Robust CT Synthesis for Radiotherapy Planning: Application to the Head and Neck Region
In this work, we propose to tackle the problem of magnetic resonance (MR)-based radiotherapy treatment planning in the head & neck area by synthesising computed tomography (CT) from MR images using an iterative multi-atlas approach. The proposed metho
- PDF / 929,470 Bytes
- 9 Pages / 439.363 x 666.131 pts Page_size
- 38 Downloads / 186 Views
Translational Imaging Group, CMIC, University College London, London, UK 2 Dementia Research Centre, Institute of Neurology, UCL, London, UK 3 The Institute of Cancer Research, Radiotherapy Imaging Department, London, UK 4 Radiation Physics Group, UCL Medical Physics and Bioengineering, London, UK 5 Centre for Medical Image Computing, UCL, London, UK 6 Centre for Medical Imaging, UCL, London, UK 7 Department of Radiology, University College London Hospitals, London, UK 8 Institute of Nuclear Medicine, UCL, London, UK 9 Centre for Medical Radiation Physics, University of Wollongong, NSW, Australia Abstract. In this work, we propose to tackle the problem of magnetic resonance (MR)-based radiotherapy treatment planning in the head & neck area by synthesising computed tomography (CT) from MR images using an iterative multi-atlas approach. The proposed method relies on pre-acquired pairs of non-rigidly aligned T2-weighted MRI and CT images of the neck. To synthesise a pseudo CT, all the MRIs in the database are first registered to the target MRI using a robust affine followed by a deformable registration. An initial pseudo CT is obtained by fusing the mapped atlases according to their morphological similarity to the target. This initial pseudo CT is then combined with the target MR image in order to improve both the registration and fusion stages and refine the synthesis in the bone region. Results showed that the proposed iterative CT synthesis algorithm is able to generate pseudo CT images in a challenging region for registration algorithms. We demonstrate that the robust affine decreases the overall absolute error compared to a single affine transformation, mainly in images with small axial field-of-view, whilst the bone refinement process further reduces the error in the bone region, increasing image sharpness.
1
Introduction
Magnetic resonance imaging (MRI) is often preferred over computed tomography (CT) as a structural imaging modality, mainly for its excellent soft-tissue contrast. However, MRI does not provide photon density information, which is essential for several applications such as performing dosimetry for MR-based radiotherapy treatment planning (RTP) or attenuation correction in the context of Positron Emission Tomography (PET)/MR scanners. To overcome this limitation, a solution is to recreate a CT image from the available MR images. c Springer International Publishing Switzerland 2015 N. Navab et al. (Eds.): MICCAI 2015, Part II, LNCS 9350, pp. 476–484, 2015. DOI: 10.1007/978-3-319-24571-3_57
Robust CT Synthesis for Radiotherapy Planning
477
Several methods exist to obtain synthetic CT images and many have been applied to RTP. Results presented in [1] are obtained from a Gaussian mixture regression model linking the MRI intensity values to the CT Hounsfield units (HU). In [2], bones are manually segmented and the MRI intensity values are converted to HU using a dual model, within and outside of the bone class. Other approaches, called registration- or atlas-based methods, rely on a single [3] or a datab
Data Loading...
