D5.3 Deep Learning Master model and Radiomic Signatures

Mar 12, 2024 | Deliverables

Deliverable 5.3, led by partner FCHAMPALIMAUD, contains the work performed by the ProCAncer-I
consortium on master models using radiomics and deep learning techniques. ’Master models’ — models
which can act as a foundation for other models — were developed for radiomics for all relevant use cases
(UC2, UC3, UC5, UC6, UC7a, UC7b and UC8) through the development of consistent and robust pipelines,
while deep learning was used only for UC1, UC2 and UC5 due to its more demanding data requirements.
Radiomics master models were developed by three partners (FCHAMPALIMAUD, FORTH and CNR), while
deep learning master models were developed and investigated by six different partners (FCHAMPALIMAUD,
CNR, FORTH, ADVANTIS, FPO, QUIBIM). Through this approach, several aspects of deep learning models
were investigated and consistent approaches and trends were identified. We finally note that the concept of
a ’master model’ is similar to that of a foundation model; in that light, this deliverable reflects that insight.
We describe the work in terms of foundation models and provide an overview of all experiments performed
to arrive at foundation models.

Highlights

Podcast Spotlight: The Future of Trustworthy AI in Healthcare

Podcast Spotlight: The Future of Trustworthy AI in Healthcare

The role of artificial intelligence (AI) in healthcare is expanding rapidly, but trust remains a crucial barrier to its widespread adoption. The following AI-generated audio file, titled, serves as an example of how AI-driven technologies can contribute to medical research and education.

Dissemination Event of the ProCAncer-I Project in Vienna, Austria

Dissemination Event of the ProCAncer-I Project in Vienna, Austria

ProCAncer-I organised the 4th Dissemination Event of the project at the ECR 2025 held in Vienna, Austria, February 25-26, 2025. During the congress, ProCAncer-I organised a Dedicated Session on the project on the 26th of February 2025, at 15.00-16.00, with the title...

The brand effect: how different MRI machines trip up AI

The brand effect: how different MRI machines trip up AI

Prostate cancer can vary greatly in how aggressive it is, and knowing this in advance helps doctors decide the best course of treatment. Magnetic resonance imaging (MRI) is often used to detect prostate cancer, but figuring out just how aggressive the cancer is...

Dissemination Event of the ProCAncer-I Project in Vienna

Dissemination Event of the ProCAncer-I Project in Vienna

We are delighted to invite you to our session, “ProCAncer-I: An AI Platform Integrating Multiparametric MRI and AI Models”, at the European Congress of Radiology (ECR) 2025.  Date: 26 February 2025  Time: 15:00 – 16:00  Location: ECR 2025, Vienna, Austria (conference...

Twitter feed is not available at the moment.

Stay in touch!