Automating Catheterization Labs with Real-Time Perception

TL;DR

A visual perception system, namely AutoCBCT, seamlessly integrated with an angiography suite, that enables a novel workflow with automated positioning, navigation and simulated test-runs, eliminating the need for manual operations and interactions.

Abstract

For decades, three-dimensional C-arm Cone-Beam Computed Tomography (CBCT) imaging system has been a critical component for complex vascular and nonvascular interventional procedures. While it can significantly improve multiplanar soft tissue imaging and provide pre-treatment target lesion roadmapping and guidance, the traditional workflow can be cumbersome and time-consuming, especially for less experienced users. To streamline this process and enhance procedural efficiency overall, we proposed a visual perception system, namely AutoCBCT, seamlessly integrated with an angiography suite. This system dynamically models both the patient's body and the surgical environment in real-time. AutoCBCT enables a novel workflow with automated positioning, navigation and simulated test-runs, eliminating the need for manual operations and interactions. The proposed system has been successfully deployed and studied in both lab and clinical settings, demonstrating significantly improved workflow efficiency.

Figures (9)

• Figure 1: Left: Conventional C-arm CBCT of the head (red dot: region of interest; orange dot: radiation center; green arrows: C-arm motion). Right: (A) Vision-empowered C-arm system in an operating room (with $\mathbf{c}_0$, $\mathbf{c}_1$, $\mathbf{c}_2$ RGB-depth sensors). (B) Paired RGB-D images obtained from the cameras. (C) Resulting fused point cloud displayed from three views.
• Figure 2: (A) Test protocol of C-arm CBCT. (B) Conventional patient positioning.
• Figure 3: Qualitative results from clinical evaluations.
• Figure 4: Qualitative results of AutoCBCT and VTR for collision detection (highlighted red regions).
• Figure 5: System overview. (A) Proposed 3D patient body modeling pipeline, refining the patient's pose and shape at each timestep. (B) Proposed virtual test run pipeline, detecting possible collisions during scanning.