Fiducial marker recovery and detection from severely truncated data in navigation assisted spine surgery

Fan F, Kreher BW, Keil H, Maier A, Huang Y (2022)


Publication Language: English

Publication Type: Journal article, Original article

Publication year: 2022

Journal

DOI: 10.1002/mp.15617

Abstract

Purpose: Fiducial markers are commonly used in navigation assisted minimally invasive spine surgery and they help transfer image coordinates into real world coordinates. In practice, these markers might be located outside the field-of-view (FOV) of C-arm cone-beam computed tomography (CBCT) systems used in intraoperative surgeries, due to the limited detector sizes. As a consequence, reconstructed markers in CBCT volumes suffer from artifacts and have distorted shapes, which sets an obstacle for navigation.
Methods: In this work, we propose two fiducial marker detection methods: direct detection from distorted markers (direct method) and detection after marker recovery (recovery method). For direct detection from distorted markers in reconstructed volumes, an efficient automatic marker detection method using {two neural networks and a conventional circle detection algorithm} is proposed. For marker recovery, a task-specific learning strategy is proposed to recover markers from severely truncated data. Afterwards, a conventional marker detection algorithm is applied for position detection.
Results: The two methods are evaluated on simulated and real data. The direct method achieves 100% detection rates with maximal 2-pixel difference on simulated data with normal truncation and simulated data with severe noise, but fails to detect all the markers in extremely severe truncation case. The recovery method detects all the markers successfully with maximal 1 pixel difference on all simulated data sets. For real data, both methods achieve 100% marker detection rates with mean registration error below 0.2 mm.
Conclusions: Our experiments demonstrate that the direct method is capable of detecting distorted markers accurately and the recovery method with task-specific learning has high robustness and generalizability on various data sets.
The task-specific learning is able to reconstruct structures of interest outside the FOV from severely truncated data, which has the potential to empower CBCT systems with new applications.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Fan, F., Kreher, B.W., Keil, H., Maier, A., & Huang, Y. (2022). Fiducial marker recovery and detection from severely truncated data in navigation assisted spine surgery. Medical Physics. https://doi.org/10.1002/mp.15617

MLA:

Fan, Fuxin, et al. "Fiducial marker recovery and detection from severely truncated data in navigation assisted spine surgery." Medical Physics (2022).

BibTeX: Download