The European Digital Innovation Hub for the application of artificial intelligence in healthcare and medicine, known as AI4Health.Cro, recently presented 14 selected teams that will participate in an innovation competition focused on developing prototypes of AI applications to improve the detection of potentially carcinogenic lesions on mammographic breast images.

The competition, launched in December 2024, attracted 34 teams with a total of 106 participants, including IT experts, innovators, and healthcare professionals, ready to face the challenges of breast cancer diagnosis. After a detailed evaluation, 14 top teams were selected to present at the initial event held at the Zagreb Innovation Center – ZICER. They will compete for a prize fund of 9,000 euros.

The teams come from different parts of Croatia, including Čakovec, Karlovac, Osijek, Split, and Zagreb. Among the selected teams are: Breast Friends, BreastQuestAI, Code to Heal, D308, Deregularizatori, GANga, Guard(AI)ns of Precision, JMM Kronos, MDT, MediSense, OncoVision, ProtostarLabsTeam, and SCIOM.

Challenges in Breast Cancer Diagnosis

Breast cancer represents the most common malignant tumor in women globally, responsible for more than 670,000 deaths annually. Early diagnosis is crucial for successful treatment, but existing systems face challenges such as the increased number of mammographic images that need to be analyzed and the lack of expert personnel, which particularly affects rural areas. In this context, artificial intelligence offers potential solutions.

The Role of Artificial Intelligence in Improving Diagnosis

The application of AI technologies can significantly speed up and simplify the analysis of mammographic images, enabling faster and more accurate diagnostic decisions. This helps radiologists, alleviates the healthcare system, and optimizes resources, directly contributing to better care for patients.

Tasks for the Participants

The participants will face four key tasks:

1. Develop an AI model that identifies and classifies breast lesions according to the BI-RADS system, which is important for assessing the risk of breast cancer.


2. Mark suspicious areas on the images, similar to an experienced radiologist.


3. Explain how their model arrives at conclusions, helping to uncover important patterns and potential biases.


4. Design a simple and useful interface that helps doctors interpret results, with clear explanations of diagnoses and their reliability.

Data Security and Resources

To address these tasks, the participants will use real, but anonymized mammographic data, with strict privacy protection. This type of data allows testing of solutions in a secure environment thanks to the collaboration of AI4Health.Cro with hospitals and clinics, ensuring that the developed technologies are applicable in everyday clinical practice. The necessary computing resources are provided by the Ruđer Bošković Institute and the University Computing Centre - SRCE.

Expectations and Future

The top three teams will present their solutions in April at the annual AI4Health.Cro conference, which brings together leading experts in healthcare and AI technology. This initiative represents a step forward in integrating artificial intelligence into medical practice, aiming to improve the diagnosis and treatment of breast cancer.

Wider Context of Artificial Intelligence Application in Medicine

Artificial intelligence (AI) is increasingly becoming a key tool in medicine, not only in breast cancer diagnosis but also in other areas. Its ability to analyze large amounts of data and recognize patterns that may elude the human eye makes it an invaluable resource in modern medicine.

AI Application in Other Diagnostic Areas

In addition to mammography, AI is used in the analysis of other medical images, such as CT and MRI scans, for the early detection of various diseases. For example, in lung cancer diagnosis, AI systems help identify small nodules that may be indicators of early-stage disease.

Advantages and Challenges of Implementing AI in the Healthcare System

Implementing AI technologies in the healthcare system brings numerous advantages, including increased diagnostic accuracy, faster data processing, and reduced burden on healthcare workers. However, there are challenges, such as the need for large amounts of high-quality data to train AI models, ethical issues related to patient privacy, and the integration of these systems into existing medical processes.

The Future of AI in Medicine

AI is expected to play an even more significant role in personalized medicine in the future, providing tailored therapies based on patients' individual characteristics. Additionally, the development of AI systems that can predict the risk of developing certain diseases will enable preventive measures and early intervention, improving treatment outcomes and reducing healthcare costs.

The Future of AI in Healthcare

Initiatives such as the AI4Health.Cro competition demonstrate how artificial intelligence can play a key role in improving medical diagnostics. The development of AI models for analyzing mammographic images is just one example of how technology can aid in the early detection of diseases, optimize resources in the healthcare system, and improve patient care.

It is expected that in the future, artificial intelligence will become an indispensable tool in medicine, not only in diagnosis but also in personalized therapy, patient monitoring, and the optimization of healthcare services. However, its full potential can only be realized with proper regulation, patient data protection, and continuous technological development in collaboration with medical professionals.