Method for adaptive computer-aided detection of pulmonary nodules in thoracic computed tomography images using hierarchical vector quantization and apparatus for same
Provided are an apparatus and method for fast and adaptive computer-aided detection of pulmonary nodules and differentiation of malignancy from benignancy in thoracic CT images using a hierarchical vector quantization scheme. Anomalous pulmonary nodules are detected by obtaining a two-dimensional (2D) feature model of a pulmonary nodule, segmenting the pulmonary nodule by performing vector quantification to expand the 2D feature model to a three-dimensional (3D) model, and displaying image information representing whether the pulmonary nodule is benign, based upon the 3D model expanded from the 2D feature model, with duplicate information eliminated by performing feature reduction performed using a principal component analysis and a receiver operating characteristics area under the curve merit analysis. A textural feature analysis detects an anomalous pulmonary nodule, and 2D texture features are calculated from 3D volumetric data to provide improved gain compared to calculation from a single slice of 3D data.
1. A method for detecting anomalous pulmonary nodules, the method comprising:
obtaining a two-dimensional (2D) feature model of a pulmonary nodule;
segmenting the pulmonary nodule by performing vector quantification to expand the 2D feature model to a three-dimensional (3D) model; and
displaying, on a display, image information representing whether the pulmonary nodule is benign, based upon the 3D model expanded from the 2D feature model.
2. The method of claim 1 , further comprising performing feature reduction.
3. The method of claim 2 , wherein the feature reduction eliminates duplicate information.
4. The method of claim 3 , wherein the feature reduction is performed using a Principal Component Analysis.
5. The method of claim 3 , wherein the feature reduction is performed using a receiver operating characteristic area under curve merit analysis.
6. The method of claim 1 , further comprising performing a textural feature analysis to detect an anomalous pulmonary nodule.
7. The method of claim 6 , further comprising calculating 2D texture features from 3D volumetric data to provide improved gain.
8. An apparatus for detecting anomalous pulmonary nodules, the apparatus comprising:
a controller configured to obtain a two-dimensional (2D) feature model of a pulmonary nodule, to segment the pulmonary nodule by performing vector quantification to expand the 2D feature model to a three-dimensional (3D) model, and to display image information representing whether the pulmonary nodule is benign, based upon the 3D model expanded from the 2D feature model.
9. The apparatus of claim 8 , wherein the controller is further configured to eliminate duplicate information by performing feature reduction.
10. The apparatus of claim 9 , wherein the feature reduction is performed using a Principal Component Analysis.
11. The apparatus of claim 9 , wherein the feature reduction is performed using a receiver operating characteristic area under the curve merit analysis.
12. The apparatus of claim 8 , wherein the controller is further configured to perform a textural feature analysis to detect an anomalous pulmonary nodule.
13. The apparatus of claim 8 , wherein calculating 2D texture features from 3D volumetric data provides improved gain.