Deep Feature Stability Analysis Using CT Images of a Physical Phantom across Scanner Manufacturers, Cartridges, Pixel Sizes, and Slice Thickness
Open Access
- 1 June 2020
- journal article
- research article
- Published by MDPI AG in Tomography
- Vol. 6 (2) , 250-260
Abstract
Image acquisition parameters for computed tomography scans such as slice thickness and field of view may vary depending on tumor size and site. Recent studies have shown that some radiomics features were dependent on voxel size (= pixel size × slice thickness), and with proper normalization, this voxel size dependency could be reduced. Deep features from a convolutional neural network (CNN) have shown great promise in characterizing cancers. However, how do these deep features vary with changes in imaging acquisition parameters? To analyze the variability of deep features, a physical radiomics phantom with 10 different material cartridges was scanned on 8 different scanners. We assessed scans from 3 different cartridges (rubber, dense cork, and normal cork). Deep features from the penultimate layer of the CNN before (pre-rectified linear unit) and after (post-rectified linear unit) applying the rectified linear unit activation function were extracted from a pre-trained CNN using transfer learning. We studied both the interscanner and intrascanner dependency of deep features and also the deep features' dependency over the 3 cartridges. We found some deep features were dependent on pixel size and that, with appropriate normalization, this dependency could be reduced. False discovery rate was applied for multiple comparisons, to mitigate potentially optimistic results. We also used stable deep features for prognostic analysis on 1 non–small cell lung cancer data set.Keywords
This publication has 17 references indexed in Scilit:
- Can radiomics features be reproducibly measured from CBCT images for patients with non‐small cell lung cancer?Medical Physics, 2015
- Measuring Computed Tomography Scanner Variability of Radiomics FeaturesInvestigative Radiology, 2015
- Exploring Variability in CT Characterization of Tumors: A Preliminary Phantom StudyTranslational Oncology, 2014
- Reproducibility and Prognosis of Quantitative Features Extracted from CT ImagesTranslational Oncology, 2014
- High quality machine‐robust image features: Identification in nonsmall cell lung cancer computed tomography imagesMedical Physics, 2013
- Receiver Operating Characteristic (ROC) Curve Analysis for Medical Diagnostic Test Evaluation.2013
- Radiomics: the process and the challengesMagnetic Resonance Imaging, 2012
- Radiomics: Extracting more information from medical images using advanced feature analysisEuropean Journal of Cancer, 2012
- Variability of textural features in FDG PET images due to different acquisition modes and reconstruction parametersActa Oncologica, 2010
- A Concordance Correlation Coefficient to Evaluate Reproducibility1989