ProCAncer-I: An AI Platform Integrating Imaging Data and Models, Supporting Precision Care Through Prostate Cancer's Continuum
Study Details
Study Description
Brief Summary
Currently, in the clinical landscape of PCa, much of the AI work is limited to single-centre, single AI-architecture analyses and critically, on small data sets. ProCAncer-I will create a vast, diversified and multidisciplinary repository, fed by a large collection of mp-MRI. The participating clinical partners will congregate mp-MRI and clinical data, retrospectively and prospectively, from more than 17.000 PCa patients (11.000 retrospective and 6.000 prospective mp-MRI cases), including baseline examinations and follow up studies to form the ProstateNET dataset, counting more than 1.5 million image representations of the prostate (cancerous, non-cancerous and benign cases).
ProCAncer-I aims to address the unmet clinical needs in PCa regarding precision diagnosis and personalised disease management with a disruptive paradigm change in clinical research, exploiting a novel multi centre collaboration, comprising a master-global model, boosted with MRI and AI modelling methodology. ProCAncer-I will deal with both retrospective and prospective data. Retrospective data will be collected and will be used to implement and train AI algorithms by other partners of the Consortium. Similarly, prospective data will be collected for the development of vendor specific models and external validation of AI models.
| Condition or Disease | Intervention/Treatment | Phase |
|---|---|---|
|
|
Detailed Description
In Europe, prostate cancer (PCa) is the second most frequent type of cancer in men and the third most lethal. Current clinical practices, often leading to overdiagnosis and overtreatment of indolent tumors, suffer from lack of precision.
This calls for advanced Artificial Intelligence (AI) models to decipher non-intuitive, high-level medical image patterns and increase performance in discriminating indolent from aggressive disease early on. This extends to these models also predicting recurrence, detecting metastases and predicting the effectiveness of therapies. To date, efforts in this field are fragmented, based on single-institution, size-limited and vendor-specific datasets while available PCa public datasets are only a few hundred cases, making model generalisability impossible.
The ProCAncer-I project brings together 13 partners (the consortium), including The Royal Marsden NHS Foundation Trust (RMH), PCa centers, world leaders in AI and innovative enterprises with recognised expertise in their respective domains. The objective is to design, develop and sustain a cloud-based, secure European Image Infrastructure with tools and services for data handling. The platform hosts the largest collection of PCa multi-parametric Magnetic Resonance Imaging (mpMRI) scans and anonymised image data worldwide with more than 17,000 cases, based on retrospective and prospective data from the consortium in line with EU legislation (GDPR).
Robust AI models will be developed, based on novel learning methodologies, leading to AI models that will address nine PCa clinical scenarios. To accelerate the clinical adoption of PCa AI models, the project focuses on improving the trust in the AI solutions with respect to fairness, safety, explainability and reproducibility. Metrics to monitor model performance are being developed to further increase clinical trust and inform on possible failures and errors, hopefully validating the effectiveness of AI-based models for clinical decision making.
Study Design
Outcome Measures
Primary Outcome Measures
- Primary Study Objective [Protocol duration, 2 years]
The primary objective of the research is to create a vast, diversified and multidisciplinary repository, fed by a large collection of mp-MRI scans, including a high-resolution T2-weighted imaging and at least two physiology-based MRI techniques (diffusion-weighted (DW) and dynamic contrast-enhanced (DCE) imaging)
Secondary Outcome Measures
- Secondary Study Objective [Protocol duration, 2 years]
To develop AI models in the context of nine clinical scenarios including detection, characterisation and treatment response of PCa.
Other Outcome Measures
- Exploratory Objectives [Protocol duration, 2 years]
To identify/validate new prognostic and predictive markers in PCa patients.
Eligibility Criteria
Criteria
Inclusion Criteria:
-
mp-MRI imaging including a high-resolution T2-weighted imaging and at least two physiology-based MRI techniques (DW, DCE imaging);
-
results of histology (either biopsy or prostatectomy) or a minimum one-year clinical follow-up in men with no disease evidence at baseline mp-MRI;
-
age >18 years at the time of diagnosis.
-
written informed consent (for Pro-Cancer-I-Prospective only)
Exclusion Criteria:
- There are no exclusion criteria specified in this study protocol.
Contacts and Locations
Locations
| Site | City | State | Country | Postal Code | |
|---|---|---|---|---|---|
| 1 | Department of Radiology, The Royal Marsden NHS Foundation Trust | Sutton | Surrey | United Kingdom | SM2 5PT |
Sponsors and Collaborators
- Royal Marsden NHS Foundation Trust
Investigators
- Study Chair: Manolis Tsiknakis, Computational Bio-Medicine Laboratory (CBML) Institute of Computer Science (ICS) Foundation for Research and Technology - Hellas (FORTH)
Study Documents (Full-Text)
None provided.More Information
Publications
None provided.- CCR5616