Detection of ISUP≥2 Prostate Cancers Using Multiparametric MRI: Prospective Multicenter Comparison of the PI-RADS Score and an Artificial Intelligence System
Overview
- Phase
- N/A
- Intervention
- Not specified
- Conditions
- Prostate Cancer
- Sponsor
- Hospices Civils de Lyon
- Enrollment
- 420
- Locations
- 17
- Primary Endpoint
- Evaluation of the non-inferiority of the AUC of the final CAD developed in the PERFUSE program for the detection of ISUP ≥2 cancers, as compared to that of the PI-RADSv2.1 score (human reading), at per-patient analysis.
- Status
- Recruiting
- Last Updated
- 2 years ago
Overview
Brief Summary
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.
Investigators
Eligibility Criteria
Inclusion Criteria
- •Men over 18 years of age
- •Patient with clinical suspicion of prostate cancer referred for a multiparametric MRI of the prostate before a first series of biopsies or before new biopsies after one or more series of negative biopsies
- •PSA ≤ 30 ng / ml
- •Clinical stage ≤ T2c
- •Affiliation or beneficiary of a social security scheme
Exclusion Criteria
- •Men over 80 years of age
- •PSA\> 30 ng / ml
- •Stage T3 or T4 on digital rectal examination
- •Previous prostate biopsy performed within 12 months
- •History of prostate cancer diagnosed by biopsy or endourethral resection.
- •History of pelvic radiotherapy regardless of the cause.
- •History of total or focal treatment for prostate cancer.
- •History of hormone therapy
- •MRI performed more than 3 months before biopsy
- •Prostate MRI performed on a machine other than the center's machines accredited for the study.
Outcomes
Primary Outcomes
Evaluation of the non-inferiority of the AUC of the final CAD developed in the PERFUSE program for the detection of ISUP ≥2 cancers, as compared to that of the PI-RADSv2.1 score (human reading), at per-patient analysis.
Time Frame: Through recruitment completion, an average of 2 years
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.
Secondary Outcomes
- Comparison of the sensitivities of the CAD and of the PI-RADSv2.1 score for the detection of ISUP ≥2 cancers at per-patient, per-lobe and per-lesion analysis .(Through recruitment completion, an average of 2 years)
- Comparison of the specificities of the CAD and of the PI-RADSv2.1 score for the detection of ISUP ≥2 cancers at per-patient, per-lobe and per-lesion analysis.(Through recruitment completion, an average of 2 years)
- Comparison of the AUCs of the final CAD and of the PI-RADSv2.1 score for predicting the diagnosis of ISUP ≥2 cancer within 3 years, at per-patient analysis.(Through recruitment completion, an average of 2 years)
- Comparison of the sensitivities and specificities of the final CAD and the PI-RADSv2.1 score for predicting the diagnosis of ISUP ≥2 cancer within 3 years, at per-patient analysis.(Through study completion, an average of 5 years)
- Comparison of the AUC of the PHI index to that of the final CAD and of the PI-RADSv2.1 score for the detection of ISUP ≥2 cancers, at per-patient analysis.(Through recruitment completion, an average of 2 years)
- Estimation of the number of biopsies avoided and the number of ISUP cancers ≥2 missed for the following diagnostic strategies:(Through recruitment completion, an average of 2 years)
- Assessment of the impact of biopsy setting, magnetic field strength, human reader's experience, biopsy guidance technique and prostate volume on the AUC of the CAD and the PI-RADSv2.1 scores for the detection of ISUP cancers ≥2, at per-patient analysis.(Through recruitment completion, an average of 2 years)