The segmentation of nonsolid pulmonary nodules in CT images

Nonsolid nodules are a common radiographical finding in high resolution CT images of the lung. A main factor in determining a nodules malignancy status is the change in the nodule size over time. A method for automatically segmenting a nonsolid nodule from CT images is presented in this thesis. Precise image segmentation is a prerequisite for determining the volumetric growth rate from multiple image scans and the corresponding nodule malignancy status. There has been limited previous work on a segmentation technique for nonsolid nodules. The methods that have been proposed have lacked clinical validation with a radiologist ground truth and often include smaller datasets. The method in this thesis directly compares radiologist ground truth with our automated method and examines the consistency of growth measurement for further validation. The segmentation method consists of three stages; bilateral noise reduction, a probability based voxel classifier and geometric vessel removal. Parameter optimization and validation of the segmentation algorithm is facilitated with a dataset of 20 nonsolid nodule images in which a radiologist has established ground truth by outlining the boundary of the nodule in each image that it is visible. The optimal parameters were determined using the overlap metric and a training/testing methodology. The automated method achieved an average overlap of 0.43 with the radiologist ground truth. An experiment was conducted to determine whether the radiologist manual boundaries or the automated segmentations were more consistent at measuring the volumetric growth between three time scans of the same nodule. Results were determined for two different growth models (exponential and linear) on a dataset of 25 nonsolid nodules. The growth variation of the automated method was found to be 1.87 compared to the radiologist growth variation of 3.00. This suggests that, if the assumption of consistent nodule growth holds for nonsolid nodules, then the automated method provides a more precise growth rate estimate than the radiologist markings.

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

[2]  Its'hak Dinstein,et al.  Regulated morphological operations , 1999, Pattern Recognit..

[3]  Ming Fang,et al.  Consistent interactive segmentation of pulmonary ground glass nodules identified in CT studies , 2004, SPIE Medical Imaging.

[4]  Rajiv Gupta,et al.  Small pulmonary nodules: evaluation with repeat CT--preliminary experience. , 1999, Radiology.

[5]  Bram van Ginneken,et al.  Computer analysis of computed tomography scans of the lung: a survey , 2006, IEEE Transactions on Medical Imaging.

[6]  Anthony P. Reeves,et al.  Automated volumetric segmentation method for growth consistency of nonsolid pulmonary nodules in high-resolution CT , 2007, SPIE Medical Imaging.

[7]  O. Miettinen,et al.  Survival of Patients with Stage I Lung Cancer Detected on CT Screening , 2008 .

[8]  Gabriel Oliver,et al.  On the use of the overlapping area matrix for image segmentation evaluation: A survey and new performance measures , 2006, Pattern Recognit. Lett..

[9]  Anthony P. Reeves,et al.  Three-Dimensional Shape Analysis Using Moments and Fourier Descriptors , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  J. Goo,et al.  Nodular Ground-Glass Opacities on Thin-section CT: Size Change during Follow-up and Pathological Results , 2007, Korean journal of radiology.

[11]  Geoffrey McLennan,et al.  The Lung Image Database Consortium (LIDC): pulmonary nodule measurements, the variation, and the difference between different size metrics , 2007, SPIE Medical Imaging.

[12]  Hironobu Ohmatsu,et al.  Progression of Focal Pure Ground-Glass Opacity Detected by Low-Dose Helical Computed Tomography Screening for Lung Cancer , 2004, Journal of computer assisted tomography.

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

[14]  Shoji Kido,et al.  Automatic segmentation of pulmonary nodules on CT images by use of NCI lung image database consortium , 2006, SPIE Medical Imaging.

[15]  Iva Petkovska,et al.  The effect of lung volume on nodule size on CT. , 2007, Academic radiology.

[16]  S Sone,et al.  Growth rate of small lung cancers detected on mass CT screening. , 2000, The British journal of radiology.

[17]  Albert C. S. Chung,et al.  Trilateral filtering for biomedical images , 2004, 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821).

[18]  O. Miettinen,et al.  CT screening for lung cancer: frequency and significance of part-solid and nonsolid nodules. , 2002, AJR. American journal of roentgenology.

[19]  Roberto Manduchi,et al.  Bilateral filtering for gray and color images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[20]  Yu Jin Zhang,et al.  A review of recent evaluation methods for image segmentation , 2001, Proceedings of the Sixth International Symposium on Signal Processing and its Applications (Cat.No.01EX467).

[21]  Kenji Suzuki,et al.  Radiologic classification of small adenocarcinoma of the lung: radiologic-pathologic correlation and its prognostic impact. , 2006, The Annals of thoracic surgery.

[22]  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.

[23]  Binsheng Zhao,et al.  Small pulmonary nodules: volumetrically determined growth rates based on CT evaluation. , 2000, Radiology.

[24]  Sang Uk Lee,et al.  Segmentation of ground glass opacities by asymmetric multi-phase deformable model , 2006, SPIE Medical Imaging.