Deep Learning–based Image Conversion of CT Reconstruction Kernels Improves Radiomics Reproducibility for Pulmonary Nodules or Masses
Jooae Choe, Sang Min Lee , Kyung-Hyun Do, Gaeun Lee, June-Goo Lee, Sang Min Lee, Joon Beom Seo
Author Affiliations
From the Department of Radiology and Research Institute of Radiology (J.C., S.M.L.[1], K.H.D., S.M.L.[2], J.B.S.) and Department of Convergence Medicine (G.L., J.G.L.), University of Ulsan College of Medicine, Asan Medical Center, 88 Olympic-ro 43 Gil, Songpa-gu, Seoul 138-736, Korea.
Address correspondence to S.M.L. (e-mail: sangmin.lee.md@gmail.com).
Published Online:Jun 18 2019https://doi.org/10.1148/radiol.2019181960
See editorial byChang Min Park
Sections
Full text
PDF
Tools
Share
Abstract
CT image conversion using a convolutional neural network can reduce the effect of different reconstruction kernels on radiomic parameters. This will facilitate comparison of image features derived from different CT scanners.

Background
Intratumor heterogeneity in lung cancer may influence outcomes. CT radiomics seeks to assess tumor features to provide detailed imaging features. However, CT radiomic features vary according to the reconstruction kernel used for image generation.

Purpose
To investigate the effect of different reconstruction kernels on radiomic features and assess whether image conversion using a convolutional neural network (CNN) could improve reproducibility of radiomic features between different kernels.

Materials and Methods
In this retrospective analysis, patients underwent non–contrast material–enhanced and contrast material–enhanced axial chest CT with soft kernel (B30f) and sharp kernel (B50f) reconstruction using a single CT scanner from April to June 2017. To convert different kernels without sinogram, the CNN model was developed using residual learning and an end-to-end way. Kernel-converted images were generated, from B30f to B50f and from B50f to B30f. Pulmonary nodules or masses were semiautomatically segmented and 702 radiomic features (tumor intensity, texture, and wavelet features) were extracted. Measurement variability in radiomic features was evaluated using the concordance correlation coefficient (CCC).

Results
A total of 104 patients were studied, including 54 women and 50 men, with pulmonary nodules or masses (mean age, 63.2 years ± 10.5). The CCC between two readers using the same kernel was 0.92, and 592 of 702 (84.3%) of the radiomic features were reproducible (CCC ≥ 0.85); using different kernels, the CCC was 0.38 and only 107 of 702 (15.2%) of the radiomic features were reliable. Texture features and wavelet features were predominantly affected by reconstruction kernel (CCC, from 0.88 to 0.61 for texture features and from 0.92 to 0.35 for wavelet features). After applying image conversion, CCC improved to 0.84 and 403 of 702 (57.4%) radiomic features were reproducible (CCC, 0.85 for texture features and 0.84 for wavelet features).

Conclusion
Chest CT image conversion using a convolutional neural network effectively reduced the effect of two different reconstruction kernels and may improve the reproducibility of radiomic features in pulmonary nodules or masses.

© RSNA, 2019