PRONOBIS:A Robotic System for Automated Ultrasound-Based Prostate Reconstruction and Biopsy Planning

This paper presents the PRONOBIS project, an ultrasound-only, robotically navigated prostate scanning and biopsy treatment planning. The proposed system addresses the challenges of precise prostate reconstruction and inter-operator variability by performing fully automated prostate scanning, real-time ultrasound image processing, 3D prostate reconstruction, and biopsy needle position planning. Fully automated prostate scanning is achieved by using a robotic arm with an ultrasound system. Real-time ultrasound image processing utilizes deep learning algorithms for precise prostate segmentation. To create a high-quality prostate segmentation dataset, this paper proposes a deep-learning based medical annotation platform - MedAP. For precise segmentation of the entire prostate sweep, DAF3D and MicroSegNet models are evaluated, and additional computer vision postprocessing methods are proposed. The 3D visualization and prostate reconstruction are performed based on the segmentation results and robotic positional data, enabling robust and user-friendly biopsy treatment planning. The real-time sweep scanning and segmentation operates at 30Hz, which enables full sweep scanning in 15 to 20 seconds, depending on the prostate size. The system is evaluated on prostate phantoms by reconstructing the sweep and by performing dimensional analysis, which indicates 92\% and 98\% volumetric accuracy on used phantoms. 3D prostate reconstruction takes approximately 3 seconds and enables a fast and detailed insight for precise biopsy needle position planning.