Editorial by Prof Manolis Tsiknakis, Coordinator of ProCAncer-I project
The ProCAncer-I consortium welcomes you to our first newsletter!
We are very happy that our project ProCAncer-I on dealing with prostate cancer was funded by the EU and that through its successful implementation, we may contribute to the better diagnosis, management and therapy of prostate cancer.
In Europe, prostate cancer (PCa) is the second most frequent type of cancer in men and the third most lethal. Considering that about 1,300,000 citizens of the European Union are estimated to have had a prostate cancer diagnosis in the last five years, the severe socioeconomic burden for health services and the negative effects on the quality of life of patients call for immediate actions.
The fact is that in the domain of PCa detection, treatment and/or management, several pressing and unmet needs do currently exist. Current screening practices based on prostate serum antigen (PSA) blood test and digital rectal examination (DRE) have led to significant overdiagnosis, i.e. the diagnosis of indolent tumours which, once diagnosed, are treated as a deadly disease with radical therapies that severely affect patient quality of life.
At the same time, Artificial Intelligence (AI) is transforming the field of healthcare in general and medical imaging in specific. Worldwide interest in artificial intelligence (AI) applications, including imaging, is high and growing rapidly, fueled by the availability of large datasets (“big data”), substantial advances in computing power, and new algorithms. Recent advances in AI methodologies have made great strides in automatically quantifying radiographic patterns in medical imaging data. Deep learning, a subset of AI, is an especially promising method that automatically learns feature representations from sample images and has been shown to match and even surpass human performance in task-specific applications.
The project “ProCAncer-I: An AI Platform integrating imaging data and models, supporting precision care through prostate cancer’s continuum”, focuses on developing advanced AI-base models that go beyond current SoA by deciphering non-intuitive, high-level medical image patterns in a) discriminating indolent from aggressive disease, b) early predicting recurrence and detecting metastases or c) predicting the effectiveness of therapies. To achieve this, the project will generate a large interoperable repository of health images, and a scalable high-performance computing platform hosting the largest collection of PCa Magnetic Resonance Images (an estimated 1,5 Million images coupled with accompanying clinical data) to be used for developing these robust PCa AI models.
ProCAncer-I recognizes that while computational techniques to build AI-based models for medical care have been pursued for years, there is currently a more urgent need to build AI solutions that can be trusted in order to be accepted by regulating bodies and adopted by the clinical community. Although AI-based models hold promise for improving care, especially in imaging diagnosis, robust evaluation of AI-based software before implementation is needed to reduce patient and health system risk, establish trust, and facilitate wide adoption. Towards this direction, the project is devoting significant efforts in developing the methodological framework and tools to support the fairness, robustness, traceability and explainability of the models to be developed.
The ProCAncer-I project (https://www.procancer-i.eu/) brings together the best of bread in the technological, scientific and clinical domains, a unique team of 20 institutions from 12 different countries from Europe and elsewhere. It combines expertise from academia and the market with vibrant and dynamic SMEs with a proven track record, as well as non-profit research institutions and leading university hospitals in the field of prostate cancer. It’s a balanced consortium geographical wise with partners from East and West Europe as well as from Turkey and the US.