Neoplasms

Urinary Tract, Sexual Organs, and Pregnancy Conditions

All Conditions

Prostatic Neoplasms

Genital Neoplasms, Male

Urogenital Neoplasms

Genital Diseases

Genital Diseases, Male

Urogenital Diseases

Prostatic Diseases

Male Urogenital Diseases

Constitution of a prospective multicenter cohort of 420 patients with suspected prostate cancer that will undergo prostate multiparametric MRI followed by systematic and targeted biopsy.

When available (i.e., at the end of the RHU PERFUSE program, November 2022), the final version of the CAD will be used retrospectively to assess the risk that the prostate/targeted lesions harbor ISUP ≥2 cancer.

In addition, a blood sample will be taken in all patients before the biopsy to assess the performance of the PHI index in predicting the presence of ISUP ≥2 cancer at systematic and targeted biopsy (ancillary study, secondary objective).

Blood sample

Follow up questionnaire

The PI-RADSv2.1 score will be compared to systematic and targeted biopsy findings (primary objective) and 3-year follow-up (secondary objective)

Human reading of prostate MR images (PI-RADSv2.1).

Olivier ROUVIERE, Pr

Adeline MANSUY, PhD

Clément Marcellin, Dr

Franck Bladou, Pr

Bénedicte Guillaume, Dr

Gaelle Fiard, MD

Philippe Puech, Pr

Arnauld Villers, Pr

Olivier Rouvière, Pr

Sébastien Crouzet, Pr

Favie Bratan, MD

Nicolas Arfi, MD

Marc André, MD

Antoine Van Hove, MD

Serge Brunelle, MD

Jochen Walz, MD

Grégoire Poinas, Dr

Ingrid Millet, Pr

Rodolphe Thuret, Pr

Eric Potiron, MD

Raphaele renardpenna, Pr

Pierre Mozer, Pr

jean-michel correas, Pr

Paul Moldovan, MD

Alain Ruffion, Pr

Guillaume Ploussard, MD/PhD

Nicolas Mottet-Auselot, Pr

Remi Grange, Dr

Catherine Roy, Pr

Thibault Tricard, Pr

aziza richard, MD

bernard malavaud, Pr

Multiparametric MRI of the prostate is recommended before each prostate biopsy. It identifies suspicious areas which will then be the subject of targeted biopsies. However, MRI suffers from low specificity and moderate inter-reader reproducibility, including with the use of the PI-RADS version 2.1 score.

We are developing, within the framework of RHU PERFUSE, a computer-aided diagnosis system (CAD) for the detection of ISUP ≥2 cancers. This system has been trained on a database of patients who had prostate MRI and prostatectomy at the Hospices Civils de Lyon and performed well on a database of patients who had prostate MRI before biopsy at the Hopices civils de Lyon.

However, one of the weaknesses of artificial intelligence systems is their low robustness when tested on MRI images from different manufacturers or institutions.

The goal of the CHANGE study is to build a prospective multicenter cohort of patients who underwent prostate multiparametric MRI followed by systematic and targeted prostate biopsies. The cohort will be used for the final external validation of the CAD developed in PERFUSE.

Detection of ISUP≥2 Prostate Cancers Using Multiparametric MRI: Prospective Multicenter Comparison of the PI-RADS Score and an Artificial Intelligence System

After publication of the results of the trial, the CHANGE cohort will be made partially accessible to other investigators wishing to test a CAD system aimed at detecting/localizing prostate cancer on MR images while respecting patient information. Request for access to pseudonymized data will be reviewed by the Trial Steering Committee that will grant access or not. To gain access, requestors will be required to sign a data access agreement. Of note, investigators will have access only to the MR images and not to the histological findings. After analysis of the CHANGE MR images by their CAD system, the investigator will be requested to send the results to the Hospices Civils de Lyon. The comparison between the CAD findings and the targeted and systematic biopsy findings will be made by the Hospices Civils de Lyon that will then inform the investigator of the CAD diagnostic performance.

AUC of the final CAD and of the PI-RADS version 2.1 score for the detection of ISUP ≥2 cancers on systematic and targeted biopsies performed after MRI, at per-patient analysis. A priori-defined non-inferiority margin: 5 percentage points.

Specificity of the final CAD and of the PI-RADSv2.1 score for the detection of ISUP ≥2 cancers on systematic and targeted biopsies performed after MRI (per-patient, per-lobe and per-lesion analysis).

Sensitivity of the final CAD and of the PI-RADSv2.1 score for the detection of ISUP ≥2 cancers on systematic and targeted biopsies performed after MRI (per-patient, per-lobe and per-lesion analysis)

AUC of the final CAD and the PI-RADSv2.1 score for predicting the diagnosis of ISUP ≥2 cancer within 3 years of follow-up, at per-patient analysis.

Sensitivity and specificity of the final CAD and the PI-RADSv2.1 score for predicting the diagnosis of ISUP ≥2 cancer within 3 years of follow-up, at per-patient analysis.

Analysis of the effect of biopsy setting, magnetic field strength, reader's experience, biopsy guidance technique and prostate volume on the AUC of the final CAD and the PI-RADv2.1, at per-patient analysis.

AUC of the PHI index for the detection of cancers ISUP ≥2 on systematic and targeted biopsies performed after MRI, at per-patient analysis.

Number of biopsies avoided and number of ISUP cancers ≥2 missed according to the strategies described below:

1. PHI index then, if positive, MRI and biopsies regardless of the MRI result (MRI used only to guide targeted biopsies).
2. PHI index then, if positive, MRI then, if positive, targeted biopsies.
3. Biopsy only if MRI positive; no PHI index.
4. MRI then, if positive, PHI index then, if positive, targeted biopsies.
5. MRI then, if negative, PHI index; biopsy for patients with a positive MRI or with a negative MRI but a positive PHI index
6. PHI index and MRI for all patients; biopsy if positive PHI index AND positive MRI.
7. PHI index and MRI for all patients; biopsy if positive PHI OR positive MRI.

Hospices Civils de Lyon

Spots Global Cancer Trial Database for follow up questionnaire