Automated segmentation of a motion mask to preserve sliding motion in deformable registration of thoracic CT Jef Vandemeulebroucke a) Universite ´ de Lyon, CREATIS; CNRS UMR5220; Inserm U1044; INSA-Lyon; Universite ´ Lyon 1, France; Le ´on Be ´rard Cancer Center, F-69373, Lyon, France; and Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague, Czech Republic Olivier Bernard Universite ´ de Lyon, CREATIS; CNRS UMR5220; Inserm U1044; INSA-Lyon; Universite ´ Lyon 1, France Simon Rit Universite ´ de Lyon, CREATIS; CNRS UMR5220; Inserm U1044; INSA-Lyon; Universite ´ Lyon 1, France; and Le ´on Be ´rard Cancer Center, F-69373, Lyon, France Jan Kybic Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague, Czech Republic Patrick Clarysse Universite ´ de Lyon, CREATIS; CNRS UMR5220; Inserm U1044; INSA-Lyon; Universite ´ Lyon 1, France David Sarrut Universite ´ de Lyon, CREATIS; CNRS UMR5220; Inserm U1044; INSA-Lyon; Universite ´ Lyon 1, France; and Le ´on Be ´rard Cancer Center, F-69373, Lyon, France (Received 30 June 2011; revised 31 October 2011; accepted for publication 2 January 2012; published 2 February 2012) Purpose: Deformable registration generally relies on the assumption that the sought spatial trans- formation is smooth. Yet, breathing motion involves sliding of the lung with respect to the chest wall, causing a discontinuity in the motion field, and the smoothness assumption can lead to poor matching accuracy. In response, alternative registration methods have been proposed, several of which rely on prior segmentations. We propose an original method for automatically extracting a particular segmentation, called a motion mask, from a CT image of the thorax. Methods: The motion mask separates moving from less-moving regions, conveniently allowing si- multaneous estimation of their motion, while providing an interface where sliding occurs. The sought segmentation is subanatomical and based on physiological considerations, rather than organ boundaries. We therefore first extract clear anatomical features from the image, with respect to which the mask is defined. Level sets are then used to obtain smooth surfaces interpolating these features. The resulting procedure comes down to a monitored level set segmentation of binary label images. The method was applied to sixteen inhale-exhale image pairs. To illustrate the suitability of the motion masks, they were used during deformable registration of the thorax. Results: For all patients, the obtained motion masks complied with the physiological requirements and were consistent with respect to patient anatomy between inhale and exhale. Registration using the motion mask resulted in higher matching accuracy for all patients, and the improvement was statistically significant. Registration performance was comparable to that obtained using lung masks when considering the entire lung region, but the use of motion masks led to significantly bet- ter matching near the diaphragm and mediastinum, for the bony anatomy and for the trachea. The use of the masks was shown to facilitate the registration, allowing to reduce the complexity of the spatial transformation considerably, while maintaining matching accuracy. Conclusions: We proposed an automated segmentation method for obtaining motion masks, capa- ble of facilitating deformable registration of the thorax. The use of motion masks during registra- tion leads to matching accuracies comparable to the use of lung masks for the lung region but motion masks are more suitable when registering the entire thorax. V C 2012 American Association of Physicists in Medicine. [DOI: 10.1118/1.3679009] Key words: deformable registration, respiratory motion, lung cancer I. INTRODUCTION In radiation therapy, deformable image registration of com- puted tomography (CT) images of the thorax has been exten- sively used for a variety of tasks 1,2 and is a key enabling tool for 4D radiotherapy. 3 Image registration aims at finding a suit- able spatial transformation such that a transformed target image becomes similar to a reference image. The underlying 1006 Med. Phys. 39 (2), February 2012 0094-2405/2012/39(2)/1006/10/$30.00 V C 2012 Am. Assoc. Phys. Med. 1006