A kernel-based method for markerless tumor tracking in kV fluoroscopic images

Abstract

Markerless tracking of respiration-induced tumor motion in kilo-voltage (kV) fluoroscopic image sequence is still a challenging task in real time image-guided radiation therapy (IGRT). Most of existing markerless tracking methods are based on a template matching technique or its extensions that are frequently sensitive to non-rigid tumor deformation and involve expensive computation. This paper presents a kernel-based method that is capable of tracking tumor motion in kV fluoroscopic image sequence with robust performance and low computational cost. The proposed tracking system consists of the following three steps. To enhance the contrast of kV fluoroscopic image, we firstly utilize a histogram equalization to transform the intensities of original images to a wider dynamical intensity range. A tumor target in the first frame is then represented by using a histogram-based feature vector. Subsequently, the target tracking is then formulated by maximizing a Bhattacharyya coefficient that measures the similarity between the tumor target and its candidates in the subsequent frames. The numerical solution for maximizing the Bhattacharyya coefficient is performed by a mean-shift algorithm. The proposed method was evaluated by using four clinical kV fluoroscopic image sequences. For comparison, we also implement four conventional template matching-based methods and compare their performance with our proposed method in terms of the tracking accuracy and computational cost. Experimental results demonstrated that the proposed method is superior to conventional template matching-based methods.

Motion management in particle therapy

“…"Supervised learning IGPT" combines IGPT and machine learning. Several publications have reported on markerless tumor tracking techniques using kernel-based algorithms, 36 regression analysis, [37][38][39] and the multiple-template-matching technique. 40 Intrafractional bony structure motion, especially that of ribs, can pose a problem in markerless tumor tracking in the thorax, but may be dealt with by dual-energy subtraction.…”

Tumor motion tracking using kV/MV X-ray fluoroscopy for adaptive radiation therapy

“…Most of existing methods are based on the template matching technique or its extensions. In our previous study [13], [15], we have proposed a kernel-based method for tracking lung tumor motion in kV fluoroscopy. The proposed method is based on a well-known visual tracking technique named as mean-shift algorithm [3] that formulates the tracking problem as a statistical optimization process.…”

“…This paper summarizes our recent studies on development of markerless tumor tracking system for adaptive radiation therapy. We will briefly introduce the kV and MV X-ray fluoroscopic imaging systems used in radiation therapy, and present a kernel-based algorithm for tracking lung tumor position in kV fluoroscopy [13], [15] and a level set method (LSM)-based algorithm for tracking tumor boundary in MV fluoroscopy [14], [16].…”

A new scheme for real-time high-contrast imaging in lung cancer radiotherapy: a proof-of-concept study

“…These methods may still present poor correlation between the surrogate and tumor motion (Ahn et al , 2004; Hoisak et al , 2004; Tsunashima et al , 2004; Yan et al , 2006). Projection based imaging methods are another subcategory of marker-less motion monitoring and include kV fluoroscopy and MV Beam Eye View (BEV) images (Berbeco et al , 2004; Jiang, 2004; Berbeco et al , 2005; Cho et al , 2009; Lin et al , 2009; Rottmann et al , 2010; Yang et al , 2012; Rottmann et al , 2013; Yan et al , 2013; Zhang et al , 2014). However, the projection nature of these approaches superimposes 3D anatomy on a 2D plane.…”