Evaluation of 2D and 3D ultrasound tracking algorithms and impact on ultrasound-guided liver radiotherapy margins.

Autor: De Luca V; Computer Vision Laboratory, ETH Zurich, Zürich, Switzerland.; Novartis Institutes for Biomedical Research, Basel, Switzerland., Banerjee J; Translational Imaging Group, University College London, London, UK., Hallack A; Institute of Biomedical Engineering, University of Oxford, Oxford, UK., Kondo S; Konica Minolta Inc., Osaka, Japan., Makhinya M; Computer Vision Laboratory, ETH Zurich, Zürich, Switzerland., Nouri D; Natural Vision UG, Berlin, Germany., Royer L; Institut de Recherche Technologique b-com, Rennes, France., Cifor A; Mirada Medical, Oxford, UK., Dardenne G; Institut de Recherche Technologique b-com, Rennes, France., Goksel O; Computer Vision Laboratory, ETH Zurich, Zürich, Switzerland., Gooding MJ; Mirada Medical, Oxford, UK., Klink C; Department of Radiology, Erasmus MC, Rotterdam, The Netherlands., Krupa A; Institut de Recherche Technologique b-com, Rennes, France., Le Bras A; Institut de Recherche Technologique b-com, Rennes, France., Marchal M; Institut de Recherche Technologique b-com, Rennes, France., Moelker A; Department of Radiology, Erasmus MC, Rotterdam, The Netherlands., Niessen WJ; Department of Radiology, Erasmus MC, Rotterdam, The Netherlands., Papiez BW; Institute of Biomedical Engineering, University of Oxford, Oxford, UK., Rothberg A; 4Catalyzer Inc., Guilford, CT, USA., Schnabel J; School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK., van Walsum T; Department of Radiology, Erasmus MC, Rotterdam, The Netherlands., Harris E; Institute of Cancer Research, London, UK., Lediju Bell MA; Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, USA., Tanner C; Computer Vision Laboratory, ETH Zurich, Zürich, Switzerland.
Jazyk: angličtina
Zdroj: Medical physics [Med Phys] 2018 Nov; Vol. 45 (11), pp. 4986-5003. Date of Electronic Publication: 2018 Oct 01.
DOI: 10.1002/mp.13152
Abstrakt: Purpose: Compensation for respiratory motion is important during abdominal cancer treatments. In this work we report the results of the 2015 MICCAI Challenge on Liver Ultrasound Tracking and extend the 2D results to relate them to clinical relevance in form of reducing treatment margins and hence sparing healthy tissues, while maintaining full duty cycle.
Methods: We describe methodologies for estimating and temporally predicting respiratory liver motion from continuous ultrasound imaging, used during ultrasound-guided radiation therapy. Furthermore, we investigated the trade-off between tracking accuracy and runtime in combination with temporal prediction strategies and their impact on treatment margins.
Results: Based on 2D ultrasound sequences from 39 volunteers, a mean tracking accuracy of 0.9 mm was achieved when combining the results from the 4 challenge submissions (1.2 to 3.3 mm). The two submissions for the 3D sequences from 14 volunteers provided mean accuracies of 1.7 and 1.8 mm. In combination with temporal prediction, using the faster (41 vs 228 ms) but less accurate (1.4 vs 0.9 mm) tracking method resulted in substantially reduced treatment margins (70% vs 39%) in contrast to mid-ventilation margins, as it avoided non-linear temporal prediction by keeping the treatment system latency low (150 vs 400 ms). Acceleration of the best tracking method would improve the margin reduction to 75%.
Conclusions: Liver motion estimation and prediction during free-breathing from 2D ultrasound images can substantially reduce the in-plane motion uncertainty and hence treatment margins. Employing an accurate tracking method while avoiding non-linear temporal prediction would be favorable. This approach has the potential to shorten treatment time compared to breath-hold and gated approaches, and increase treatment efficiency and safety.
(© 2018 American Association of Physicists in Medicine.)
Databáze: MEDLINE
Externí odkaz: