The BETTER Project has a new project coordinator!
Before we present our new coordinator, we want to say thank you to Matteo Bregonzio for his dedication to the BETTER Project and wish him alle the best in the future!

Without further ado, please allow us to present BETTER’s new project coordinator Michele Compare from Datrix:

I’m thrilled to share that I've been appointed by Datrix to coordinate the BETTER Project. This is a fantastic opportunity to work on a project that truly resonates with my expertise and interests, and to collaborate with an outstanding consortium partners to advance the research on cancer.

A little about me: I'm CTO of Datrix, with a background in Nuclear Engineering. I earned my MSc from the University of Naples Federico II and my PhD from Politecnico di Milano, both with honors. I've also had the privilege of conducting research at Politecnico di Milano and leading R&D projects to apply AI to industrial problems.

I'm eager to dive into this new challenge and work alongside the talented team involved in BETTER. Let's make a real impact!

Curiosity has always been behind innovation, especially in healthcare. Think about how far we have come: from stacks of paper-based patient records, scattered across different hospitals, and difficult to share, to an era where AI has the potential to revolutionize medicine. Today, federated learning allows institutions to collaborate on research while preserving patient privacy.

But there’s a challenge: how do we ensure that data from different hospitals, recorded in different formats and languages, can work together?

Without a shared structure, even the most advanced AI models would struggle to make sense of fragmented and inconsistent data. That’s where conceptual modeling becomes the secret ingredient that transforms scattered information into a unified and powerful resource for medical research. By creating a common language, conceptual modeling allows different datasets to “speak” to each other, ensuring that AI can learn from them in a meaningful way.

At the heart of the BETTER project, conceptual modeling plays a crucial role in three key areas: ETL (Extract, Transform, Load) processes, FAIRification (making data Findable, Accessible, Interoperable, and Reusable), and Synthetic Data Generation (generating high-quality synthetic datasets that retain the statistical properties of real data while ensuring patient confidentiality).

This isn’t just about making AI work; it’s about making it work right. With the BETTER project leading the way, we are not just unlocking the potential of AI in healthcare. We are redefining what is possible. The road ahead is exciting, and conceptual modeling is lighting the path forward.

Our partners from Aston University and Datrix presented their latest advancements of image quality in the diagnosis of Inherited Retinal Diseases in the BETTER Project at SPIE Photonics West 2025. We are proud to share the abstract here on this blog:

Title: “Enhancing retinal image clarity: denoising fundus and OCT images using advanced U-Net deep learning”

Abstract:
This research addresses the challenge of image quality in the diagnosis of Inherited Retinal Diseases (IRDs) by leveraging advanced U-Net deep learning models to denoise Fundus and Optical Coherence Tomography (OCT) images. Highresolution imaging, essential for accurate IRD assessment, is often compromised by inherent noise that obscures critical details. To enhance diagnostic accuracy, we employed U-Net, an autoencoder network renowned for its efficiency in medical image processing, to perform deep learning-based denoising. Our approach involves adding Gaussian noise to Fundus images from the ORIGA-light dataset to simulate real-world conditions and subsequently employing U-Net for noise reduction. This methodology not only clarifies the images but also retains essential pathological features critical for accurate diagnosis. The performance of the U-Net model was quantitatively evaluated using metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM), where it demonstrated significant improvements over traditional methods. This enhanced imaging capability facilitates better clinical insights into IRDs, promotes earlier and more accurate diagnoses, and supports the development of personalized treatment plans, advancing the field of precision medicine.


Authors:
J. Fartiyal, P. C. Sourza, Y. Whayeb, M. Bregonzio, J. S. Wolffsohn, S. G. Sokolovski.

We owe a lot to the human nature’s curiosity. Also in the history of medical treatments. Take a moment and think about medical treatments today compared to 40 years ago. It’s easy to take for granted how advanced our technology and knowledge is today. What seems painfully obvious now, would have been a groundbreaking way of thinking 40 years ago. So many lives are saved every single day who would have been lost back then.

Now take a moment and imagine what we can do 40 years into the future. We don’t know it yet, but in 40 years we can save lives who can’t be saved today. Exciting isn’t it?

The road to new knowledge and technology is often difficult with several roadblocks along the way. However, has a little challenge ever stopped the human race in the past? No, thankfully not! Curiosity has always driven us to explore new ideas, new paths, and new technology.

The BETTER Project is exploring a new path. A path of using AI and federated learning in the healthcare sector to research diseases, especially rare diseases with limited data available in each health institution. It takes resources to take a chance on a new idea and the funding from an EU Horizon project like BETTER makes it possible.

We are driven by human curiosity and the ambition to make a difference, let’s see where this project leads us to. We expect a BETTER future!