Decentralized artificial intelligence for diagnosis, prognostication and response prediction in colorectal cancer

groups_2

58.000 people

Bowel cancer is one of the most common and deadly types of cancer in Germany. Every year, around 58.000 people are diagnosed with the disease. If detected early, bowel cancer is easily curable. However, despite significant advances in screening and treatment, diagnosis and prognosis are challenging.

Five partners

German university hospitals in Dresden, Heidelberg, Mainz, Bonn and Düsseldorf are working together to investigate how the use of artificial intelligence (AI) and swarm learning (SL) can significantly improve the care and treatment of colorectal cancer patients.

AI-based diagnosis

The project partners will use SL to develop AI algorithms for diagnosing and subtyping colorectal cancer and predicting disease progression. More powerful AI systems could help physicians detect bowel cancer at an earlier stage and treat it more effectively.

Swarm learning

Data exchange between hospitals is severely restricted by legal and ethical hurdles. By using swarm learning and decentralized AI, several institutions can jointly train medical AI models without exchanging data. DECADE will set a precedent for the use of SL in medicine that can serve as a template for any AI system in the healthcare sector.

Swarm learning and how AI can improve cancer diagnosis and treatment

AI is capable of analyzing large amounts of data and recognizing certain patterns. These insights can help to better predict the course of the disease or to make more individualized diagnoses. But AI tools have so far only been used hesitantly in routine clinical practice.

A key reason is that AI requires training on large and diverse multi-centric datasets. In practice, data sharing between hospitals is severely restricted by legal and ethical hurdles. A technical solution to this problem is swarm learning. It is a special form of machine learning in which models are trained without exchanging data between institutions. The coordination and merging of models are performed via a blockchain, eliminating the need for a central instance.

The DECADE project builds on this method:
Using SL-based AI technology it will solve real-world clinical problems related to colorectal cancer.

DECADE Project Insights

Learn more about the DECADE project, its aims and our ambitious work plan.

Work Plan

DECADE is divided into five subprojects. Different work packages are carried out at our partner sites in Dresden, Bonn, Heidelberg, Mainz and Düsseldorf.

Consortium

Learn more about the members at our five partner sites.

Get in touch

Reach out if you have any questions and want to know more about DECADE and our research.