To report the development of artificial intelligence (AI)-based software to allow for the autonomous fusion of transrectal ultrasound and multiparametric magnetic resonance images of the prostate to be used during transperineal prostate biopsies.
This study was approved by the Institutional Review Board (protocol ID3167CESC). The automatic software development for fusion biopsy involved three steps: 1) Developing an AI component to segment the prostate during ultrasound; 2) Developing the component to segment anatomical structures in magnetic resonance images using labeled datasets from the Cancer Imaging Archive and in-house scans; 3) Developing the fusion component to register segmented ultrasound and magnetic resonance images using a three-step process: pre-alignment, rigid alignment, and elastic fusion, validated by measuring the lesion distance between modalities. Statistical analysis included descriptive statistics and the Mann-Whitney U test, evaluating outcomes with Dice scores and average precision metrics.
The ultrasound component showed a Dice score of 0.87 with a test set of 75,357 images and 28,946 annotations. The magnetic resonance component achieved a Dice score of 0.85 on a test set of 2,494 images and annotations. It also demonstrated a mean Average Precision of 0.80 for bounding boxes and 0.88 for segmented objects, both measured at a 50% intersection over union threshold. The fusion AI component reduced the median magnetic resonance-ultrasound lesion distance from 8 mm (IQR 6-9) after rigid fusion to 4 mm (IQR 3-5) after elastic fusion (p<0.001).
A data processing pipeline and AI were created to allow for the autonomous fusion of ultrasound and magnetic resonance images to be ideally used during transperineal prostate biopsies.
Urology. 2025 Mar 11 [Epub ahead of print]
Francesco Cianflone, Bogdan Maris, Riccardo Bertolo, Alessandro Veccia, Francesco Artoni, Greta Pettenuzzo, Francesca Montanaro, Antonio Benito Porcaro, Alberto Bianchi, Sarah Malandra, Francesco Ditonno, Maria Angela Cerruto, Giulia Zamboni, Paolo Fiorini, Alessandro Antonelli
Department of Surgery, Dentistry, Pediatrics and Gynecology, Urology Unit, Azienda Ospedaliera Universitaria Integrata, University of Verona, Verona, Italy., Department of Engineering for Innovation Medicine, Verona, Italy., Department of Surgery, Dentistry, Pediatrics and Gynecology, Urology Unit, Azienda Ospedaliera Universitaria Integrata, University of Verona, Verona, Italy. Electronic address: ., Department of Diagnostic and Public Health, Unit of Radiology, Azienda Ospedaliera Universitaria Integrata, University of Verona, Verona, Italy.