ProCanAid: transforming prostate cancer diagnosis with a digital twin for aided detection

Blog
Tags: CancerProCanAidprostate cancer

ProCanAid is a collaborative project involving the University and Polytechnic La Fe Hospital of Valencia (HULAFE), the University of Zaragoza (UNIZAR), and Quibim. The project officially commenced with the Kick-Off Meeting (KOM) held at Quibim on December 14, 2021. Most recently, the 5th consortium meeting took place at HULAFE on November 26, 2023, where the latest progress was reviewed, and upcoming steps were discussed to ensure the successful continuation of the project.

How to know the diagnosis of prostate cancer with digital twin technology 

The main aim of the ProCanAid project is to develop a computational tool to create a 4D digital twin of the entire prostate of a patient. Novel AI-based magnetic resonance imaging (MRI) segmentation algorithms will be applied, not only to extract patient-specific prostate anatomy—transitional zone, peripheral zone, seminal vesicles—, but also to segment the lesion/s within the prostate gland. In addition, the study also seeks to develop an advanced AI algorithm capable of automatically segmenting neurovascular bundles. The infiltration fo these structures have recently been shown to be of importance in understanding the progression and invasion of prostate cancer.

ProCanAid will be the first AI-based imaging biomarkers analysis platform capable of performing accurate, automatic, medically certified and cost-effective quantitative analysis as an automatic diagnosis platform for prostate cancer (PCa) based on Multiparametric magnetic resonance imaging (mpMRI). An integrative tool (clinical data – imaging biomarkers – advanced multiscale FE simulations) for an improved

Digital Twin

A comprehensive database for twin diagnosis

The database will include clinical data, radiological and biopsy-based pathological reports, and the corresponding MRIs at diagnosis and during follow-up for 500 patients. The AI tool will incorporate in silico models considering the behavior of cells and tissues, to predict the effects of different types of oncological treatments, not only on the tumor, but also on the entire prostate. This predictive model supports a twin diagnosis approach, helping doctors understand the possible evolution of the disease.

Moreover, multiscale finite element (FE) simulations of solid tumor growth will be developed to be finally integrated into the 4D prostate digital twin. These simulations will allow clinicians to explore simulation prostate scenarios, predicting the impact of various treatment plans before the implementation.  

Clinical research in prostate cancer diagnosis 

The main challenge of the project is the combination of different technologies towards the same goal. The development of this 4D digital twin will help clinicians to make a more specific and earlier diagnosis of prostate cancer and will assist them in the treatment decision-making process and in patient follow-up. 

In addition, the combination of MRI and targeted biopsy has been shown to improve prostate cancer detection, and consequently, following this procedure, the number of unnecessary biopsies per procedure could be reduced.

Quibim’s role in ProCanAid

In ProCanAid, Quibim, as a coordinator, is taking care of project management tasks, such as organizing the bi-monthly virtual study meeting and the consortium meetings, every 6 months, having the 5th consortium meeting on 26th November 2024 in HULAFE. Quibim is also leading the development of the automated segmentation method to extract and characterize the neurovascular bundles. 

In addition, the platform is being used to host the real-world data collected in the project and to extract the imaging biomarkers for the prostate gland in all the MRIs acquired to each patient in the standard-of-care. These contributions position Quibim and our partners as a pioneers in prostate cancer research.

With ProCanAid, Quibim wants to move clinical research onto the next level.

 

Project PLEC2021-007709 (ProCanAid) funded by: