Automatic segmentation of phase‐correlated CT scans through nonrigid image registration using geometrically regularized free‐form deformation

Abstract

Conventional radiotherapy is planned using free-breathing computed tomography (CT), ignoring the motion and deformation of the anatomy from respiration. New breath-hold-synchronized, gated, and four-dimensional (4D) CT acquisition strategies are enabling radiotherapy planning utilizing a set of CT scans belonging to different phases of the breathing cycle. Such 4D treatment planning relies on the availability of tumor and organ contours in all phases. The current practice of manual segmentation is impractical for 4D CT, because it is time consuming and tedious. A viable solution is registration-based segmentation, through which contours provided by an expert for a particular phase are propagated to all other phases while accounting for phase-to-phase motion and anatomical deformation. Deformable image registration is central to this task, and a free-form deformation-based nonrigid image registration algorithm will be presented. Compared with the original algorithm, this version uses novel, computationally simpler geometric constraints to preserve the topology of the dense control-point grid used to represent free-form deformation and prevent tissue fold-over. Using mean squared difference as an image similarity criterion, the inhale phase is registered to the exhale phase of lung CT scans of five patients and of characteristically low-contrast abdominal CT scans of four patients. In addition, using expert contours for the inhale phase, the corresponding contours were automatically generated for the exhale phase. The accuracy of the segmentation (and hence deformable image registration) was judged by comparing automatically segmented contours with expert contours traced directly in the exhale phase scan using three metrics: volume overlap index, root mean square distance, and Hausdorff distance. The accuracy of the segmentation (in terms of radial distance mismatch) was approximately 2 mm in the thorax and 3 mm in the abdomen, which compares favorably to the accuracies reported elsewhere. Unlike most prior work, segmentation of the tumor is also presented. The clinical implementation of 4D treatment planning is critically dependent on automatic segmentation, for which is offered one of the most accurate algorithms yet presented.

An evaluation of planning techniques for stereotactic body radiation therapy in lung tumors

“…The voxel displacement was obtained by the B-splines based cubic interpolation of the coordinates of the control points in the voxel's neighborhood. The accuracy of this algorithm in the thoracic anatomy has been previously reported [31].…”

“…The displacement of each voxel with respect to a reference image set (the reference image set in this study corresponded to end-exhale) was obtained by registering each of the 3D CT images in the 4D CT to the reference CT image set. The image registration algorithm used in this study was a previously published elastic registration algorithm [31]. Details of the algorithm can be found in the above reference but are briefly summarized here.…”

Recent Advances and Challenges in Adaptive Radiotherapy for Patients with Locally Advanced NSCLC

“…However, it is time-intensive to contour tumor target and Organ at Risk (OAR) for each of these plan adaptations [36]. To address this issue, DIR algorithms were employed to propagate OAR contours automatically from the original planning CT images to during-RT images [37,38]. Due to limited contrasts and gradients in during-RT images, the registrations could have large errors, and the propagated volumes should be thoroughly assessed [6].…”

Model-based mapping of a nonrigid image registration algorithm to heterogeneous architectures

“…One of the most robust and popular ways of doing this is the one proposed by Rueckert et al [7] [16]. It has been shown in [17] that this method properly corrects soft tissue deformation while maintaining the consistent characteristics of the body organs. This technique is flexible enough to be applicable to all of the organs of the body and is a popular choice for automatic image registration.…”