Automatic analysis of 3D low dose CT images for early diagnosis of lung cancer

Our long term research goal is to develop a fully automated, image-based diagnostic system for early diagnosis of pulmonary nodules that may lead to lung cancer. This paper focuses on monitoring the development of lung nodules detected in successive chest low dose (LD) CT scans of a patient. We propose a new methodology for 3D LDCT data registration which is non-rigid and involves two steps: (i) global target-to-prototype alignment of one scan to another using the learned prior appearance model followed by (ii) local alignment in order to correct for intricate relative deformations. After equalizing signals for two subsequent chest scans, visual appearance of these chest images is described using a Markov-Gibbs random field (MGRF) model with multiple pairwise interaction. An affine transformation that globally registers a target to a prototype is estimated by the gradient ascent-based maximization of a special Gibbs energy function. To get an accurate visual appearance model, we developed a new approach to automatic selection of most characteristic second-order cliques that describe pairwise interactions in the LDCT data. To handle local deformations, we displace each voxel of the target over evolving closed equi-spaced surfaces (iso-surfaces) to closely match the prototype. The evolution of the iso-surfaces is guided by a speed function in the directions that minimize distances between the corresponding voxel pairs on the iso-surfaces in both the data sets. Preliminary results on the 135 LDCT data sets from 27 patients show that the proposed accurate registration could lead to precise diagnosis and identification of the development of the detected pulmonary nodules.

[1]  Anthony P. Reeves,et al.  Three-dimensional segmentation and growth-rate estimation of small pulmonary nodules in helical CT images , 2003, IEEE Transactions on Medical Imaging.

[2]  W. Heindel,et al.  Volumetric measurements of pulmonary nodules at multi-row detector CT: in vivo reproducibility , 2003, European Radiology.

[3]  Ayman El-Baz,et al.  Quantitative Nodule Detection in Low Dose Chest CT Scans: New Template Modeling and Evaluation for CAD System Design , 2005, MICCAI.

[4]  Eric A. Hoffman,et al.  3D intersubject warping and registration of pulmonary CT images for a human lung model , 2002, SPIE Medical Imaging.

[5]  G. Chatellier,et al.  Pulmonary nodules: preliminary experience with three-dimensional evaluation. , 2004, Radiology.

[6]  Berthold K. P. Horn,et al.  Closed-form solution of absolute orientation using unit quaternions , 1987 .

[7]  Jiang Hsieh,et al.  Theoretical prediction of lung nodule measurement accuracy under different acquisition and reconstruction conditions , 2004, SPIE Medical Imaging.

[8]  Colin Studholme,et al.  An overlap invariant entropy measure of 3D medical image alignment , 1999, Pattern Recognit..

[9]  J A Sethian,et al.  A fast marching level set method for monotonically advancing fronts. , 1996, Proceedings of the National Academy of Sciences of the United States of America.

[10]  Li Fan,et al.  Integrated approach to 3D warping and registration from lung images , 1999, Optics & Photonics.

[11]  Aly A. Farag,et al.  A Framework for Automatic Segmentation of Lung Nodules from Low Dose Chest CT Scans , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[12]  Antoni B. Chan,et al.  On measuring the change in size of pulmonary nodules , 2006, IEEE Transactions on Medical Imaging.

[13]  Michael F. McNitt-Gray,et al.  Method for segmenting chest CT image data using an anatomical model: preliminary results , 1997, IEEE Transactions on Medical Imaging.

[14]  Aly A. Farag,et al.  Precise segmentation of multimodal images , 2006, IEEE Transactions on Image Processing.

[15]  Anthony P. Reeves,et al.  THREE-DIMENSIONAL MULTICRITERION AUTOMATIC SEGMENTATION OF PULMONARY NODULES OF HELICAL COMPUTED TOMOGRAPHY IMAGES , 1999 .

[16]  Paul A. Viola,et al.  Alignment by Maximization of Mutual Information , 1995, Proceedings of IEEE International Conference on Computer Vision.

[17]  Simina C. Fluture,et al.  Small pulmonary nodules: reproducibility of three-dimensional volumetric measurement and estimation of time to follow-up CT. , 2004, Radiology.

[18]  J. Goo,et al.  Volumetric measurement of synthetic lung nodules with multi-detector row CT: effect of various image reconstruction parameters and segmentation thresholds on measurement accuracy. , 2005, Radiology.

[19]  Joseph M. Reinhardt,et al.  3D pulmonary CT image registration with a standard lung atlas , 2000, Medical Imaging.

[20]  O. Martínez,et al.  Amplification of nanosecond pulses in dye-laser amplifiers , 1987 .

[21]  Georgy L. Gimel'farb,et al.  Image Textures and Gibbs Random Fields , 1999, Computational Imaging and Vision.

[22]  A. Reeves,et al.  Two-dimensional multi-criterion segmentation of pulmonary nodules on helical CT images. , 1999, Medical physics.

[23]  Margrit Betke,et al.  Chest CT: automated nodule detection and assessment of change over time--preliminary experience. , 2001, Radiology.

[24]  Ayman El-Baz,et al.  New Motion Correction Models for Automatic Identification of Renal Transplant Rejection , 2007, MICCAI.

[25]  Chang Wen Chen,et al.  Model supported image registration and warping for change detection in computer-aided diagnosis , 2000, Proceedings 29th Applied Imagery Pattern Recognition Workshop.

[26]  Robert J. Maciunas,et al.  Registration of head CT images to physical space using a weighted combination of points and surfaces [image-guided surgery] , 1998, IEEE Transactions on Medical Imaging.

[27]  I. El Naqa,et al.  Automated breathing motion tracking for 4D computed tomography , 2003, 2003 IEEE Nuclear Science Symposium. Conference Record (IEEE Cat. No.03CH37515).

[28]  Margrit Betke,et al.  Small pulmonary nodules: volume measurement at chest CT--phantom study. , 2003, Radiology.

[29]  Max A. Viergever,et al.  A survey of medical image registration , 1998, Medical Image Anal..

[30]  G. Christensen,et al.  A method for the reconstruction of four-dimensional synchronized CT scans acquired during free breathing. , 2003, Medical physics.

[31]  D. Naidich,et al.  Computer-aided diagnosis and the evaluation of lung disease. , 2004, Journal of thoracic imaging.

[32]  Lawrence Dougherty,et al.  Alignment of CT lung volumes with an optical flow method. , 2003, Academic radiology.

[33]  Aly A. Farag,et al.  Appearance Models for Robust Segmentation of Pulmonary Nodules in 3D LDCT Chest Images , 2006, MICCAI.

[34]  Daniel Rueckert,et al.  Nonrigid registration using free-form deformations: application to breast MR images , 1999, IEEE Transactions on Medical Imaging.

[35]  Dorin Comaniciu,et al.  Robust anisotropic Gaussian fitting for volumetric characterization of Pulmonary nodules in multislice CT , 2005, IEEE Transactions on Medical Imaging.