Computerized Detection of Pulmonary Nodule Based on Two-Dimensional PCA

The main purpose of pulmonary nodule detection is to classify nodule from the lung computed tomography (CT) images. The variability of class is mainly expected to the grey-level variance, texture differences and shape. The purpose of this study is to develop a nodule detector based on Two-dimensional Principal Component Analysis (2DPCA). We extract the features using 2DPCA from nodule candidate images. Nodule candidates are then classified using threshold. The proposed method significantly reduces false positive (FP) rate. We applied it to Lung Imaging Database Consortium (LIDC) database of National Cancer Institute (NCI). The experimental results show the effectiveness and efficiency of the proposed method. The proposed method achieved 80.60% detection rate with 0.0391 FPs per slice.

[1]  Onur Osman,et al.  Lung nodule diagnosis using 3D template matching , 2007, Comput. Biol. Medicine.

[2]  Xavier Lladó,et al.  False Positive Reduction in Breast Mass Detection Using Two-Dimensional PCA , 2007, IbPRIA.

[3]  James C. Gee,et al.  Pulmonary nodule detection in CT images with quantized convergence index filter , 2006, Medical Image Anal..

[4]  Alejandro F. Frangi,et al.  Two-dimensional PCA: a new approach to appearance-based face representation and recognition , 2004 .

[5]  Guido Governatori,et al.  Agent Computing and Multi-Agent Systems, 10th Pacific Rim International Conference on Multi-Agents, PRIMA 2007, Bangkok, Thailand, November 21-23, 2007. Revised Papers , 2009, PRIMA.

[6]  E. Hoffman,et al.  Lung image database consortium: developing a resource for the medical imaging research community. , 2004, Radiology.

[7]  Tatyana Yakhno,et al.  Advances in Information Systems , 2002, Lecture Notes in Computer Science.

[8]  Hiroshi Fujita,et al.  Automated detection of pulmonary nodules in helical CT images based on an improved template-matching technique , 2001, IEEE Transactions on Medical Imaging.

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

[10]  Jamshid Dehmeshki,et al.  Automated detection of lung nodules in CT images using shape-based genetic algorithm , 2007, Comput. Medical Imaging Graph..

[11]  Serhat Ozekes,et al.  Automatic Lung Nodule Detection Using Template Matching , 2006, ADVIS.

[12]  Chao Wang,et al.  Palmprint Recognition Based on Improved 2DPCA , 2006, PRIMA.