A new version of computer aided screening system in chest photofluorograms

Presents a new system for automated screening of chest photofluorograms taken with high voltage. This system detects and marks the shadows suspected to be abnormal using a procedure consisting of the following three steps: (1) detection of suspicious regions (SR) by a new filter (called Min-/spl phi/DD filter), (2) measurement of features for each SR, and (3) classification of all SRs into two classes (normal or abnormal) by the maximum likelihood method. The Min-/spl phi/DD filter enhances the abnormal shadows. The authors used three filters that have different sizes of masks considering the relation between the size of the filter and the size of the abnormal shadow. They calculated twenty-five features at each SR in Step (2) and designed three classifiers according to the size of the Min-/spl phi/DD filter in Step (3). Fifty-eight chest photofluorograms taken with high voltage were used to evaluate the performance of the system. The recognition rates for the SR's evaluated by the L-method were from 67.5% to 75.5% using five features.<
>