Automated Retinal Vein Cannulation on Silicone Phantoms Using Optical-Coherence-Tomography-Guided Robotic Manipulations

Abstract

Retinal vein occlusion is one of the most common causes of vision loss, occurring when a blood clot or other obstruction occludes a retinal vein. A potential remedy for retinal vein occlusion is retinal vein cannulation, a surgical procedure that involves infusing the occluded vein with a fibrinolytic drug to restore blood flow through the vascular lumen. This work presents an image-guided robotic system capable of performing automated cannulation on silicone retinal vein phantoms. The system is integrated with an optical coherence tomography probe and camera to provide visual feedback to guide the robotic system. Through automation, the developed system targets a vein phantom to within 20 μm and automatically cannulates and infuses the vascular lumen with dyed water. The system was evaluated through 30 experimental trials and shown to be capable of performing automated cannulation of retinal vein phantoms with no reported cases of failure.

Fig. 14.

(a & b) B-scan data evaluated to detect the optical shadow cast by the micropipette, (c) detected micropipette centerline in the top view, and (d) detected steel edge, micropipette tip, and micropipette centerline in the side view.

Fig. 15.

Two examples of the OCT feedback provided to the operator at a rate of 5 Hz during automated retinal vein cannulation of (a) a Ø120 μm vein and (b) a Ø160 μm vein. The tip of the micropipette (yellow “plus” symbol) was automatically overlaid atop the data and followed the tip as it cannulated the vein. In (b), the example shown was acquired within 1 s of infusion and shows the dyed water (yellow arrow) being infused through the vein phantom.

Fig. 1.

Shown is a schematic that highlights the critical steps of retinal vein cannulation from a surgical perspective.

Fig. 2.

(a) Illustration of the OCT-integrated robotic system with coordinate frames and joint angles indicated. In this work, this system was used to demonstrate automated, image-guided retinal vein cannulation on silicone vein phantoms. (b) System-level diagram showing data and signal flow. The OCT and camera data are used as visual feedback in the automatic controller (host PC) to control the micropipette.

Fig. 3.

Photograph of piezo-actuated mechanism with mounted glass micropipette.

Fig. 4.

Illustration of the five-step process to create the retinal vein phantoms. Aside from an overnight cure time, the process was fast (approximately 10 minutes) and produced sufficiently realistic vein phantoms.

Fig. 5.

(a) Example camera image with operator-selected cannulation point, (b) B-scan cross-section of phantom, (c) region of interest (ROI), and (d) detected vein center (the output of the image-processing algorithm).

Fig. 6.

Generated vein model and with two-part trajectory for approaching the desired cannulation point.

Fig. 7.

Schematic showing the three main steps of the procedure. Solid black dots represent start points; white dots represent end points. Variable definitions are provided in the text.

Fig. 8.

Illustration of mathematical definitions during the vein targeting step. Note: Relative dimensions are not to scale and ${\overline{d}}_e$ represents the projection of d_e onto the $\widehat{X}\widehat{Z}$ plane.

Fig. 9.

The system automatically confirmed vein cannulation by detecting a color change (green to red) in the glass micropipette after vein puncture. This color change was guaranteed upon successful cannulation due to the controlled pressure differential between the blood analog inside the vein phantom and the dyed water inside the micropipette. Important steps of the image-processing algorithm included (a) selecting an ROI, (b) blurring and masking, and (c) averaging hue values to determine color.

Fig. 10.

(a) Camera view following successful vein cannulation and (b) following successful infusion. For comparison purposes only, three failure cases were manually produced via teleoperation of the robotic system outside of the scope of the experimental trials: (c) no infusion due to failed cannulation, (d) reflux, and (e) subretinal bleb formation.

Fig. 11.

Average time requirements across all trials. The majority of time was spent acquiring OCT C-scans and translating the OCT probe.

Fig. 12.

(a) Side view and (b) top view of OCT data demonstrating OCT-based visual servoing of the micropipette during the vein targeting step for the more common two-iteration case. (c) The calculated error shows a fast (two iteration) decrease to less than the error threshold (20 μm).

Fig. 13.

Fabrication differences between phantoms resulted in a variety of vein depths (open dots), but the system was able to target each (solid dots) with acceptable error (vertical bars).