Computerized method for estimation of the location of a lung tumor on EPID cine images without implanted markers in stereotactic body radiotherapy

Abstract

The purpose of this study was to develop a computerized method for estimation of the location of a lung tumor in cine images on an electronic portal imaging device (EPID) without implanted markers during stereotactic body radiotherapy (SBRT). Each tumor region was segmented in the first EPID cine image, i.e., reference portal image, based on a multiple-gray level thresholding technique and a region growing technique, and then the image including the tumor region was cropped as a 'tumor template' image. The tumor location was determined as the position in which the tumor template image took the maximum cross-correlation value within each consecutive portal image, which was acquired in cine mode on the EPID in treatment. EPID images with 512 x 384 pixels (pixel size: 0.56 mm) were acquired at a sampling rate of 0.5 frame s(-1) by using energies of 4, 6 or 10 MV on linear accelerators. We applied our proposed method to EPID cine images (226 frames) of 12 clinical cases (ages: 51-83, mean: 72) with a non-small cell lung cancer. As a result, the average location error between tumor points obtained by our method and the manual method was 1.47 +/- 0.60 mm. This preliminary study suggests that our method based on the tumor template matching technique might be feasible for tracking the location of a lung tumor without implanted markers in SBRT.

Feasibility Study for Markerless Tracking of Lung Tumors in Stereotactic Body Radiotherapy

“…However, the approach of markerless tumor tracking in EPID movies could be improved with the help of external motion signals (5), with further image processing of the EPID movies to improve the signal-to-noise-contrast, or based on machine learning algorithms (4,17). Tang et al recently published a method to decide if the tumor is either inside or outside the beam aperture based on neural networks (17).…”

“…Precise assessment and quantification of breathinginduced target motion and its integration into the treatment workflow are essential for adaptive treatment techniques (1). Existing strategies for tumor tracking approaches can be grouped roughly into three categories: external surrogate based (2,3), markerless (4)(5)(6), and internal marker-based systems (7)(8)(9).…”

Enhancement of megavoltage electronic portal images for markerless tumor tracking

“…The contrast value was calculated as follows: $\text{Contrast}=\frac{I_{\mathrm{normalw}}-I_{\mathrm{normalb}}}{I_{\mathrm{w}}}$, where I w and I b were the average intensities within a 10 × 10 square pixels inside a white rectangular and a black rectangular, respectively, between two numbers ‘1’ and ‘2’ of the phantom image (Fig. 1(a)) 26. The signal‐to‐noise ratio (SNR) was evaluated using the following formula: $\text{SNR}=\frac{I_{\mathrm{w}}}{{\sigma }_{\mathrm{b}}}$, where I w was the same as above, and the σ b was the standard deviation inside the same black box also mentioned above.…”

Suitability of markerless EPID tracking for tumor position verification in gated radiotherapy

“…Markerless tumor tracking, by means of both kV and MV imaging, is a research area receiving increasing attention in recent years. Studies such as those conducted by Meyer et al, 18 Arimura et al, 19 and more recently by Rottmann et al 20 have demonstrated the feasibility and more favorable advantages of markerless EPID tracking compared to implant-based kV tracking approaches, although these have not yet been applied to RGRT. In this work, the suitability and potential of an in-house clinical tool for markerless position verification of lung tumors during RGRT is investigated.…”