Gated-tracking: Estimation of Respiratory Motion with Confidence
Image-guided radiation therapy during free-breathing requires estimation of the target position and compensation for its motion. Estimation of the observed motion during therapy needs to be reliable and accurate. In this paper we propose a novel, image se
- PDF / 1,117,556 Bytes
- 8 Pages / 439.363 x 666.131 pts Page_size
- 14 Downloads / 190 Views
stract. Image-guided radiation therapy during free-breathing requires estimation of the target position and compensation for its motion. Estimation of the observed motion during therapy needs to be reliable and accurate. In this paper we propose a novel, image sequence-specific confidence measure to predict the reliability of the tracking results. The sequence-specific statistical relationship between the image similarities and the feature displacements is learned from the first breathing cycles. A confidence measure is then assigned to the tracking results during the realtime application phase based on the relative closeness to the expected values. The proposed confidence was tested on the results of a learning-based tracking algorithm. The method was assessed on 9 2D B-mode ultrasound sequences of healthy volunteers under free-breathing. Results were evaluated on a total of 15 selected vessel centers in the liver, achieving a mean tracking accuracy of 0.9 mm. When considering only highly-confident results, the mean (95th percentile) tracking error on the test data was reduced by 12% (16%) while duty cycle remained sufficient (60%), achieving a 95% accuracy below 3 mm, which is clinically acceptable. A similar performance was obtained on 10 2D liver MR sequences, showing the applicability of the method to a different image modality. Keywords: confidence, tracking, learning, respiratory motion, image guidance, ultrasound.
1
Introduction
Image-guided radiation therapy of abdominal organs during free-breathing requires estimation of the target position and compensation for its motion over the duration of the entire treatment session [9]. Examples of imaging techniques available for observing the internal motion are ultrasound (US) and magnetic resonance imaging (MRI). US is increasingly used, as it can image soft tissues in real time, and with higher temporal and spatial resolution than other modalities, is non-ionizing and inexpensive [4]. MRI is a popular choice for guidance of focused ultrasound surgery as it provides thermometry images, also used for tracking [15], yet the temporal resolution is about 5 times lower than US.
We thank the European Union’s 7th Framework Program (FP7/2007-2013) under grant agreement no. 611889 (TRANS-FUSIMO) for funding.
c Springer International Publishing Switzerland 2015 N. Navab et al. (Eds.): MICCAI 2015, Part III, LNCS 9351, pp. 451–458, 2015. DOI: 10.1007/978-3-319-24574-4_54
452
V. De Luca, G. Sz´ekely, and C. Tanner
The intrafraction motion estimation needs to be reliable and accurate, to reduce the size of the safety margins due to expected residual tumor motion in the planned dose delivery [19]. Gating is commonly used to reduce motion uncertainties. Yet it generally leads to relatively low duty cycles (20-50%) for maintaining acceptable accuracy [9,16]. Following the tumor motion by tracking keeps duty cycle at 100%, but can have high errors. Here we propose gated-tracking, where gating (i.e. accepting motion predictions) is based on the estimated accuracy (confidence) of t
Data Loading...
