in each of the fields. A literature review and interviews with key experts among the survey respondents further informed the consortium on the operation and management of local, national and international incident learning systems in addition to current practices, associated successes and barriers to implementation.

The consortium has prepared draft guidelines and recommendations to enhance implementation of the legal requirements and systems to manage risk and disseminate lessons learned in the use of ionising radiation. Consultation with important stakeholders will be undertaken in 2024 before presentation at a project workshop in September.

The AI-POD project (Trustworthy AI Tools for the Prediction of Obesity Related Vascular Diseases) was launched in May 2023 by a consortium of 11 partners from eight countries, with the ambitious goal of reducing cardiovascular disease (CVD) risks in the obese population through innovative AI-based predictive tools.

Obesity is a pressing concern in Europe. However, current risk assessment methods are inadequate in terms of accuracy and practical application. AI-POD aims to tackle these challenges by integrating clinical, laboratory, and imaging data to translate disease risk into actionable health information that can guide diagnostic steps and treatment recommendations. Over the course of four years, experts from various fields, including radiology, computational imaging research and industry, collaborate to develop a state-of-the-art imaging-based AI risk score, a clinical decision support system (CDSS), and a mobile app for personalized risk assessment and prediction of obesity-related CVDs and their associated complications.

During 2023, the consortium mainly focused on preparatory work, incl. ethics approvals for the retrospective and prospective studies, which will be carried out in six clinical sites, and the technical set up of the AI-POD’s central, secure and compliant multi modal data repository.

The project is coordinated by Prof. Ulrike Attenberger from the University Hospital Bonn, and EIBIR is in charge of the project management and dissemination tasks.

You will find more project information here: www.ai-pod.eu/