An AI Platform Integrating Imaging Data and Models, Supporting Precision Care Through Prostate Cancer's Continuum

In Europe, prostate cancer (PCa) is the second most frequent type of cancer in men and the fifth most lethal. Current clinical practices, often leading to overdiagnosis and overtreatment of indolent tumors, suffer from lack of precision calling for advanced AI models to go beyond SoA by deciphering non-intuitive, high-level medical image patterns and increase performance in discriminating indolent from aggressive disease, early predicting recurrence and detecting metastases or predicting effectiveness of therapies. To date efforts are fragmented, based on single-institution, size-limited and vendorspecific datasets while available PCa public datasets (e.g. US TCIA) are only few hundred cases making model generalizability impossible.

The ProCAncer-I project brings together 20 partners, including PCa centers of reference, world leaders in AI and innovative SMEs, with recognized expertise in their respective domains, with the objective 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 (mp)MRI, anonymized image data worldwide (>14,000 cases), based on data donorship, in line with EU legislation (GDPR). Robust AI models are developed, based on novel ensemble learning methodologies, leading to vendor-specific and -neutral AI models for addressing 8 PCa clinical scenarios.

To accelerate clinical translation of PCa AI models, we focus on improving the trust of the solutions with respect to fairness, safety, explainability and reproducibility. Metrics to monitor model performance and a causal explainability functionality are developed to further increase clinical trust and inform on possible failures and errors. A roadmap for AI models certification is defined, interacting with regulatory authorities, thus contributing to a European regulatory roadmap for validating the effectiveness of AI-based models for clinical decision making.

Study Overview

• Status: Completed
• Conditions: Prostate Cancer; Prostate Cancer Recurrent; Prostate Cancer Metastatic; Prostate Cancer Aggressiveness
• Intervention / Treatment: Diagnostic test: Magnetic Resonance Imaging

• Study Type: Observational
• Enrollment (Actual): 14000

Contacts and Locations

Study Locations

• Italy
  • Italy
    • Candiolo, Italy, Italy, 10060
      • Fondazione del Piemonte per l'Oncologia

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years to 85 years (Adult, Older Adult)
• Accepts Healthy Volunteers: Yes

• Sampling Method: Non-Probability Sample

Study Population

Patients who underwent MRI examination with pathological confirmation of prostate cancer (positive group) or at least 1-year follow-up to exclude presence of prostate cancer (negative group).

Description

Inclusion Criteria:

1. histological confirmed PCa or suspicion of PCa (abnormal PSA values and/or positive DRE);
2. magnetic resonance imaging examination, including at least a high-resolution axial T2-weighted imaging and axila diffusion-weighted imaging (dynamic contrast-enhanced imaging is recommended, but not mandatory);
3. age ≥ 18 years at the time of diagnosis
4. signed written informed consent form (only for prospective enrollement).

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Retrospective (training model)	Diagnostic test: Magnetic Resonance Imaging; Patients who underwent MRI with confirmed pathology data (either biopsy or prostatectomy)
Prospective (validation model)	Diagnostic test: Magnetic Resonance Imaging; Patients who underwent MRI with confirmed pathology data (either biopsy or prostatectomy)

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Time Frame
To create a repository (Prostate-NET) of retrospective MRI examinations with related clinical and pathology data dedicated to prostate cancer.	24 months
To use the retrospective data collection (Prostate-NET) to solve 9 different clinical scenarios to improve diagnosis, characterization, treatment and follow-up of men with prostate cancer.	36 months
To develop vendor-specific and vendor neutral AI models exploiting the prospective data that will be uploaded to the Prostate-NET platform.	48 months

Collaborators and Investigators

• Sponsor: Fondazione del Piemonte per l'Oncologia
• Collaborators: National Cancer Institute (NCI); University of Pisa; Royal Marsden NHS Foundation Trust; Hacettepe University; Institut d'Investigació Biomèdica de Girona Dr. Josep Trueta; University of Vienna; Institut Paoli-Calmettes; Fondazione C.N.R./Regione Toscana "G. Monasterio", Pisa, Italy; Fundacion Para La Investigacion Hospital La Fe; Stichting Katholieke Universiteit; Fundacao Champalimaud; QS INSTITUTO DE INVESTIGACION E INNOVACION SL; IDRYMA TECHNOLOGIAS KAI EREVNAS; THE GENERAL HOSPITAL CORPORATION; BIOTRONICS 3D LIMITED; QUIBIM SOCIEDAD LIMITADA; JCC DIAGNOSTIC IMAGING; Agios Savas; Advantis Medical Imaging
• Investigators: Study Director: Manolis Tsiknakis, FORTH; Study Chair: Nickolas Papanikolau, Fundacao Champalimaud; Study Chair: Kostantinos Marias, FORTH

Study record dates

Study Major Dates

• Study Start (Actual): February 24, 2021
• Primary Completion (Actual): March 31, 2025
• Study Completion (Actual): March 31, 2025

Study Registration Dates

• First Submitted: May 17, 2022
• First Submitted That Met QC Criteria: May 17, 2022
• First Posted (Actual): May 20, 2022

Study Record Updates

• Last Update Posted (Actual): June 4, 2026
• Last Update Submitted That Met QC Criteria: June 3, 2026
• Last Verified: June 1, 2026

More Information

Terms related to this study

• Keywords: prostate cancer; repository; open image space; annotated and under donorship images; quality of image providers; cloud infrastructure; tools to build AI applications; advanced AI techniques
• Additional Relevant MeSH Terms: Urogenital Diseases; Genital Diseases; Genital Neoplasms, Male; Urogenital Neoplasms; Neoplasms by Site; Neoplasms; Genital Diseases, Male; Prostatic Diseases; Male Urogenital Diseases; Prostatic Neoplasms; Prostate Cancer, Hereditary, 7; Diagnostic Techniques and Procedures; Diagnosis; Tomography; Diagnostic Imaging; Magnetic Resonance Imaging
• Other Study ID Numbers: ProCAncer-I

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No