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

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.

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).

Time frame: Through recruitment completion, an average of 2 years

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 .

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)

Time frame: 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.

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.

Time frame: 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.

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.

Time frame: Through study completion, an average of 5 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.

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.

Time frame: Through recruitment completion, an average of 2 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.

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

Time frame: 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:

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.

Time frame: Through recruitment completion, an average of 2 years