Investigative Ophthalmology & Visual Science Cover Image for Volume 65, Issue 7
June 2024
Volume 65, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2024
Low-latency surgical scene imaging with scene prediction and dynamics-aware scans
Author Affiliations & Notes
  • Dhyey Manish Rajani
    Robotics, University of Michigan, Ann Arbor, Michigan, United States
  • Federico Seghizzi
    Robotics, University of Michigan, Ann Arbor, Michigan, United States
  • Yang-Lun Lai
    Robotics, University of Michigan, Ann Arbor, Michigan, United States
  • Koerner Gray Buchta
    Robotics, University of Michigan, Ann Arbor, Michigan, United States
  • Mark Draelos
    Robotics, University of Michigan, Ann Arbor, Michigan, United States
    Ophthalmology, University of Michigan, Ann Arbor, Michigan, United States
  • Footnotes
    Commercial Relationships   Dhyey Manish Rajani None; Federico Seghizzi None; Yang-Lun Lai None; Koerner Buchta None; Mark Draelos Horizon Surgical Systems, Code C (Consultant/Contractor)
  • Footnotes
    Support  NIH R00EY034200
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 5920. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Dhyey Manish Rajani, Federico Seghizzi, Yang-Lun Lai, Koerner Gray Buchta, Mark Draelos; Low-latency surgical scene imaging with scene prediction and dynamics-aware scans. Invest. Ophthalmol. Vis. Sci. 2024;65(7):5920.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : Point-scan optical coherence tomography (OCT) is limited by a tradeoff between scan resolution and frame rate, which may introduce unacceptable latency for surgical scene imaging. To overcome this issue, we exploit an adaptive scanning strategy to scan regions of higher interest with greater frequency, enabling faster performance without reducing quality.

Methods : We extend our probabilistic adaptive scanning paradigm with machine learning and path planning to intelligently determine when and where to collect OCT data. To enable anticipation of object motion, we leverage the convolutional long short-term memory (ConvLSTM) neural network architecture to extract spatio-temporal characteristics of frame sequences that generalize well across different scenes (Fig. 1). This network determines the lateral positions for data acquisition, which we combine with random exploration to discover unknown objects. We then derive the corresponding scan path by formulating and solving a clustered traveling salesperson problem (CTSP) that seeks the shortest duration path subject to the known dynamic limits of our scanner hardware. The full scene is reconstructed from only the visited positions. To evaluate our system, we collected real-time OCT data on surgically-relevant imaging phantoms, including one designed to simulate ophthalmic surgical forceps.

Results : When imaging our forceps-shaped phantom, adaptive scanning with ConvLSTM and CTSP operated 2.97x faster than dense raster scanning and created high-fidelity images while imaging only 9.7% of the scene on average. Despite limited scene coverage, qualitative inspection of the resulting OCT data (Fig. 2) demonstrates an improvement in object boundaries compared to our prior approach.

Conclusions : Trajectory generation using CTSPs for scan planning and the predictive capabilities of ConvLSTM not only enhance the scan efficiency but also reduce the image latency. This approach maintains a high level of scene fidelity throughout the scanning process.

This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.

 

Adaptive scanning pipeline for scene prediction and dynamics-aware scan trajectories.

Adaptive scanning pipeline for scene prediction and dynamics-aware scan trajectories.

 

Side-by-side comparison (a) of image quality for our prior probabilistic adaptive scanning (PAS) approach and adaptive scanning with ConvLSTM and CTSP capabilities using surgical (Forceps) and non-surgical (Shapes) phantoms. OCT data time series (b) indicating fraction of scene scanned (α) and instantaneous speedup factor (γ).

Side-by-side comparison (a) of image quality for our prior probabilistic adaptive scanning (PAS) approach and adaptive scanning with ConvLSTM and CTSP capabilities using surgical (Forceps) and non-surgical (Shapes) phantoms. OCT data time series (b) indicating fraction of scene scanned (α) and instantaneous speedup factor (γ).

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×