Perfusion computed tomography (CT) has been widely used to assess the response of lung cancer treatment. However,
the respiratory motion has become the major obstacle to the pixel-based time-series analyses. To minimize the effect of
respiratory motion and investigate the feasibility of perfusion CT for prediction of tumor response and prognosis of non-small cell lung cancer, an image registration framework is proposed by unifying a virtual 3D local rigid alignment and 3D global non-rigid alignment. The basic idea is to use the perfusion CT data and routine whole-lung CT data,
respectively. To realize this idea, maximum intensity projection (MIP) of the time series perfusion CT images is first
generated, followed by decomposing the MIP image into region of interest (ROI), which is located on a lung nodule. For the ROI, affine transformation model based on mutual information is performed to estimate the virtual three dimensional linear deformations. Following that, the 3D thin plate spline (TPS) is carried out to establish the pixel correspondence between the paired volumetric CT data. The control points for the TPS are global feature points chosen from the boundary of whole lung, which are automatically derived by using the iterative closest point (ICP) matching Algorithm. The proposed algorithm has been evaluated both qualitatively and quantitatively on real lung perfusion CT datasets. From the time-intensity curves and perfusion parameters, the experiment results suggest that the findings on perfusion CT images obtained after treatment may be considered as a significant predictor of lung cancer.
Image segmentation for the demarcation of pulmonary nodules in CT images is intrinsically an arduous task. The
difficulty can be summarized into two aspects. Firstly, lung tumor can be various in terms of physical densities in
pulmonary regions, implying the different interpretation as a mixture of GGO and solid nodules. Hence, processing of
lung CT images may generally encounter tissue inhomogeneous problem. The second factor that complicates the task of
nodule demarcation is the irregular shapes that most nodules are directly connected to other structures sharing the similar
density profile. In this paper, an image segmentation framework is proposed by unifying the techniques of statistical
region merging and conditional random field (CRF) with graph cut optimization to address the difficult problem of GGO
nodules quantification in CT images. Different from traditional segmentation methods that use pixel-based approach
such as region growing and morphological constraints, we employ a hierarchical segmentation tree to alleviate the effect
of inhomogeneous attenuation. In addition to building perceptual prominent regions, we perform inference in CRF model
based on restricting the pool of segmented regions. Following that, an inference CRF model is carried out to detect and
localize individual object instances in CT images. The proposed algorithm is evaluated with four sets of manual
delineations on 77 lung CT images. Incorporating with the efficiency and accuracy of pulmonary nodules segmentation
method proposed in this paper, a computer aided system is hence feasible to develop related clinical application.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.