Premium
Technical Note: Image filtering to make computer‐aided detection robust to image reconstruction kernel choice in lung cancer CT screening
Author(s) -
Ohkubo Masaki,
Narita Akihiro,
Wada Shinichi,
Murao Kohei,
Matsumoto Toru
Publication year - 2016
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.4953247
Subject(s) - kernel (algebra) , cad , artificial intelligence , hounsfield scale , receiver operating characteristic , iterative reconstruction , mathematics , computer science , computer aided diagnosis , filter (signal processing) , standard deviation , pattern recognition (psychology) , computer vision , computed tomography , radiology , medicine , statistics , combinatorics , engineering drawing , engineering
Purpose: In lung cancer computed tomography (CT) screening, the performance of a computer‐aided detection (CAD) system depends on the selection of the image reconstruction kernel. To reduce this dependence on reconstruction kernels, the authors propose a novel application of an image filtering method previously proposed by their group. Methods: The proposed filtering process uses the ratio of modulation transfer functions (MTFs) of two reconstruction kernels as a filtering function in the spatial‐frequency domain. This method is referred to as MTF ratio filtering. Test image data were obtained from CT screening scans of 67 subjects who each had one nodule. Images were reconstructed using two kernels: f STD (for standard lung imaging) and f SHARP (for sharp edge‐enhancement lung imaging). The MTF ratio filtering was implemented using the MTFs measured for those kernels and was applied to the reconstructed f SHARP images to obtain images that were similar to the f STD images. A mean filter and a median filter were applied (separately) for comparison. All reconstructed and filtered images were processed using their prototype CAD system. Results: The MTF ratio filtered images showed excellent agreement with the f STD images. The standard deviation for the difference between these images was very small, ∼6.0 Hounsfield units (HU). However, the mean and median filtered images showed larger differences of ∼48.1 and ∼57.9 HU from the f STD images, respectively. The free‐response receiver operating characteristic (FROC) curve for the f SHARP images indicated poorer performance compared with the FROC curve for the f STD images. The FROC curve for the MTF ratio filtered images was equivalent to the curve for the f STD images. However, this similarity was not achieved by using the mean filter or median filter. Conclusions: The accuracy of MTF ratio image filtering was verified and the method was demonstrated to be effective for reducing the kernel dependence of CAD performance.