| 摘要 |
An automated method, and a computer storage medium storing instructions for executing the method, for analysis of image features in lung nodule detection in a chest radiographic image represented by digital data, including preprocessing the image to identify candidate nodules in the image; establishing a region of interest (ROI) including a candidate nodule identified in the preprocessing step; performing image enhancement of the candidate nodule within the ROI; obtaining a histogram of accumulated edge gradients as a function of radial angles withing the ROI after performing the image enhancement; and determining whether the candidate nodule is a false positive based on the obtained histogram. A 64x64-pixel region of interest (ROI) centered at the candidate location is used. The contrast of the ROI is improved by a two-dimensional background subtraction. A nodule shape matched filter is used for enhancement of the nodular pattern located in the central area of the ROI. Analysis of the histogram resulted in identification of seven features, including (1) a maximum histogram value, (2) a minimum histogram value, (3) a partial average value of the histogram, (4) a standard deviation of the histogram values near the radial axis, (5) a partial standard deviation of histogram values, (6) a width of the histogram including both sides from zero degrees of the radial angle, at a predetermined histogram value, and (7) a ratio of a maximum histogram value near the radial axis to a maximum histogram value in two predetermined outside ranges of the radial axis, useful for the identification and elimination of false positives. |
