Creation of an Image Database for the Development of a Computer Aided Diagnostic (CAD) System in Patients With Prostate Cancer

Creation of a Multimodality Image Database (MRI + Ultrasound) for the Development of a Computer Aided Diagnostic (CAD) System in Patients With Prostate Cancer

Prostate cancer is currently detected by ultrasound-guided biopsy. Computer-aided diagnostic (CAD) systems based on multiparametric MRI are now capable of detecting most aggressive cancer foci non-invasively, but additional progress is needed for the technique to be accepted in clinical practice. We hypothesize that combining MRI and ultrasound imaging can improve the detection of cancerous tumors. As a first step in this direction, we need to create a database with MR images, 3D ultrasound images, and corresponding histopathology results, in patients treated by radical prostatectomy for prostate cancer. This is the purpose of the present study.

In a later stage (outside the scope of this study), we will be learning how to combine these images to best recognize cancerous tumors, we will use that knowledge to develop a new CAD system, and we will assess the performance of the new CAD. We expect this future system to improve the detection of prostate cancer and to reduce the number of patients requiring biopsy.

Inclusion Criteria:

• Patient referred for radical prostatectomy
• Patient with multiparametric prostate MRI (3T) performed in our institution (Edouard Herriot Hospital) in the year preceding the surgery
• Informed consent signed
• Patient affiliated to the French Health Insurance system

Exclusion Criteria:

• History of prostatic surgery or radiation therapy (prostatic or pelvic)
• History of hormone therapy for prostate cancer
• Previous surgery of the abdomino-perineal region, or other contraindication for transrectal ultrasound
• Patient on protection of the court, under supervision or under trusteeship
• Inability to express a consent